diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000000000000000000000000000000000000..482ced4679301bf287ebb310bdd1790eb4514232 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..abb2327740c65c78fa57de0b931ce3a9b171c301 --- /dev/null +++ b/config.json @@ -0,0 +1,49 @@ +{ + "_attn_implementation_autoset": true, + "_name_or_path": "/monster/data/cl/cl-QwQ-32B-Preview-qwq-32b-preview-pack1-lr2.2e-05-cosine-bs2--mtl5952-seq8192-diaphragmatic-28_13-23-12/checkpoint-220", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "max_position_embeddings": 32768, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "quantization_config": { + "bits": 4, + "checkpoint_format": "gptq", + "desc_act": true, + "dynamic": null, + "group_size": 32, + "lm_head": false, + "meta": { + "damp_auto_increment": 0.0015, + "damp_percent": 0.1, + "quantizer": "gptqmodel:1.2.2", + "static_groups": false, + "true_sequential": true, + "uri": "https://github.com/modelcloud/gptqmodel" + }, + "quant_method": "gptq", + "sym": true, + "true_sequential": true + }, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.46.3", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/model-00001-of-00067.safetensors b/model-00001-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..538e8c60e233ae35921bee53a96005f88bdd6862 --- /dev/null +++ b/model-00001-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0fddf319ca50e1a0fa22da90db822ab2009acb195a5c776b820fc3b01024454 +size 1557135504 diff --git a/model-00002-of-00067.safetensors b/model-00002-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2560d78c2ce0b8a6b6704d069535f73bd1970a4 --- /dev/null +++ b/model-00002-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3dc344c7ff2ff9bbf46bc0f75248e9c192fecd7c0e485fc0b5deb7682d24e2a +size 10360 diff --git a/model-00003-of-00067.safetensors b/model-00003-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff07d7ca091919fab0f74de7dd02613cf2117544 --- /dev/null +++ b/model-00003-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48357a297e1c474db5f7424e666630620fd973e409e9528a1a3ccdd3dc341d9 +size 1557135488 diff --git a/model-00004-of-00067.safetensors b/model-00004-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5031626f0b8ef008e7826894bf02a63d54d6b6e7 --- /dev/null +++ b/model-00004-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b2dfcf215f5735ab23fd3d015fad26db3b60d479cf82057aaadf6c170dcd40 +size 282158672 diff --git a/model-00005-of-00067.safetensors b/model-00005-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a00827d0b72e207c872417038c1abbffb3acb06 --- /dev/null +++ b/model-00005-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c30ac3d200fbf40c7055cad47de36d76e70c7b856f56a5e0b38794752346cdb1 +size 282158672 diff --git a/model-00006-of-00067.safetensors b/model-00006-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d20660406cd14d1f864575198393abf2296bf3f0 --- /dev/null +++ b/model-00006-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89bd5679aa2e018cfff205b2c5ee30de8b89428c45a366ca7e972847bf98963 +size 282158672 diff --git a/model-00007-of-00067.safetensors b/model-00007-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ac51a8dc40ace0050de19eed4817e83fa3ac860 --- /dev/null +++ b/model-00007-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce7dad3ecc5d71e354181ba3a80c51f4eaff5f4d2ede0dd8be76e3a8e4509acc +size 282158672 diff --git a/model-00008-of-00067.safetensors b/model-00008-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..762db564777e096ba1624e852cb7df1d6125be51 --- /dev/null +++ b/model-00008-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f29686a025be8d8be28999d7c907dfb1deb811fe4d88ef100d44c3a4ca024c +size 282158672 diff --git a/model-00009-of-00067.safetensors b/model-00009-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c137a4d40c48e87b4c75fcf0631da5b9608934bd --- /dev/null +++ b/model-00009-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:338848e7978a3326a56a6e29bb210138ad16b7d1517278e601847f7b0f559730 +size 282158672 diff --git a/model-00010-of-00067.safetensors b/model-00010-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34bc15afa92b5dcd0e6dcb638c1ac0db3f192e4e --- /dev/null +++ b/model-00010-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2608970d510b77b527ca9a11c6a3f2207e5e4b5db3d483453993b69bb39b841 +size 282158672 diff --git a/model-00011-of-00067.safetensors b/model-00011-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1dc020367bc9dc32f5e9368fced199797486a4b --- /dev/null +++ b/model-00011-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f241a7d02075688e89652c8e08918ce8589ae63153e89e1a01d65e100a5b010 +size 282158672 diff --git a/model-00012-of-00067.safetensors b/model-00012-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2cd52061f757b7a128c73f1fe48c3296ae4cf3e --- /dev/null +++ b/model-00012-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a2d1e4dade761784c2c566c511c1d1a75574455797e4b6cc834109ffcbadf3 +size 282158672 diff --git a/model-00013-of-00067.safetensors b/model-00013-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d80077fba1e47bdab17756ed812236ece7f0994 --- /dev/null +++ b/model-00013-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526dd898c8a8412b5e24c295548514ed6831fcd43bf6c1753185dd9925535f1b +size 282158672 diff --git a/model-00014-of-00067.safetensors b/model-00014-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6d9ec72ba122bd1387a25cd3fc7ef0f77f166a1 --- /dev/null +++ b/model-00014-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:495b817d0712801fd5bfbbddafbace91d9181b288a7e4e05cfc075456bc41cb6 +size 282158704 diff --git a/model-00015-of-00067.safetensors b/model-00015-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..935b1c435013168a10916d78c24d2386518f5c14 --- /dev/null +++ b/model-00015-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995574945a25fd8e0b0c5798f59077e18524eeb03c707d8283ac6e1ba6fd12d7 +size 282158704 diff --git a/model-00016-of-00067.safetensors b/model-00016-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..251d019a61dfe603812cfef5a3c5bb7ecc979c5d --- /dev/null +++ b/model-00016-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcf616ceec5f46cc06bafd44a22a8404b8a6c1d72e075f29007dcfa06362bdf +size 282158704 diff --git a/model-00017-of-00067.safetensors b/model-00017-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..064de3fe7fdaec9d1bcf4314f9af308dccf9adf0 --- /dev/null +++ b/model-00017-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:943cb9452eefd8d0ac74edf9532da81be903534a32058ce45ac24f4a97cbf87c +size 282158704 diff --git a/model-00018-of-00067.safetensors b/model-00018-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ad8ef20408ea4a53f5c1848cc5780d5b016c58d0 --- /dev/null +++ b/model-00018-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6815439c1635df66209edb087e87431adb6ad07fb1e3506c4195b18d219f99 +size 282158704 diff --git a/model-00019-of-00067.safetensors b/model-00019-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb03049d5c5cd62e1316ef3851011b6c938176d2 --- /dev/null +++ b/model-00019-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dea61bf3b865241bc4922a51afaca12c217c01126d81f0aaa4759b55a4f17f9 +size 282158704 diff --git a/model-00020-of-00067.safetensors b/model-00020-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..234791bf0f832fbfd2022b673bd29b2183650e28 --- /dev/null +++ b/model-00020-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e354351b96b9a97694798f4cac17b3da5d5ceec1890da64e067d931047a09c +size 282158704 diff --git a/model-00021-of-00067.safetensors b/model-00021-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e434c04ce27b320161c76fd270ad39262fb5c3e --- /dev/null +++ b/model-00021-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58902b609aad9aa80f34539efe3e172cc30ffe83e654c3a1c211fe566e74d1e9 +size 282158704 diff --git a/model-00022-of-00067.safetensors b/model-00022-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12b0b3d6894c1335bf1fdee2f2076f588a791c87 --- /dev/null +++ b/model-00022-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d3710db175eca279f39fe5d02335a542dfcb33ac29658538779d0514ae225a +size 282158704 diff --git a/model-00023-of-00067.safetensors b/model-00023-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..856fad2b2837d675224f2bb4937851570124a77f --- /dev/null +++ b/model-00023-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5f4d373d2d03b9b30df4e3fa30b1f7f827f75fbc3061d370305099ec612c30 +size 282158704 diff --git a/model-00024-of-00067.safetensors b/model-00024-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d21407dc6e7e1641ee5cff5b76749c864e60b5f8 --- /dev/null +++ b/model-00024-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a983d2b6d7a271d6c771813dcf763a521dac98d09fa5dab9a2eb9237303d2ee +size 282158704 diff --git a/model-00025-of-00067.safetensors b/model-00025-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21a87cf5db404a2b61e65690877008b6515bd440 --- /dev/null +++ b/model-00025-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b54b042baf2d56cbb0062cce69d9fc529d5be8f455687ef7162e225568ae7920 +size 282158704 diff --git a/model-00026-of-00067.safetensors b/model-00026-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec352843010aa80c0f3816714d04dba1eba9c6f2 --- /dev/null +++ b/model-00026-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c63c7302f750490d6e6e687f3295dc8594c05d38b2a72f4f27e47d557e2c3a +size 282158704 diff --git a/model-00027-of-00067.safetensors b/model-00027-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab9da3d671d3325fcb64988e6a72d719604503ab --- /dev/null +++ b/model-00027-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f824baf11c8925967aada4d3d10516922f10dab2925b61b9a1a6b0400ce2d0c +size 282158704 diff --git a/model-00028-of-00067.safetensors b/model-00028-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4b597c308467777673271da16b71a95c891cdd23 --- /dev/null +++ b/model-00028-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f41381daf913cd87f042a7a4fc0ac0447bb2c1faabf11a14a5bd78c96d0d5b +size 282158704 diff --git a/model-00029-of-00067.safetensors b/model-00029-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..206989e7cda434dff1bcafb91fb55218f2f3abd8 --- /dev/null +++ b/model-00029-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a3a0204fb3e9a6a647435585c2d9de4f8e33c3aabea9e94402282c1958515a +size 282158704 diff --git a/model-00030-of-00067.safetensors b/model-00030-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1fe30fefd304949fcab3ac02b4580e5a6aea2c07 --- /dev/null +++ b/model-00030-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af00ec017260391786a05ea96b812a4603182c4255b15bc6c60206ade56aca8 +size 282158704 diff --git a/model-00031-of-00067.safetensors b/model-00031-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2478381635b43c07658912ea2a95aab31b5267e7 --- /dev/null +++ b/model-00031-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682badd76e613a15080084ef4747979281bddb765dc881962e28500139319c26 +size 282158704 diff --git a/model-00032-of-00067.safetensors b/model-00032-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cdfef431423741a26f6fbdfeccb1dc7906fd185 --- /dev/null +++ b/model-00032-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595146d3da976be1604fe371672375590819f909c4cc50ca8aa2fe37bb0f2add +size 282158704 diff --git a/model-00033-of-00067.safetensors b/model-00033-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d6b8e074659a11bb15aebb7de738eb72d275121d --- /dev/null +++ b/model-00033-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fbaedfb71a79a34270b3ca11ec206832065a2edb88436c3b8653dec1e6f67c6 +size 282158704 diff --git a/model-00034-of-00067.safetensors b/model-00034-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c6181c7178cdc74f79a3e18af3591ec6828b614 --- /dev/null +++ b/model-00034-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef9bdddbbdc628295b2b2600b380b3b2752c2f309ed6b1852b5656c0afdf6d1 +size 282158704 diff --git a/model-00035-of-00067.safetensors b/model-00035-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4227d1d496155de790ccbe6097b0c9b39293aa51 --- /dev/null +++ b/model-00035-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ae7217579586f489bffa71708a6203e5f41b7a31ea39ea41dea6daa8cd3f92 +size 282158704 diff --git a/model-00036-of-00067.safetensors b/model-00036-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d35793f7a9872195d0363c3d706f966495c14430 --- /dev/null +++ b/model-00036-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8088ece332f6aa170d2a47af926c74f4ce1549838458d6baedf405025c4eaaae +size 282158704 diff --git a/model-00037-of-00067.safetensors b/model-00037-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56323dc84f6d8155d31bfa01e174028c8ac19e90 --- /dev/null +++ b/model-00037-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0836b91117ad70d6a03fb43d7d9ebfd11a4676afb6addff86693eb145184af04 +size 282158704 diff --git a/model-00038-of-00067.safetensors b/model-00038-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..836784e8495abc53d8be54c7c359b8e35d32a65e --- /dev/null +++ b/model-00038-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa715908fdaf2925def655b1263ce3bbcfff0c3884f7e347e6ecd8a84bad3243 +size 282158704 diff --git a/model-00039-of-00067.safetensors b/model-00039-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c3868e0a60301e13ad4c05270743a9fefaf2382e --- /dev/null +++ b/model-00039-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:502e1cfa6005e99b7a70c442ae6e96e0ad85d5ce8d85f415ea0ae070ec242e3e +size 282158704 diff --git a/model-00040-of-00067.safetensors b/model-00040-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2192b6122d28c12a3834f6e7ffeb4ceac6550898 --- /dev/null +++ b/model-00040-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4eadfb9071a7a75aedf19919de7d618757fe719a345a4244f91d56430aa87f5 +size 282158704 diff --git a/model-00041-of-00067.safetensors b/model-00041-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b80eb6bf248a0a9a60f4062ffa0c62fb1dec6a5e --- /dev/null +++ b/model-00041-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d08e0833fcc627b507fde9c8fd5334b5dc6bfd121ce885a15ce900c02454af9d +size 282158704 diff --git a/model-00042-of-00067.safetensors b/model-00042-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2439e68aeb61028f7afcae7d4e89fd3b7c22c449 --- /dev/null +++ b/model-00042-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9855f8c29214381c8a38d969f1faf508c0e27d24471bdc08d4ea5916ff042822 +size 282158704 diff --git a/model-00043-of-00067.safetensors b/model-00043-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..544854048f5ad4e1927afbe0cc627a1635edcfe6 --- /dev/null +++ b/model-00043-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9cadcb8ebda6f0ca0518915ff0161a89d925b2967eda469aee2dfa4d6407ce +size 282158704 diff --git a/model-00044-of-00067.safetensors b/model-00044-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6bed4d4241a12b08f4d325166eb1f358fa51cb3 --- /dev/null +++ b/model-00044-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1444495bab3bf0df180e0d378a6dc0bd4296e1d577d50316c7e941d6ad21c458 +size 282158704 diff --git a/model-00045-of-00067.safetensors b/model-00045-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6d227c207d06a86da1037295f7468ba5ecfe943 --- /dev/null +++ b/model-00045-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2bfaf4386befa592fdec5730e7e7bc6d99f4fae57c86db207dc48bde06c11c +size 282158704 diff --git a/model-00046-of-00067.safetensors b/model-00046-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cc263ecca80f91a26b445ef673e24de81e26671 --- /dev/null +++ b/model-00046-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0e07f6e6d7c3ef0a939ab5e7a64dac4c1ff422203f348f771c5bdfb99f5603 +size 282158704 diff --git a/model-00047-of-00067.safetensors b/model-00047-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..73387362faae5cfe4f90283505b8f00fbb0cbadc --- /dev/null +++ b/model-00047-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473b416b3c5246334cb606c4ce8e9dfbac92fee2196fdfac0a7d781339e69b46 +size 282158704 diff --git a/model-00048-of-00067.safetensors b/model-00048-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68ed9a3dfb4df57d4773cc694c93ac923db3881c --- /dev/null +++ b/model-00048-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67ba2c15eb8ec91dd7bdacac9ff56deeb34872d6a9717daf2ae3580943f6dcdd +size 282158704 diff --git a/model-00049-of-00067.safetensors b/model-00049-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88b09b43970b424aa0f4f1130e4098ee230b0160 --- /dev/null +++ b/model-00049-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda602f2da853093065ece315c8aad24e765b0c520781299b57e84cfb61376a7 +size 282158704 diff --git a/model-00050-of-00067.safetensors b/model-00050-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fd0a4379bbc93d30d8e78c9997ac29edc7302ab --- /dev/null +++ b/model-00050-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2fc0bd171eb8d483c5a23908af332954dba089ba3597a774121b0f47642d894 +size 282158704 diff --git a/model-00051-of-00067.safetensors b/model-00051-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46bee0fd54cab654d28dd234bb64cb6db84d5c5a --- /dev/null +++ b/model-00051-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfb5223e818362004857759deedbfacd8f9a0bb53213d1806bda5cafdbaf6e0 +size 282158704 diff --git a/model-00052-of-00067.safetensors b/model-00052-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4caef2a8c80a2fc3896a8f44520853d9c3366b84 --- /dev/null +++ b/model-00052-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f886c495664071602ed50d9a480872d54553ae47bb6541e7f85f20bb86695d11 +size 282158704 diff --git a/model-00053-of-00067.safetensors b/model-00053-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5de348e193084abb6a80cd3f21944bdc5eb0bb6e --- /dev/null +++ b/model-00053-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169b5d13cb1cb2eb1c4f5b8dbefc6dc6d9b17b073cd90fecefa65eb496c7b69f +size 282158704 diff --git a/model-00054-of-00067.safetensors b/model-00054-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b88383e4017fa89f755e951c5010794e38f556b0 --- /dev/null +++ b/model-00054-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877160023872d8c5f48bba315e3a36811f731a5e988b43d04793a037aa705633 +size 282158704 diff --git a/model-00055-of-00067.safetensors b/model-00055-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b6865f3ccad21855b9d0bb63191a767a69b9282 --- /dev/null +++ b/model-00055-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde55899b7907b351f9919cbca2aec1badd0c01d7654c2c5bb61f557495442da +size 282158704 diff --git a/model-00056-of-00067.safetensors b/model-00056-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..797ef120dca4c25a48afc3ddc8087be847da0ba7 --- /dev/null +++ b/model-00056-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e886a385f43062ac8acc66b22c41ca85f18ca5277614305094069a30d1771c4 +size 282158704 diff --git a/model-00057-of-00067.safetensors b/model-00057-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a106974b3b13a687c388cafd70448ea58c63746 --- /dev/null +++ b/model-00057-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f554108ffc74966f72a7809450182dd72f78b4456f321f12c7947dd3f085bf3 +size 282158704 diff --git a/model-00058-of-00067.safetensors b/model-00058-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea8750e564c56a3dd8917fc65bead67ae468c165 --- /dev/null +++ b/model-00058-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a45dc285042e20368238fe2bcc4433c82a694ae93709d9f88d0f27fdade246 +size 282158704 diff --git a/model-00059-of-00067.safetensors b/model-00059-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d31342fcfeba5c4cdc1321364a29f3cdc97f2671 --- /dev/null +++ b/model-00059-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6ca87db2d48f48820b1006a92362c97dd9bec121412beecec88827ba463bcc +size 282158704 diff --git a/model-00060-of-00067.safetensors b/model-00060-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6eb060ed3d544233c9770cc1b82aa8f66a6bcc4 --- /dev/null +++ b/model-00060-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92f630d80f1e8e156d0a308d5233f016b90063127bb9cdebdc53027604f4adb +size 282158704 diff --git a/model-00061-of-00067.safetensors b/model-00061-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..573342059b70e7efbffc5950fb626f24c6ef33c5 --- /dev/null +++ b/model-00061-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d266e51f26d31f07564929d9bb8db3e0ae9e3777d4c5eaf8ec4f3d283f07e49 +size 282158704 diff --git a/model-00062-of-00067.safetensors b/model-00062-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15506278488b3f3ffe7764e54ccc3fa9316e9fdc --- /dev/null +++ b/model-00062-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f67036027149af2fd55b2816d5b6770bf8c5a86c62b822fc58320be2bd25c37 +size 282158704 diff --git a/model-00063-of-00067.safetensors b/model-00063-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b2fcfa1cfa4d6ecf2e8769928a538f70c2fb94d0 --- /dev/null +++ b/model-00063-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43d8e4f0f7ed12dcf03956367f78071b7f89953eee4fc8859e4dbb51a275fb7d +size 282158704 diff --git a/model-00064-of-00067.safetensors b/model-00064-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1763a1e54b9de43dfee8540b580b4b0cc33fd5f7 --- /dev/null +++ b/model-00064-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a14efb0bd32d9a0f8d95a2d413a967bf9f5596651c18327745b57f6e177917 +size 282158704 diff --git a/model-00065-of-00067.safetensors b/model-00065-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77bbbbc586e4194123cb41c24b7d80a60f366891 --- /dev/null +++ b/model-00065-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d2f9612cc765022c42e8ee2b29883618e0ffdacc5d826c7b6c1ba8ad6f93d5 +size 282158704 diff --git a/model-00066-of-00067.safetensors b/model-00066-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4dd38046c15bbd8aac6db4fc1341713c255e4a0 --- /dev/null +++ b/model-00066-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04b56cb1ce4be15800142de3c2ef267606c91b810dbb33a106c46ed8b5675c5 +size 282158704 diff --git a/model-00067-of-00067.safetensors b/model-00067-of-00067.