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/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..10c36a4601cbbd02a51ca8a81635cdb9d093b86f --- /dev/null +++ b/config.json @@ -0,0 +1,80 @@ +{ + "architectures": [ + "GptOssForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": 200002, + "experts_per_token": 4, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2880, + "initial_context_length": 4096, + "initializer_range": 0.02, + "intermediate_size": 2880, + "layer_types": [ + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gpt_oss", + "num_attention_heads": 64, + "num_experts_per_tok": 4, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "num_local_experts": 128, + "output_router_logits": false, + "pad_token_id": 199999, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "beta_fast": 32.0, + "beta_slow": 1.0, + "factor": 32.0, + "original_max_position_embeddings": 4096, + "rope_type": "yarn", + "truncate": false + }, + "rope_theta": 150000, + "router_aux_loss_coef": 0.9, + "sliding_window": 128, + "swiglu_limit": 7.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.56.0.dev0", + "use_cache": true, + "vocab_size": 201088 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..78317cfc44866df4ad74d80917d2de9ec763d414 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "bos_token_id": 199998, + "do_sample": true, + "eos_token_id": [ + 200002, + 199999 + ], + "pad_token_id": 199999, + "transformers_version": "4.56.0.dev0" +} diff --git a/model-00001-of-00073.safetensors b/model-00001-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ddd8a9ed06fd52c69aa47296fd1baa1d837bb822 --- /dev/null +++ b/model-00001-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b5b69e7feecbc961896afbe7be9a02fce772d236eb5d14d98bf9f93565e872 +size 1212106064 diff --git a/model-00002-of-00073.safetensors b/model-00002-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffc0cdeabd7728fd42611ee0398fa4b6378779da --- /dev/null +++ b/model-00002-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f8d893fc4fbd27a07d2454114d5cc84821fa18d7575b625aa184b31ef0a572 +size 4248207640 diff --git a/model-00003-of-00073.safetensors b/model-00003-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26d291d507c85ca8471d240dd86d0e672cb8c397 --- /dev/null +++ b/model-00003-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26fb7705dba6ce529158ecea8863e20dc2c197790c159f3ec15b865b8474c97a +size 2177954736 diff --git a/model-00004-of-00073.safetensors b/model-00004-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..83f6cf600c5f0c8b103e33df6643999950836fb8 --- /dev/null +++ b/model-00004-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dda6a71a050e68fe98ddfc12c0e3e86234b29d2ee5a6ba9083cabcc9e173563f +size 4248207640 diff --git a/model-00005-of-00073.safetensors b/model-00005-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cecacd34bd0264855ff18dbe2c90a5d7bf028f40 --- /dev/null +++ b/model-00005-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a37774982420254a3c7141b981aa37878713d6bc6f78a756295cd9e41c1ab88 +size 2177954736 diff --git a/model-00006-of-00073.safetensors b/model-00006-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4826abbdd222efc4dd73a42a68a3767db186b184 --- /dev/null +++ b/model-00006-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b81738668bce7b58ec8cef5e8c25b1e2b7afafcd1af7913da2788838263bd0 +size 4248207640 diff --git a/model-00007-of-00073.safetensors b/model-00007-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c7b7984e500cd312528d731e1a75da66ae9e5d0 --- /dev/null +++ b/model-00007-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42c25b0c1f0d5f64594529628151ace3ae838869c744c361cd5421165442e26e +size 2177954736 diff --git a/model-00008-of-00073.safetensors b/model-00008-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2420db70e716e40cceab702078683d15ae2a9c77 --- /dev/null +++ b/model-00008-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b43d83c403e92882c79cdfbeb8b80e30d0d7fe58329ab8d3a8a13db0c1d7c5d +size 4248207640 diff --git a/model-00009-of-00073.safetensors b/model-00009-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da1c422b997c24cbff193005405cbfa8b6b6afbe --- /dev/null +++ b/model-00009-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58fc61132427d0002e559feca0a040ddcc2be59557bc9b713c5011702c25e5b6 +size 2177954736 diff --git a/model-00010-of-00073.safetensors b/model-00010-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e60d1990f00f619edf4f6cd8d8c70146e442bea3 --- /dev/null +++ b/model-00010-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc516fd1e058767eb5d566b81f2619fc9319aed76409628d94b9fda5e4994a0 +size 4248207640 diff --git a/model-00011-of-00073.safetensors