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..959492ac17b694a77d97607b476b338baf4750ef --- /dev/null +++ b/model-00067-of-00067.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03627c9d31d8e214202f09e3fb2c1eebac5e909866c16161d083271c4691ef3a +size 282158704 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..5abfa8c0c09ff6af142a339b66f4311efe980519 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,2122 @@ +{ + "metadata": { + "total_size": 21172201472 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00067.safetensors", + "model.norm.weight": "model-00002-of-00067.safetensors", + "lm_head.weight": "model-00003-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.q_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.q_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.q_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.q_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.q_proj.bias": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.k_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.k_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.k_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.k_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.k_proj.bias": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.v_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.v_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.v_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.v_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.v_proj.bias": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.o_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.o_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.o_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.self_attn.o_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.gate_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.gate_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.gate_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.gate_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.up_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.up_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.up_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.up_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.down_proj.qweight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.down_proj.qzeros": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.down_proj.scales": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.mlp.down_proj.g_idx": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.input_layernorm.weight": "model-00004-of-00067.safetensors", + "model.layers.0.model.layers.0.post_attention_layernorm.weight": "model-00004-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.q_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.q_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.q_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.q_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.q_proj.bias": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.k_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.k_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.k_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.k_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.k_proj.bias": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.v_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.v_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.v_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.v_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.v_proj.bias": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.o_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.o_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.o_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.self_attn.o_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.gate_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.gate_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.gate_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.gate_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.up_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.up_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.up_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.up_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.down_proj.qweight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.down_proj.qzeros": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.down_proj.scales": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.mlp.down_proj.g_idx": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.input_layernorm.weight": "model-00005-of-00067.safetensors", + "model.layers.1.model.layers.1.post_attention_layernorm.weight": "model-00005-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.q_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.q_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.q_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.q_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.q_proj.bias": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.k_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.k_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.k_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.k_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.k_proj.bias": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.v_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.v_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.v_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.v_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.v_proj.bias": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.o_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.o_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.o_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.self_attn.o_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.gate_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.gate_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.gate_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.gate_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.up_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.up_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.up_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.up_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.down_proj.qweight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.down_proj.qzeros": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.down_proj.scales": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.mlp.down_proj.g_idx": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.input_layernorm.weight": "model-00006-of-00067.safetensors", + "model.layers.2.model.layers.2.post_attention_layernorm.weight": "model-00006-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.q_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.q_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.q_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.q_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.q_proj.bias": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.k_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.k_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.k_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.k_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.k_proj.bias": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.v_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.v_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.v_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.v_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.v_proj.bias": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.o_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.o_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.o_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.self_attn.o_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.gate_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.gate_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.gate_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.gate_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.up_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.up_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.up_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.up_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.down_proj.qweight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.down_proj.qzeros": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.down_proj.scales": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.mlp.down_proj.g_idx": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.input_layernorm.weight": "model-00007-of-00067.safetensors", + "model.layers.3.model.layers.3.post_attention_layernorm.weight": "model-00007-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.q_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.q_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.q_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.q_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.q_proj.bias": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.k_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.k_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.k_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.k_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.k_proj.bias": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.v_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.v_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.v_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.v_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.v_proj.bias": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.o_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.o_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.o_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.self_attn.o_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.gate_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.gate_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.gate_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.gate_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.up_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.up_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.up_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.up_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.down_proj.qweight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.down_proj.qzeros": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.down_proj.scales": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.mlp.down_proj.g_idx": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.input_layernorm.weight": "model-00008-of-00067.safetensors", + "model.layers.4.model.layers.4.post_attention_layernorm.weight": "model-00008-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.q_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.q_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.q_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.q_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.q_proj.bias": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.k_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.k_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.k_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.k_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.k_proj.bias": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.v_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.v_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.v_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.v_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.v_proj.bias": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.o_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.o_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.o_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.self_attn.o_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.gate_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.gate_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.gate_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.gate_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.up_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.up_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.up_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.up_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.down_proj.qweight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.down_proj.qzeros": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.down_proj.scales": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.mlp.down_proj.g_idx": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.input_layernorm.weight": "model-00009-of-00067.safetensors", + "model.layers.5.model.layers.5.post_attention_layernorm.weight": "model-00009-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.q_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.q_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.q_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.q_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.q_proj.bias": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.k_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.k_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.k_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.k_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.k_proj.bias": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.v_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.v_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.v_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.v_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.v_proj.bias": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.o_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.o_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.o_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.self_attn.o_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.gate_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.gate_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.gate_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.gate_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.up_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.up_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.up_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.up_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.down_proj.qweight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.down_proj.qzeros": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.down_proj.scales": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.mlp.down_proj.g_idx": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.input_layernorm.weight": "model-00010-of-00067.safetensors", + "model.layers.6.model.layers.6.post_attention_layernorm.weight": "model-00010-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.q_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.q_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.q_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.q_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.q_proj.bias": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.k_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.k_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.k_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.k_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.k_proj.bias": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.v_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.v_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.v_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.v_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.v_proj.bias": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.o_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.o_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.o_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.self_attn.o_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.gate_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.gate_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.gate_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.gate_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.up_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.up_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.up_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.up_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.down_proj.qweight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.down_proj.qzeros": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.down_proj.scales": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.mlp.down_proj.g_idx": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.input_layernorm.weight": "model-00011-of-00067.safetensors", + "model.layers.7.model.layers.7.post_attention_layernorm.weight": "model-00011-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.q_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.q_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.q_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.q_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.q_proj.bias": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.k_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.k_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.k_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.k_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.k_proj.bias": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.v_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.v_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.v_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.v_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.v_proj.bias": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.o_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.o_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.o_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.self_attn.o_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.gate_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.gate_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.gate_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.gate_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.up_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.up_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.up_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.up_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.down_proj.qweight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.down_proj.qzeros": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.down_proj.scales": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.mlp.down_proj.g_idx": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.input_layernorm.weight": "model-00012-of-00067.safetensors", + "model.layers.8.model.layers.8.post_attention_layernorm.weight": "model-00012-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.q_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.q_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.q_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.q_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.q_proj.bias": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.k_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.k_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.k_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.k_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.k_proj.bias": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.v_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.v_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.v_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.v_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.v_proj.bias": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.o_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.o_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.o_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.self_attn.o_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.gate_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.gate_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.gate_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.gate_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.up_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.up_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.up_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.up_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.down_proj.qweight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.down_proj.qzeros": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.down_proj.scales": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.mlp.down_proj.g_idx": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.input_layernorm.weight": "model-00013-of-00067.safetensors", + "model.layers.9.model.layers.9.post_attention_layernorm.weight": "model-00013-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.q_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.q_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.q_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.q_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.q_proj.bias": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.k_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.k_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.k_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.k_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.k_proj.bias": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.v_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.v_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.v_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.v_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.v_proj.bias": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.o_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.o_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.o_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.self_attn.o_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.gate_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.gate_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.gate_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.gate_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.up_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.up_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.up_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.up_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.down_proj.qweight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.down_proj.qzeros": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.down_proj.scales": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.mlp.down_proj.g_idx": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.input_layernorm.weight": "model-00014-of-00067.safetensors", + "model.layers.10.model.layers.10.post_attention_layernorm.weight": "model-00014-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.q_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.q_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.q_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.q_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.q_proj.bias": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.k_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.k_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.k_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.k_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.k_proj.bias": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.v_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.v_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.v_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.v_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.v_proj.bias": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.o_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.o_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.o_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.self_attn.o_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.gate_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.gate_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.gate_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.gate_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.up_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.up_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.up_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.up_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.down_proj.qweight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.down_proj.qzeros": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.down_proj.scales": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.mlp.down_proj.g_idx": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.input_layernorm.weight": "model-00015-of-00067.safetensors", + "model.layers.11.model.layers.11.post_attention_layernorm.weight": "model-00015-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.q_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.q_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.q_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.q_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.q_proj.bias": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.k_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.k_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.k_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.k_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.k_proj.bias": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.v_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.v_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.v_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.v_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.v_proj.bias": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.o_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.o_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.o_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.self_attn.o_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.gate_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.gate_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.gate_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.gate_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.up_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.up_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.up_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.up_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.down_proj.qweight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.down_proj.qzeros": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.down_proj.scales": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.mlp.down_proj.g_idx": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.input_layernorm.weight": "model-00016-of-00067.safetensors", + "model.layers.12.model.layers.12.post_attention_layernorm.weight": "model-00016-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.q_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.q_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.q_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.q_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.q_proj.bias": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.k_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.k_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.k_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.k_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.k_proj.bias": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.v_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.v_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.v_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.v_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.v_proj.bias": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.o_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.o_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.o_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.self_attn.o_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.gate_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.gate_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.gate_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.gate_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.up_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.up_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.up_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.up_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.down_proj.qweight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.down_proj.qzeros": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.down_proj.scales": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.mlp.down_proj.g_idx": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.input_layernorm.weight": "model-00017-of-00067.safetensors", + "model.layers.13.model.layers.13.post_attention_layernorm.weight": "model-00017-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.q_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.q_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.q_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.q_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.q_proj.bias": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.k_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.k_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.k_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.k_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.k_proj.bias": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.v_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.v_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.v_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.v_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.v_proj.bias": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.o_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.o_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.o_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.self_attn.o_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.gate_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.gate_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.gate_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.gate_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.up_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.up_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.up_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.up_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.down_proj.qweight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.down_proj.qzeros": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.down_proj.scales": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.mlp.down_proj.g_idx": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.input_layernorm.weight": "model-00018-of-00067.safetensors", + "model.layers.14.model.layers.14.post_attention_layernorm.weight": "model-00018-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.q_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.q_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.q_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.q_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.q_proj.bias": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.k_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.k_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.k_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.k_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.k_proj.bias": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.v_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.v_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.v_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.v_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.v_proj.bias": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.o_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.o_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.o_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.self_attn.o_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.gate_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.gate_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.gate_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.gate_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.up_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.up_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.up_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.up_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.down_proj.qweight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.down_proj.qzeros": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.down_proj.scales": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.mlp.down_proj.g_idx": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.input_layernorm.weight": "model-00019-of-00067.safetensors", + "model.layers.15.model.layers.15.post_attention_layernorm.weight": "model-00019-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.q_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.q_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.q_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.q_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.q_proj.bias": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.k_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.k_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.k_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.k_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.k_proj.bias": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.v_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.v_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.v_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.v_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.v_proj.bias": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.o_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.o_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.o_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.self_attn.o_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.gate_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.gate_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.gate_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.gate_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.up_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.up_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.up_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.up_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.down_proj.qweight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.down_proj.qzeros": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.down_proj.scales": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.mlp.down_proj.g_idx": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.input_layernorm.weight": "model-00020-of-00067.safetensors", + "model.layers.16.model.layers.16.post_attention_layernorm.weight": "model-00020-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.q_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.q_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.q_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.q_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.q_proj.bias": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.k_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.k_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.k_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.k_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.k_proj.bias": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.v_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.v_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.v_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.v_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.v_proj.bias": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.o_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.o_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.o_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.self_attn.o_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.gate_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.gate_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.gate_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.gate_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.up_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.up_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.up_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.up_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.down_proj.qweight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.down_proj.qzeros": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.down_proj.scales": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.mlp.down_proj.g_idx": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.input_layernorm.weight": "model-00021-of-00067.safetensors", + "model.layers.17.model.layers.17.post_attention_layernorm.weight": "model-00021-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.q_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.q_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.q_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.q_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.q_proj.bias": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.k_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.k_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.k_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.k_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.k_proj.bias": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.v_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.v_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.v_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.v_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.v_proj.bias": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.o_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.o_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.o_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.self_attn.o_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.gate_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.gate_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.gate_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.gate_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.up_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.up_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.up_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.up_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.down_proj.qweight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.down_proj.qzeros": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.down_proj.scales": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.mlp.down_proj.g_idx": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.input_layernorm.weight": "model-00022-of-00067.safetensors", + "model.layers.18.model.layers.18.post_attention_layernorm.weight": "model-00022-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.q_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.q_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.q_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.q_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.q_proj.bias": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.k_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.k_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.k_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.k_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.k_proj.bias": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.v_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.v_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.v_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.v_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.v_proj.bias": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.o_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.o_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.o_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.self_attn.o_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.gate_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.gate_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.gate_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.gate_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.up_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.up_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.up_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.up_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.down_proj.qweight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.down_proj.qzeros": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.down_proj.scales": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.mlp.down_proj.g_idx": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.input_layernorm.weight": "model-00023-of-00067.safetensors", + "model.layers.19.model.layers.19.post_attention_layernorm.weight": "model-00023-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.q_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.q_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.q_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.q_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.q_proj.bias": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.k_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.k_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.k_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.k_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.k_proj.bias": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.v_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.v_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.v_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.v_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.v_proj.bias": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.o_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.o_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.o_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.self_attn.o_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.gate_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.gate_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.gate_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.gate_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.up_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.up_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.up_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.up_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.down_proj.qweight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.down_proj.qzeros": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.down_proj.scales": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.mlp.down_proj.g_idx": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.input_layernorm.weight": "model-00024-of-00067.safetensors", + "model.layers.20.model.layers.20.post_attention_layernorm.weight": "model-00024-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.q_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.q_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.q_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.q_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.q_proj.bias": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.k_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.k_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.k_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.k_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.k_proj.bias": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.v_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.v_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.v_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.v_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.v_proj.bias": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.o_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.o_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.o_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.self_attn.o_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.gate_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.gate_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.gate_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.gate_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.up_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.up_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.up_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.up_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.down_proj.qweight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.down_proj.qzeros": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.down_proj.scales": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.mlp.down_proj.g_idx": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.input_layernorm.weight": "model-00025-of-00067.safetensors", + "model.layers.21.model.layers.21.post_attention_layernorm.weight": "model-00025-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.q_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.q_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.q_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.q_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.q_proj.bias": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.k_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.k_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.k_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.k_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.k_proj.bias": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.v_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.v_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.v_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.v_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.v_proj.bias": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.o_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.o_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.o_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.self_attn.o_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.gate_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.gate_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.gate_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.gate_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.up_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.up_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.up_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.up_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.down_proj.qweight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.down_proj.qzeros": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.down_proj.scales": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.mlp.down_proj.g_idx": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.input_layernorm.weight": "model-00026-of-00067.safetensors", + "model.layers.22.model.layers.22.post_attention_layernorm.weight": "model-00026-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.q_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.q_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.q_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.q_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.q_proj.bias": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.k_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.k_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.k_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.k_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.k_proj.bias": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.v_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.v_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.v_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.v_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.v_proj.bias": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.o_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.o_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.o_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.self_attn.o_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.gate_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.gate_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.gate_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.gate_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.up_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.up_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.up_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.up_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.down_proj.qweight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.down_proj.qzeros": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.down_proj.scales": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.mlp.down_proj.g_idx": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.input_layernorm.weight": "model-00027-of-00067.safetensors", + "model.layers.23.model.layers.23.post_attention_layernorm.weight": "model-00027-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.q_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.q_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.q_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.q_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.q_proj.bias": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.k_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.k_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.k_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.k_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.k_proj.bias": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.v_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.v_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.v_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.v_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.v_proj.bias": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.o_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.o_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.o_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.self_attn.o_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.gate_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.gate_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.gate_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.gate_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.up_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.up_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.up_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.up_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.down_proj.qweight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.down_proj.qzeros": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.down_proj.scales": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.mlp.down_proj.g_idx": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.input_layernorm.weight": "model-00028-of-00067.safetensors", + "model.layers.24.model.layers.24.post_attention_layernorm.weight": "model-00028-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.q_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.q_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.q_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.q_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.q_proj.bias": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.k_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.k_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.k_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.k_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.k_proj.bias": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.v_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.v_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.v_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.v_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.v_proj.bias": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.o_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.o_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.o_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.self_attn.o_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.gate_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.gate_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.gate_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.gate_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.up_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.up_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.up_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.up_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.down_proj.qweight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.down_proj.qzeros": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.down_proj.scales": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.mlp.down_proj.g_idx": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.input_layernorm.weight": "model-00029-of-00067.safetensors", + "model.layers.25.model.layers.25.post_attention_layernorm.weight": "model-00029-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.q_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.q_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.q_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.q_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.q_proj.bias": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.k_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.k_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.k_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.k_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.k_proj.bias": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.v_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.v_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.v_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.v_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.v_proj.bias": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.o_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.o_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.o_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.self_attn.o_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.gate_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.gate_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.gate_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.gate_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.up_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.up_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.up_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