b/model-00011-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f2ed9bd773f69fecb6fc117062ff3229f50a589 --- /dev/null +++ b/model-00011-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153eef134702ea1df876220d0e3873e47b124b7764dabc8c64f25a8247761fec +size 2177954736 diff --git a/model-00012-of-00073.safetensors b/model-00012-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..972054b5252c2a5dfab20c4eac58bd0309ac6975 --- /dev/null +++ b/model-00012-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b2a45ac61f5b5d44e5a2df4b88643f8c7d57545b06c60121d954a9598599c1 +size 4248207640 diff --git a/model-00013-of-00073.safetensors b/model-00013-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..681fdac1d55250a1b510443b8d9ed07ddae77074 --- /dev/null +++ b/model-00013-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ceba841dfdd14f0e2b313e676c48c4d66b5824a2fdfa25aa327fabccb227f2 +size 2177954736 diff --git a/model-00014-of-00073.safetensors b/model-00014-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8fb665708d218c8c30bf3b87cbf7e0911c014c5 --- /dev/null +++ b/model-00014-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a4ba78d4b340e08bcdb3fbfb48c26cc57abd581046b6a2a6620b9c63cca14aa +size 4248207640 diff --git a/model-00015-of-00073.safetensors b/model-00015-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..230f87e0b27b968cee20aafe3c7f1a1696abad94 --- /dev/null +++ b/model-00015-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c5e76d8bd303eba203bb00f9ab3dcb4cffa22efe3c400c63c4eb146dd1d744 +size 2177954736 diff --git a/model-00016-of-00073.safetensors b/model-00016-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b231d9ea3cbea1a55578d11a9586d7536ac7c0f3 --- /dev/null +++ b/model-00016-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925cd470b083f8ce05484d991c989419873eecf562080947d4c64649ab56677d +size 4248207640 diff --git a/model-00017-of-00073.safetensors b/model-00017-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..beba6665519353ef3a9627510a3410188e6d0133 --- /dev/null +++ b/model-00017-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ccd83bcd726ee1d758e4eda1d181fc9725e19dfd7ed6326e60b2403f394010 +size 2177954736 diff --git a/model-00018-of-00073.safetensors b/model-00018-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..284f05e627e9326343342712706cf4d4af78b817 --- /dev/null +++ b/model-00018-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52b5fe061cefc784b2fb5a09ce6f30fe1fa6641103a141a5b8722df2a48aff8 +size 4248207640 diff --git a/model-00019-of-00073.safetensors b/model-00019-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..177ee272ae674afeef8d27ed88093bd22e7be298 --- /dev/null +++ b/model-00019-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491cc447b9ac3010ddd8a5a1a2debfbf089a5fd1bececa2bca9589e23280b512 +size 2177954736 diff --git a/model-00020-of-00073.safetensors b/model-00020-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ca9839d90ea7c40c1c76454e1ede34b8f6b8480 --- /dev/null +++ b/model-00020-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3484899ce81bacff6cf71f3e225152d61b3f688906bdaca527c87c5eb35d7c1f +size 4248207640 diff --git a/model-00021-of-00073.safetensors b/model-00021-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8cfa2b32b8593d592a768bfaa2d5f66afcfae73 --- /dev/null +++ b/model-00021-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd51c755fc6bf56bbe9eff6fe4045ec3b6e36880b88a385304ce9b8e8e1d348f +size 2177954688 diff --git a/model-00022-of-00073.safetensors b/model-00022-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1046e178507ebf5cc9a623a26d45ffb1b6254d5f --- /dev/null +++ b/model-00022-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d18647e59b8982622412fa33d9c8defbac9441670fedeb94bf216382f904e48 +size 4248207640 diff --git a/model-00023-of-00073.safetensors b/model-00023-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9514d404fe87a572873f42f745cca2db2cc143e1 --- /dev/null +++ b/model-00023-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be9778c9a50388d090112715fd496790d576e6f481c4fdedfa5fae583d8b33d8 +size 2177954720 diff --git a/model-00024-of-00073.safetensors b/model-00024-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf61bb785574a6ebca04b516a646503ebc931f8c --- /dev/null +++ b/model-00024-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f75eeb2761915a28fd12ae35d2fa13b6b984d9c6829184dc6a81bb778d1811c2 +size 4248207640 diff --git a/model-00025-of-00073.safetensors b/model-00025-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d1f09fd2f8d05bd898cd06d3c000fa5c52330be --- /dev/null +++ b/model-00025-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c847991ac276820b51f8b23afb509b3c582ab9a6bbc0d737ee6148aa58215cf7 +size 2177954720 diff --git