.up_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.down_proj.qweight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.down_proj.qzeros": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.down_proj.scales": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.mlp.down_proj.g_idx": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.input_layernorm.weight": "model-00030-of-00067.safetensors", + "model.layers.26.model.layers.26.post_attention_layernorm.weight": "model-00030-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.q_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.q_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.q_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.q_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.q_proj.bias": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.k_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.k_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.k_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.k_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.k_proj.bias": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.v_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.v_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.v_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.v_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.v_proj.bias": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.o_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.o_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.o_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.self_attn.o_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.gate_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.gate_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.gate_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.gate_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.up_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.up_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.up_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.up_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.down_proj.qweight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.down_proj.qzeros": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.down_proj.scales": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.mlp.down_proj.g_idx": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.input_layernorm.weight": "model-00031-of-00067.safetensors", + "model.layers.27.model.layers.27.post_attention_layernorm.weight": "model-00031-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.q_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.q_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.q_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.q_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.q_proj.bias": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.k_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.k_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.k_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.k_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.k_proj.bias": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.v_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.v_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.v_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.v_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.v_proj.bias": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.o_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.o_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.o_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.self_attn.o_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.gate_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.gate_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.gate_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.gate_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.up_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.up_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.up_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.up_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.down_proj.qweight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.down_proj.qzeros": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.down_proj.scales": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.mlp.down_proj.g_idx": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.input_layernorm.weight": "model-00032-of-00067.safetensors", + "model.layers.28.model.layers.28.post_attention_layernorm.weight": "model-00032-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.q_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.q_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.q_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.q_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.q_proj.bias": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.k_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.k_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.k_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.k_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.k_proj.bias": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.v_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.v_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.v_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.v_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.v_proj.bias": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.o_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.o_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.o_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.self_attn.o_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.gate_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.gate_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.gate_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.gate_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.up_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.up_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.up_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.up_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.down_proj.qweight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.down_proj.qzeros": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.down_proj.scales": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.mlp.down_proj.g_idx": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.input_layernorm.weight": "model-00033-of-00067.safetensors", + "model.layers.29.model.layers.29.post_attention_layernorm.weight": "model-00033-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.q_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.q_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.q_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.q_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.q_proj.bias": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.k_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.k_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.k_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.k_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.k_proj.bias": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.v_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.v_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.v_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.v_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.v_proj.bias": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.o_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.o_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.o_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.self_attn.o_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.gate_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.gate_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.gate_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.gate_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.up_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.up_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.up_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.up_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.down_proj.qweight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.down_proj.qzeros": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.down_proj.scales": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.mlp.down_proj.g_idx": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.input_layernorm.weight": "model-00034-of-00067.safetensors", + "model.layers.30.model.layers.30.post_attention_layernorm.weight": "model-00034-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.q_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.q_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.q_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.q_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.q_proj.bias": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.k_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.k_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.k_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.k_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.k_proj.bias": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.v_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.v_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.v_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.v_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.v_proj.bias": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.o_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.o_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.o_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.self_attn.o_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.gate_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.gate_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.gate_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.gate_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.up_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.up_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.up_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.up_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.down_proj.qweight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.down_proj.qzeros": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.down_proj.scales": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.mlp.down_proj.g_idx": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.input_layernorm.weight": "model-00035-of-00067.safetensors", + "model.layers.31.model.layers.31.post_attention_layernorm.weight": "model-00035-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.q_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.q_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.q_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.q_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.q_proj.bias": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.k_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.k_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.k_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.k_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.k_proj.bias": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.v_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.v_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.v_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.v_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.v_proj.bias": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.o_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.o_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.o_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.self_attn.o_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.gate_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.gate_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.gate_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.gate_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.up_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.up_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.up_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.up_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.down_proj.qweight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.down_proj.qzeros": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.down_proj.scales": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.mlp.down_proj.g_idx": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.input_layernorm.weight": "model-00036-of-00067.safetensors", + "model.layers.32.model.layers.32.post_attention_layernorm.weight": "model-00036-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.q_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.q_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.q_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.q_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.q_proj.bias": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.k_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.k_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.k_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.k_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.k_proj.bias": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.v_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.v_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.v_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.v_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.v_proj.bias": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.o_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.o_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.o_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.self_attn.o_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.gate_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.gate_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.gate_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.gate_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.up_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.up_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.up_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.up_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.down_proj.qweight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.down_proj.qzeros": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.down_proj.scales": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.mlp.down_proj.g_idx": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.input_layernorm.weight": "model-00037-of-00067.safetensors", + "model.layers.33.model.layers.33.post_attention_layernorm.weight": "model-00037-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.q_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.q_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.q_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.q_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.q_proj.bias": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.k_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.k_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.k_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.k_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.k_proj.bias": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.v_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.v_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.v_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.v_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.v_proj.bias": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.o_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.o_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.o_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.self_attn.o_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.gate_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.gate_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.gate_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.gate_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.up_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.up_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.up_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.up_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.down_proj.qweight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.down_proj.qzeros": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.down_proj.scales": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.mlp.down_proj.g_idx": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.input_layernorm.weight": "model-00038-of-00067.safetensors", + "model.layers.34.model.layers.34.post_attention_layernorm.weight": "model-00038-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.q_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.q_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.q_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.q_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.q_proj.bias": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.k_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.k_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.k_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.k_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.k_proj.bias": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.v_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.v_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.v_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.v_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.v_proj.bias": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.o_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.o_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.o_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.self_attn.o_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.gate_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.gate_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.gate_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.gate_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.up_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.up_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.up_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.up_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.down_proj.qweight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.down_proj.qzeros": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.down_proj.scales": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.mlp.down_proj.g_idx": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.input_layernorm.weight": "model-00039-of-00067.safetensors", + "model.layers.35.model.layers.35.post_attention_layernorm.weight": "model-00039-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.q_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.q_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.q_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.q_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.q_proj.bias": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.k_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.k_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.k_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.k_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.k_proj.bias": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.v_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.v_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.v_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.v_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.v_proj.bias": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.o_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.o_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.o_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.self_attn.o_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.gate_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.gate_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.gate_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.gate_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.up_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.up_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.up_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.up_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.down_proj.qweight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.down_proj.qzeros": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.down_proj.scales": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.mlp.down_proj.g_idx": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.input_layernorm.weight": "model-00040-of-00067.safetensors", + "model.layers.36.model.layers.36.post_attention_layernorm.weight": "model-00040-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.q_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.q_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.q_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.q_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.q_proj.bias": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.k_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.k_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.k_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.k_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.k_proj.bias": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.v_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.v_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.v_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.v_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.v_proj.bias": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.o_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.o_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.o_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.self_attn.o_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.gate_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.gate_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.gate_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.gate_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.up_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.up_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.up_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.up_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.down_proj.qweight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.down_proj.qzeros": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.down_proj.scales": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.mlp.down_proj.g_idx": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.input_layernorm.weight": "model-00041-of-00067.safetensors", + "model.layers.37.model.layers.37.post_attention_layernorm.weight": "model-00041-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.q_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.q_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.q_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.q_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.q_proj.bias": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.k_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.k_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.k_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.k_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.k_proj.bias": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.v_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.v_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.v_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.v_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.v_proj.bias": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.o_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.o_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.o_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.self_attn.o_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.gate_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.gate_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.gate_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.gate_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.up_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.up_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.up_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.up_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.down_proj.qweight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.down_proj.qzeros": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.down_proj.scales": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.mlp.down_proj.g_idx": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.input_layernorm.weight": "model-00042-of-00067.safetensors", + "model.layers.38.model.layers.38.post_attention_layernorm.weight": "model-00042-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.q_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.q_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.q_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.q_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.q_proj.bias": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.k_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.k_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.k_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.k_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.k_proj.bias": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.v_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.v_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.v_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.v_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.v_proj.bias": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.o_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.o_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.o_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.self_attn.o_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.gate_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.gate_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.gate_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.gate_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.up_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.up_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.up_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.up_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.down_proj.qweight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.down_proj.qzeros": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.down_proj.scales": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.mlp.down_proj.g_idx": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.input_layernorm.weight": "model-00043-of-00067.safetensors", + "model.layers.39.model.layers.39.post_attention_layernorm.weight": "model-00043-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.q_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.q_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.q_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.q_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.q_proj.bias": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.k_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.k_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.k_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.k_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.k_proj.bias": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.v_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.v_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.v_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.v_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.v_proj.bias": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.o_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.o_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.o_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.self_attn.o_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.gate_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.gate_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.gate_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.gate_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.up_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.up_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.up_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.up_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.down_proj.qweight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.down_proj.qzeros": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.down_proj.scales": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.mlp.down_proj.g_idx": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.input_layernorm.weight": "model-00044-of-00067.safetensors", + "model.layers.40.model.layers.40.post_attention_layernorm.weight": "model-00044-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.q_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.q_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.q_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.q_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.q_proj.bias": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.k_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.k_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.k_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.k_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.k_proj.bias": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.v_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.v_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.v_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.v_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.v_proj.bias": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.o_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.o_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.o_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.self_attn.o_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.gate_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.gate_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.gate_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.gate_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.up_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.up_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.up_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.up_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.down_proj.qweight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.down_proj.qzeros": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.down_proj.scales": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.mlp.down_proj.g_idx": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.input_layernorm.weight": "model-00045-of-00067.safetensors", + "model.layers.41.model.layers.41.post_attention_layernorm.weight": "model-00045-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.q_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.q_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.q_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.q_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.q_proj.bias": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.k_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.k_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.k_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.k_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.k_proj.bias": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.v_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.v_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.v_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.v_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.v_proj.bias": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.o_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.o_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.o_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.self_attn.o_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.gate_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.gate_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.gate_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.gate_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.up_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.up_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.up_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.up_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.down_proj.qweight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.down_proj.qzeros": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.down_proj.scales": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.mlp.down_proj.g_idx": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.input_layernorm.weight": "model-00046-of-00067.safetensors", + "model.layers.42.model.layers.42.post_attention_layernorm.weight": "model-00046-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.q_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.q_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.q_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.q_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.q_proj.bias": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.k_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.k_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.k_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.k_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.k_proj.bias": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.v_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.v_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.v_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.v_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.v_proj.bias": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.o_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.o_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.o_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.self_attn.o_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.gate_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.gate_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.gate_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.gate_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.up_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.up_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.up_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.up_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.down_proj.qweight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.down_proj.qzeros": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.down_proj.scales": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.mlp.down_proj.g_idx": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.input_layernorm.weight": "model-00047-of-00067.safetensors", + "model.layers.43.model.layers.43.post_attention_layernorm.weight": "model-00047-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.q_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.q_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.q_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.q_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.q_proj.bias": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.k_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.k_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.k_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.k_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.k_proj.bias": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.v_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.v_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.v_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.v_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.v_proj.bias": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.o_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.o_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.o_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.self_attn.o_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.gate_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.gate_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.gate_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.gate_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.up_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.up_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.up_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.up_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.down_proj.qweight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.down_proj.qzeros": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.down_proj.scales": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.mlp.down_proj.g_idx": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.input_layernorm.weight": "model-00048-of-00067.safetensors", + "model.layers.44.model.layers.44.post_attention_layernorm.weight": "model-00048-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.q_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.q_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.q_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.q_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.q_proj.bias": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.k_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.k_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.k_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.k_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.k_proj.bias": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.v_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.v_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.v_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.v_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.v_proj.bias": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.o_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.o_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.o_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.self_attn.o_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.gate_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.gate_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.gate_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.gate_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.up_