a/model-00026-of-00073.safetensors b/model-00026-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0878898b2bbee01fece50654f41f0c4ce2ebba0 --- /dev/null +++ b/model-00026-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78d69f06e29de3eeb3e8df6353d418cfca5a6abb432f90b95c750252e5d3b7e1 +size 4248207640 diff --git a/model-00027-of-00073.safetensors b/model-00027-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..988a30b674388c7c582e481a987a37e48cb2ac93 --- /dev/null +++ b/model-00027-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4bfc54df034fbc9efe97ad0c08daedf84287c6f360c88d21a762345baff2ad +size 2177954720 diff --git a/model-00028-of-00073.safetensors b/model-00028-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..15e444843fc91d96ca903cb006caf5d99846de73 --- /dev/null +++ b/model-00028-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2301da5402b74812725f99d892af657a421d7d3ff1fedf3309c28aa0fa0e4353 +size 4248207640 diff --git a/model-00029-of-00073.safetensors b/model-00029-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7a4c8877f36c5f2590cf8b8bbeede64b859b7188 --- /dev/null +++ b/model-00029-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1760d57e597bea02cb84767a4f05aa4eb455a3e62bf3a0d5c4057573c5a9f1c6 +size 2177954720 diff --git a/model-00030-of-00073.safetensors b/model-00030-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..934dcb5bfa155c571fe3ab8cdbabffce45ca1824 --- /dev/null +++ b/model-00030-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad8c1f5337c4b372da5d49cfeca7996e85cf3f8af0323359abfc5a38539db4d1 +size 4248207640 diff --git a/model-00031-of-00073.safetensors b/model-00031-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d00d57eb25543f46e212fe4a0500e48627f3819d --- /dev/null +++ b/model-00031-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9db976e1804aa135d517a53275a72c450cd6b33b57cedc2bf1a8cedb2d2eb4 +size 2177954720 diff --git a/model-00032-of-00073.safetensors b/model-00032-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3cc323a0b5cf83aeb072e6aeee414ddbb742a8e3 --- /dev/null +++ b/model-00032-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a9dc8df6da9507d6f99547ed7b6ab17793cbcd5a81c0c2f3439ff8f6c1d10c9 +size 4248207640 diff --git a/model-00033-of-00073.safetensors b/model-00033-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d92f6ed43f4753a814d64ef6c02c7448aad35dc9 --- /dev/null +++ b/model-00033-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f148d7a6120c88c1087a9fe945371f1d1430bd272e21fcdebf358de56cb62e +size 2177954720 diff --git a/model-00034-of-00073.safetensors b/model-00034-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..088d89c3ce46312b5fb168b42c9b138975af0fdd --- /dev/null +++ b/model-00034-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2278f08494e6ef08a3e4b5794fc650970b01bb6652502c3bf861d9ee39024d52 +size 4248207640 diff --git a/model-00035-of-00073.safetensors b/model-00035-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..749f8e391415a9841c647bebe1c0e9a546e15793 --- /dev/null +++ b/model-00035-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad88fc9f3d9c216003a63a4a43503f662aa6f7ceec98f53d9f899ecf78420e0 +size 2177954720 diff --git a/model-00036-of-00073.safetensors b/model-00036-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8e95409219a417441b9a780689e1c0c90bf0d3c --- /dev/null +++ b/model-00036-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d28428c507c8b4e042c656f2db6c30fc9db7dd6f6c0157dcda930c2a3ea4d11c +size 4248207640 diff --git a/model-00037-of-00073.safetensors b/model-00037-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b48b15eaa4a14a2b471dd1e72d8f95a01e00064 --- /dev/null +++ b/model-00037-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5f7c63cacd4a0f5ddef7b5a382652504839d6fde62e53fad13bd7c9cec8c50 +size 2177954720 diff --git a/model-00038-of-00073.safetensors b/model-00038-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..849397898f8f12af6c3f25eb4035ca339cbf60ca --- /dev/null +++ b/model-00038-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9704e3b5209e51b7310530e1da1e31b4aafb290a21b1957990b59ee98c08312f +size 4248207640 diff --git a/model-00039-of-00073.safetensors b/model-00039-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..682a31cbb167790a0b10a7e37daac2eadf627d47 --- /dev/null +++ b/model-00039-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2a8cbe5c277b58d43031b4f4b8f120a431a305109f3f3b277c3147d3888462 +size 2177954720 diff --git a/model-00040-of-00073.safetensors b/model-00040-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87db2650c968dc085ff0badeaee1c644084e9842 --- /dev/null +++ b/model-00040-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63132593ac1bd4883db66340d38ef61685065e53db5ac40276bbfc1d83fb8bb8 +size 4248207640 diff --git a/model-00041-of-00073.safetensors b/model-00041-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7465aa7999fcc0f8579144243d22e350a85f8450 --- /dev/null +++ b/model-00041-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c457d4cf3c9f013009a45e4795cd50f015cc2d405a7e0b9ec168dcbf8f22265 +size 2177954720 diff --git a/model-00042-of-00073.safetensors b/model-00042-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e077fbf39e8f59fb092cad7e9beb0f11a35d88a2 --- /dev/null +++ b/model-00042-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e39c7084ce12ee967b6dd15c8e1849fa550d50fd8e7d123064c3b3b5a233118a +size 4248207640 diff --git a/model-00043-of-00073.safetensors b/model-00043-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd7d491f35cdd90d1aebaa971b4d330ba2b5ea6c --- /dev/null +++ b/model-00043-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5773134ef28cfc7cf7f4af256242b14e543947d9fff2bf4a095406a73863c5f +size 2177954720 diff --git a/model-00044-of-00073.safetensors b/model-00044-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dff09063452d8a0763e6ca7f2332d30c1df12eff --- /dev/null +++ b/model-00044-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3cfc8f6772d9ec8ccbbd1213069d0b8213d1f7bf4658011ac9fcb12504e941 +size 4248207640 diff --git a/model-00045-of-00073.safetensors b/model-00045-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5785bdf79530ddd5ad97104b7250440f760bea9d --- /dev/null +++ b/model-00045-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8964545596d0aa661b9c9a91abfdda250bd17f6310670f130e0d08f6f64ea3b3 +size 2177954752 diff --git a/model-00046-of-00073.safetensors b/model-00046-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f594f984ea46eff3d7723c171a02dd4f2378589 --- /dev/null +++ b/model-00046-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1939048181675b836a1f11862169988e54ecf788d4b74421f664052d565c07a +size 4248207640 diff --git a/model-00047-of-00073.safetensors b/model-00047-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4bf8945f3b0bc6b331f90a0f912425547c1726f9 --- /dev/null +++ b/model-00047-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a17484c45aed703077f81d42f438491d080999fc12e45a3edd9bbf5f5230a9 +size 2177954752 diff --git a/model-00048-of-00073.safetensors b/model-00048-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0683c5739356157326426e735f6e45b0ac3999c6 --- /dev/null +++ b/model-00048-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b5ff6161f070bca5bf419c49123a327e601f1526c1256c0f9151d3e1f53b4fa +size 4248207640 diff --git a/model-00049-of-00073.safetensors b/model-00049-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a43465bd509af1491363f26c4af3516577f80c6 --- /dev/null +++ b/model-00049-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5987ba46427a4dd4e19b61ba2ffbe7cb0b9944465f8b5f8a829e909951278e +size 2177954752 diff --git a/model-00050-of-00073.safetensors b/model-00050-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec92fb99018bb46f07247e1d0cb26ae87e64ccce --- /dev/null +++ b/model-00050-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65373fb48bed15e6db585aec180e53098ef5d59368265be9aa54da55f9ae0e05 +size 4248207640 diff --git a/model-00051-of-00073.safetensors b/model-00051-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e569ce96f0c33a60b355eeac6c883e16f1aa8969 --- /dev/null +++ b/model-00051-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea6bde31599c4042dd4f1d628bc2d1e85f092336239e9884acfad9aef4c3673 +size 2177954752 diff --git a/model-00052-of-00073.safetensors b/model-00052-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19291c6fd6b13eefbf7b721a2bf67b482efd69c6 --- /dev/null +++ b/model-00052-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3fbc51fb6592d3a61b1769c06c2a922fbe396432626191e2b036de3e507d80 +size 4248207640 diff --git a/model-00053-of-00073.safetensors b/model-00053-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6da80ade5bffc04c7d136b5a56d670518d45f826 --- /dev/null +++ b/model-00053-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e64ca8874d03e65f572f14e98f4292ca8128fdc347b101e3aa4a9e87d8eb40 +size 2177954752 diff --git a/model-00054-of-00073.safetensors b/model-00054-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d93e6623a9cb4e3de6bf754dc568c3d43496a8c0 --- /dev/null +++ b/model-00054-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0531a970dd6c5d8e7cbae562255f6a3a9436546c311a29602e0fcc0fd8a84e3 +size 4248207640 diff --git a/model-00055-of-00073.safetensors b/model-00055-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2865cd91fe491622c2f605abae434af258dbb633 --- /dev/null +++ b/model-00055-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a036a3f27720e325441159ed148dcfe385dc97f944872261392187ba87ca50e +size 2177954752 diff --git a/model-00056-of-00073.safetensors b/model-00056-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e7113d9e7d57947433e98a77c58c13231e34c68 --- /dev/null +++ b/model-00056-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05fa63d01ec993405b2926e45798aea2b185200c2f008aeeaea68d0a6945c98 +size 4248207640 diff --git a/model-00057-of-00073.safetensors b/model-00057-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e398c8663aa69de7a9b7b432f478d01d8873a7de --- /dev/null +++ b/model-00057-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c643a7f9f1352fddc2de0bf737b9f7d36fb50ce16c4cdcb95ee591b3466e3e9 +size 2177954752 diff --git a/model-00058-of-00073.safetensors b/model-00058-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bad9865380e13fc1ab55d7135f68a43edfa0b21 --- /dev/null +++ b/model-00058-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8641d3b84630260b190480647bc640fd122dbe24a6dd465b6812a17ba73989 +size 4248207640 diff --git a/model-00059-of-00073.safetensors b/model-00059-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..577d5dae86aafdb50a162a0b649f5355ec37e38a --- /dev/null +++ b/model-00059-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426e353a74f42fca266411f5b637b9abe6469865993665a9cb646964458450bf +size 2177954752 diff --git a/model-00060-of-00073.safetensors b/model-00060-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff2ead735964c12ba27e21fd67e94edcc02baedc --- /dev/null +++ b/model-00060-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2351f41533aec995d9780f0c6a4b47279ab381e02709b46fe618487503602a +size 4248207640 diff --git a/model-00061-of-00073.safetensors b/model-00061-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa2407026cbd87a629e0c4ce7041a7ca67845ccf --- /dev/null +++ b/model-00061-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd9b620877bf033462ae33bd8055d738bff12ff52f2412225be5b21bb21eaa0 +size 2177954752 diff --git a/model-00062-of-00073.safetensors b/model-00062-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2d3cf4ccf45a0fc5ac5dae3961e74f5c2493d3d --- /dev/null +++ b/model-00062-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21973e03b03ac1b40821ecfe3e5c184ad04e6ef527e0b0a44a2f1879414f3ef +size 4248207640 diff --git a/model-00063-of-00073.safetensors b/model-00063-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51141c8e278ab43d3cbb568976c274cec96a891e --- /dev/null +++ b/model-00063-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2617143e41690b4d1a560bd0380568a310079de0d1c817afa2a9be8a812c1578 +size 2177954752 diff --git a/model-00064-of-00073.safetensors b/model-00064-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bd945a93777070b19bc0f2d1d125ad656effafc --- /dev/null +++ b/model-00064-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7435c449bd45bf5a50e92bc22767fb6114afaaa5f3d12f0948649ff3eaad2353 +size 4248207640 diff --git a/model-00065-of-00073.safetensors b/model-00065-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22a1aecc7dfb8e61ad23c4abcc4736d652628538 --- /dev/null +++ b/model-00065-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f5f937977c9767685f90b2b0966c2b70751db6c0ccb030eeb89d174919f5b9 +size 2177954752 diff --git a/model-00066-of-00073.safetensors b/model-00066-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db0d65e36e3aff15a2a3698ca42bc5af09df6b40 --- /dev/null +++ b/model-00066-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbcd434c09d76339b3985c613662226dae9548395066eed1fbde54062e74932 +size 4248207640 diff --git a/model-00067-of-00073.safetensors b/model-00067-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d78e1003b555ce5d98ec2ceefe39750fc3dccc01 --- /dev/null +++ b/model-00067-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc96a5dc2eeafbe02d1b64344c1eea7228146ed00f5e3ca0eaf1bdb597328b3f +size 2177954752 diff --git a/model-00068-of-00073.safetensors b/model-00068-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d580dfb8ebe5560b1f300502947c2dd298896949 --- /dev/null +++ b/model-00068-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1f91f706f2bb4eb1d88b80208fafd72879fb5501bedc2fa87f85c4e2e6aa0ee +size 4248207640 diff --git a/model-00069-of-00073.safetensors b/model-00069-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e63f7240c2c55471515437c091eb63926516c21d --- /dev/null +++ b/model-00069-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec6dc5b9590b10027656b0da9bc61e1c9ee28db547baeabf4f1f6bec92363d9 +size 2177954752 diff --git a/model-00070-of-00073.safetensors b/model-00070-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12f4adbd05ea78a9774d4fb7818c600e720e62e5 --- /dev/null +++ b/model-00070-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:964669a60753219bb8f516f22d2985b609743436f665afa55dc9c95c40f0dd06 +size 4248207640 diff --git a/model-00071-of-00073.safetensors b/model-00071-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..550d9d6d0b8b736d965a9a4dbab389c091043a51 --- /dev/null +++ b/model-00071-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde9252c0865f1096dd3192e8f974c7cc8833914c72054f3379626c4fce7fc40 +size 2177954752 diff --git a/model-00072-of-00073.safetensors b/model-00072-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6379f048d14c4ed96435e6ce872ae048608ac57e --- /dev/null +++ b/model-00072-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d5e2198840177789319fc6ac995273dfe0b6b72325e40f641669206f49d8f3 +size 4248207640 diff --git a/model-00073-of-00073.safetensors b/model-00073-of-00073.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eaa45d8f37c71b0136457d89a39751cf452389ce --- /dev/null +++ b/model-00073-of-00073.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e493d8c2d647686efbe51251c6c2bf7473dc98090b99bbe194eacfac3302c675 +size 3282388536 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ac32376906551efb22fd6405ca90ba5c5c4e90ec --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,623 @@ +{ + "metadata": { + "total_parameters": 116829156672, + "total_size": 233658313344 + }, + "weight_map": { + "lm_head.weight": "model-00073-of-00073.safetensors", + "model.embed_tokens.weight": "model-00001-of-00073.safetensors", + "model.layers.0.input_layernorm.weight": "model-00003-of-00073.safetensors", + "model.layers.0.mlp.experts.down_proj": "model-00003-of-00073.safetensors", + "model.layers.0.mlp.experts.down_proj_bias": "model-00003-of-00073.safetensors", + "model.layers.0.mlp.experts.gate_up_proj": "model-00002-of-00073.safetensors", + "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00002-of-00073.safetensors", + "model.layers.0.mlp.router.bias": "model-00001-of-00073.safetensors", + "model.layers.0.mlp.router.weight": "model-00001-of-00073.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00073.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.sinks": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00073.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00073.safetensors", + "model.layers.1.input_layernorm.weight": "model-00005-of-00073.safetensors", + "model.layers.1.mlp.experts.down_proj": "model-00005-of-00073.safetensors", + "model.layers.1.mlp.experts.down_proj_bias": "model-00005-of-00073.safetensors", + "model.layers.1.mlp.experts.gate_up_proj": "model-00004-of-00073.safetensors", + "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00004-of-00073.safetensors", + "model.layers.1.mlp.router.bias": "model-00003-of-00073.safetensors", + "model.layers.1.mlp.router.weight": "model-00003-of-00073.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00073.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.o_proj.bias": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.sinks": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00073.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00073.safetensors", + "model.layers.10.input_layernorm.weight": "model-00023-of-00073.safetensors", + "model.layers.10.mlp.experts.down_proj": "model-00023-of-00073.safetensors", + "model.layers.10.mlp.experts.down_proj_bias": "model-00023-of-00073.safetensors", + "model.layers.10.mlp.experts.gate_up_proj": "model-00022-of-00073.safetensors", + "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00022-of-00073.safetensors", + "model.layers.10.mlp.router.bias": "model-00021-of-00073.safetensors", + "model.layers.10.mlp.router.weight": "model-00021-of-00073.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00023-of-00073.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.o_proj.bias": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.sinks": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00021-of-00073.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00021-of-00073.safetensors", + "model.layers.11.input_layernorm.weight": "model-00025-of-00073.safetensors", + "model.layers.11.mlp.experts.down_proj": "model-00025-of-00073.safetensors", + "model.layers.11.mlp.experts.down_proj_bias": "model-00025-of-00073.safetensors", + "model.layers.11.mlp.experts.gate_up_proj": "model-00024-of-00073.safetensors", + "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00024-of-00073.safetensors", + "model.layers.11.mlp.router.bias": "model-00023-of-00073.safetensors", + "model.layers.11.mlp.router.weight": "model-00023-of-00073.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00025-of-00073.