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.up_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.up_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.up_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.down_proj.qweight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.down_proj.qzeros": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.down_proj.scales": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.mlp.down_proj.g_idx": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.input_layernorm.weight": "model-00049-of-00067.safetensors", + "model.layers.45.model.layers.45.post_attention_layernorm.weight": "model-00049-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.q_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.q_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.q_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.q_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.q_proj.bias": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.k_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.k_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.k_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.k_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.k_proj.bias": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.v_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.v_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.v_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.v_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.v_proj.bias": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.o_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.o_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.o_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.self_attn.o_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.gate_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.gate_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.gate_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.gate_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.up_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.up_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.up_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.up_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.down_proj.qweight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.down_proj.qzeros": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.down_proj.scales": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.mlp.down_proj.g_idx": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.input_layernorm.weight": "model-00050-of-00067.safetensors", + "model.layers.46.model.layers.46.post_attention_layernorm.weight": "model-00050-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.q_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.q_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.q_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.q_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.q_proj.bias": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.k_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.k_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.k_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.k_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.k_proj.bias": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.v_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.v_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.v_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.v_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.v_proj.bias": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.o_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.o_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.o_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.self_attn.o_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.gate_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.gate_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.gate_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.gate_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.up_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.up_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.up_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.up_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.down_proj.qweight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.down_proj.qzeros": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.down_proj.scales": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.mlp.down_proj.g_idx": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.input_layernorm.weight": "model-00051-of-00067.safetensors", + "model.layers.47.model.layers.47.post_attention_layernorm.weight": "model-00051-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.q_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.q_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.q_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.q_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.q_proj.bias": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.k_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.k_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.k_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.k_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.k_proj.bias": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.v_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.v_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.v_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.v_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.v_proj.bias": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.o_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.o_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.o_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.self_attn.o_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.gate_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.gate_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.gate_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.gate_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.up_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.up_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.up_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.up_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.down_proj.qweight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.down_proj.qzeros": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.down_proj.scales": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.mlp.down_proj.g_idx": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.input_layernorm.weight": "model-00052-of-00067.safetensors", + "model.layers.48.model.layers.48.post_attention_layernorm.weight": "model-00052-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.q_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.q_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.q_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.q_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.q_proj.bias": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.k_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.k_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.k_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.k_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.k_proj.bias": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.v_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.v_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.v_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.v_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.v_proj.bias": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.o_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.o_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.o_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.self_attn.o_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.gate_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.gate_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.gate_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.gate_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.up_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.up_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.up_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.up_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.down_proj.qweight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.down_proj.qzeros": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.down_proj.scales": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.mlp.down_proj.g_idx": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.input_layernorm.weight": "model-00053-of-00067.safetensors", + "model.layers.49.model.layers.49.post_attention_layernorm.weight": "model-00053-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.q_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.q_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.q_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.q_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.q_proj.bias": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.k_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.k_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.k_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.k_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.k_proj.bias": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.v_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.v_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.v_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.v_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.v_proj.bias": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.o_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.o_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.o_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.self_attn.o_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.gate_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.gate_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.gate_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.gate_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.up_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.up_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.up_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.up_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.down_proj.qweight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.down_proj.qzeros": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.down_proj.scales": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.mlp.down_proj.g_idx": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.input_layernorm.weight": "model-00054-of-00067.safetensors", + "model.layers.50.model.layers.50.post_attention_layernorm.weight": "model-00054-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.q_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.q_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.q_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.q_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.q_proj.bias": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.k_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.k_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.k_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.k_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.k_proj.bias": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.v_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.v_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.v_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.v_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.v_proj.bias": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.o_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.o_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.o_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.self_attn.o_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.gate_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.gate_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.gate_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.gate_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.up_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.up_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.up_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.up_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.down_proj.qweight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.down_proj.qzeros": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.down_proj.scales": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.mlp.down_proj.g_idx": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.input_layernorm.weight": "model-00055-of-00067.safetensors", + "model.layers.51.model.layers.51.post_attention_layernorm.weight": "model-00055-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.q_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.q_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.q_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.q_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.q_proj.bias": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.k_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.k_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.k_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.k_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.k_proj.bias": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.v_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.v_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.v_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.v_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.v_proj.bias": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.o_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.o_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.o_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.self_attn.o_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.gate_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.gate_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.gate_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.gate_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.up_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.up_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.up_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.up_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.down_proj.qweight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.down_proj.qzeros": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.down_proj.scales": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.mlp.down_proj.g_idx": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.input_layernorm.weight": "model-00056-of-00067.safetensors", + "model.layers.52.model.layers.52.post_attention_layernorm.weight": "model-00056-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.q_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.q_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.q_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.q_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.q_proj.bias": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.k_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.k_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.k_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.k_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.k_proj.bias": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.v_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.v_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.v_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.v_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.v_proj.bias": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.o_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.o_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.o_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.self_attn.o_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.gate_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.gate_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.gate_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.gate_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.up_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.up_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.up_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.up_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.down_proj.qweight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.down_proj.qzeros": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.down_proj.scales": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.mlp.down_proj.g_idx": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.input_layernorm.weight": "model-00057-of-00067.safetensors", + "model.layers.53.model.layers.53.post_attention_layernorm.weight": "model-00057-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.q_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.q_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.q_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.q_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.q_proj.bias": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.k_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.k_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.k_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.k_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.k_proj.bias": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.v_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.v_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.v_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.v_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.v_proj.bias": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.o_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.o_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.o_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.self_attn.o_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.gate_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.gate_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.gate_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.gate_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.up_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.up_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.up_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.up_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.down_proj.qweight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.down_proj.qzeros": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.down_proj.scales": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.mlp.down_proj.g_idx": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.input_layernorm.weight": "model-00058-of-00067.safetensors", + "model.layers.54.model.layers.54.post_attention_layernorm.weight": "model-00058-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.q_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.q_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.q_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.q_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.q_proj.bias": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.k_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.k_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.k_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.k_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.k_proj.bias": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.v_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.v_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.v_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.v_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.v_proj.bias": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.o_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.o_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.o_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.self_attn.o_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.gate_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.gate_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.gate_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.gate_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.up_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.up_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.up_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.up_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.down_proj.qweight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.down_proj.qzeros": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.down_proj.scales": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.mlp.down_proj.g_idx": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.input_layernorm.weight": "model-00059-of-00067.safetensors", + "model.layers.55.model.layers.55.post_attention_layernorm.weight": "model-00059-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.q_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.q_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.q_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.q_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.q_proj.bias": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.k_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.k_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.k_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.k_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.k_proj.bias": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.v_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.v_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.v_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.v_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.v_proj.bias": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.o_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.o_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.o_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.self_attn.o_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.gate_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.gate_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.gate_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.gate_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.up_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.up_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.up_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.up_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.down_proj.qweight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.down_proj.qzeros": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.down_proj.scales": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.mlp.down_proj.g_idx": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.input_layernorm.weight": "model-00060-of-00067.safetensors", + "model.layers.56.model.layers.56.post_attention_layernorm.weight": "model-00060-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.q_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.q_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.q_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.q_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.q_proj.bias": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.k_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.k_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.k_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.k_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.k_proj.bias": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.v_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.v_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.v_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.v_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.v_proj.bias": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.o_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.o_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.o_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.self_attn.o_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.gate_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.gate_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.gate_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.gate_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.up_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.up_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.up_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.up_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.down_proj.qweight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.down_proj.qzeros": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.down_proj.scales": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.mlp.down_proj.g_idx": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.input_layernorm.weight": "model-00061-of-00067.safetensors", + "model.layers.57.model.layers.57.post_attention_layernorm.weight": "model-00061-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.q_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.q_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.q_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.q_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.q_proj.bias": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.k_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.k_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.k_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.k_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.k_proj.bias": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.v_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.v_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.v_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.v_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.v_proj.bias": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.o_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.o_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.o_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.self_attn.o_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.gate_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.gate_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.gate_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.gate_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.up_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.up_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.up_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.up_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.down_proj.qweight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.down_proj.qzeros": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.down_proj.scales": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.mlp.down_proj.g_idx": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.input_layernorm.weight": "model-00062-of-00067.safetensors", + "model.layers.58.model.layers.58.post_attention_layernorm.weight": "model-00062-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.q_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.q_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.q_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.q_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.q_proj.bias": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.k_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.k_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.k_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.k_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.k_proj.bias": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.v_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.v_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.v_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.v_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.v_proj.bias": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.o_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.o_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.o_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.self_attn.o_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.gate_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.gate_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.gate_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.gate_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.up_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.up_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.up_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.up_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.down_proj.qweight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.down_proj.qzeros": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.down_proj.scales": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.mlp.down_proj.g_idx": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.input_layernorm.weight": "model-00063-of-00067.safetensors", + "model.layers.59.model.layers.59.post_attention_layernorm.weight": "model-00063-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.q_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.q_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.q_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.q_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.q_proj.bias": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.k_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.k_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.k_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.k_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.k_proj.bias": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.v_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.v_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.v_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.v_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.v_proj.bias": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.o_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.o_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.o_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.self_attn.o_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.gate_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.gate_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.gate_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.gate_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.up_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.up_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.up_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.up_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.down_proj.qweight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.down_proj.qzeros": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.down_proj.scales": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.mlp.down_proj.g_idx": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.input_layernorm.weight": "model-00064-of-00067.safetensors", + "model.layers.60.model.layers.60.post_attention_layernorm.weight": "model-00064-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.q_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.q_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.q_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.q_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.q_proj.bias": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.k_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.k_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.k_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.k_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.k_proj.bias": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.v_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.v_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.v_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.v_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.v_proj.bias": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.o_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.o_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.o_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.self_attn.o_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.gate_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.gate_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.gate_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.gate_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.up_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.up_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.up_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.up_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.down_proj.qweight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.down_proj.qzeros": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.down_proj.scales": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.mlp.down_proj.g_idx": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.input_layernorm.weight": "model-00065-of-00067.safetensors", + "model.layers.61.model.layers.61.post_attention_layernorm.weight": "model-00065-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.q_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.q_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.q_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.q_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.q_proj.bias": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.k_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.k_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.k_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.k_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.k_proj.bias": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.v_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.v_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.v_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.v_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.v_proj.bias": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.o_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.o_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.o_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.self_attn.o_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.gate_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.gate_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.gate_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.gate_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.up_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.up_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.up_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.up_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.down_proj.qweight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.down_proj.qzeros": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.down_proj.scales": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.mlp.down_proj.g_idx": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.input_layernorm.weight": "model-00066-of-00067.safetensors", + "model.layers.62.model.layers.62.post_attention_layernorm.weight": "model-00066-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.q_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.q_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.q_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.q_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.q_proj.bias": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.k_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.k_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.k_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.k_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.k_proj.bias": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.v_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.v_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.v_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.v_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.v_proj.bias": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.o_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.o_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.o_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.self_attn.o_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.gate_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.gate_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.gate_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.gate_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.up_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.up_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.up_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.up_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.down_proj.qweight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.down_proj.qzeros": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.down_proj.scales": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.mlp.down_proj.g_idx": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.input_layernorm.weight": "model-00067-of-00067.safetensors", + "model.layers.63.model.layers.63.post_attention_layernorm.weight": "model-00067-of-00067.safetensors" + } +} \ No newline at end of file diff --git a/quantize_config.json b/quantize_config.json new file mode 100644 index 0000000000000000000000000000000000000000..5eacd41662f3d777e6b0d9bb55e0c53ab2ac81b0 --- /dev/null +++ b/quantize_config.json @@ -0,0 +1,19 @@ +{ + "bits": 4, + "dynamic": null, + "group_size": 32, + "desc_act": true, + "sym": true, + "lm_head": false, + "true_sequential": true, + "quant_method": "gptq", + "checkpoint_format": "gptq", + "meta": { + "quantizer": "gptqmodel:1.2.2", + "uri": "https://github.com/modelcloud/gptqmodel", + "damp_percent": 0.1, + "damp_auto_increment": 0.0015, + "static_groups": false, + "true_sequential": true + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..3b5852b3353e318db3f379abd5577c42741c3ef8 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,25 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|fim_pad|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..51ebb3ba93988c73bbd83a3c163a14343fbc5b06 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4c8f719f0a26998798f53f81e98cc49c52b35bc6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,208 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "model_max_length": 2048, + "pad_token": "<|fim_pad|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}