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.o_proj.bias": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.sinks": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00023-of-00073.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00023-of-00073.safetensors", + "model.layers.12.input_layernorm.weight": "model-00027-of-00073.safetensors", + "model.layers.12.mlp.experts.down_proj": "model-00027-of-00073.safetensors", + "model.layers.12.mlp.experts.down_proj_bias": "model-00027-of-00073.safetensors", + "model.layers.12.mlp.experts.gate_up_proj": "model-00026-of-00073.safetensors", + "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00026-of-00073.safetensors", + "model.layers.12.mlp.router.bias": "model-00025-of-00073.safetensors", + "model.layers.12.mlp.router.weight": "model-00025-of-00073.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00027-of-00073.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.o_proj.bias": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.sinks": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00025-of-00073.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00025-of-00073.safetensors", + "model.layers.13.input_layernorm.weight": "model-00029-of-00073.safetensors", + "model.layers.13.mlp.experts.down_proj": "model-00029-of-00073.safetensors", + "model.layers.13.mlp.experts.down_proj_bias": "model-00029-of-00073.safetensors", + "model.layers.13.mlp.experts.gate_up_proj": "model-00028-of-00073.safetensors", + "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00028-of-00073.safetensors", + "model.layers.13.mlp.router.bias": "model-00027-of-00073.safetensors", + "model.layers.13.mlp.router.weight": "model-00027-of-00073.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00029-of-00073.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.o_proj.bias": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.sinks": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00027-of-00073.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00027-of-00073.safetensors", + "model.layers.14.input_layernorm.weight": "model-00031-of-00073.safetensors", + "model.layers.14.mlp.experts.down_proj": "model-00031-of-00073.safetensors", + "model.layers.14.mlp.experts.down_proj_bias": "model-00031-of-00073.safetensors", + "model.layers.14.mlp.experts.gate_up_proj": "model-00030-of-00073.safetensors", + "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00030-of-00073.safetensors", + "model.layers.14.mlp.router.bias": "model-00029-of-00073.safetensors", + "model.layers.14.mlp.router.weight": "model-00029-of-00073.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00031-of-00073.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.o_proj.bias": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.sinks": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00029-of-00073.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00029-of-00073.safetensors", + "model.layers.15.input_layernorm.weight": "model-00033-of-00073.safetensors", + "model.layers.15.mlp.experts.down_proj": "model-00033-of-00073.safetensors", + "model.layers.15.mlp.experts.down_proj_bias": "model-00033-of-00073.safetensors", + "model.layers.15.mlp.experts.gate_up_proj": "model-00032-of-00073.safetensors", + "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00032-of-00073.safetensors", + "model.layers.15.mlp.router.bias": "model-00031-of-00073.safetensors", + "model.layers.15.mlp.router.weight": "model-00031-of-00073.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00033-of-00073.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.o_proj.bias": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.sinks": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00031-of-00073.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00031-of-00073.safetensors", + "model.layers.16.input_layernorm.weight": "model-00035-of-00073.safetensors", + "model.layers.16.mlp.experts.down_proj": "model-00035-of-00073.safetensors", + "model.layers.16.mlp.experts.down_proj_bias": "model-00035-of-00073.safetensors", + "model.layers.16.mlp.experts.gate_up_proj": "model-00034-of-00073.safetensors", + "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00034-of-00073.safetensors", + "model.layers.16.mlp.router.bias": "model-00033-of-00073.safetensors", + "model.layers.16.mlp.router.weight": "model-00033-of-00073.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00035-of-00073.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.o_proj.bias": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.sinks": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00033-of-00073.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00033-of-00073.safetensors", + "model.layers.17.input_layernorm.weight": "model-00037-of-00073.safetensors", + "model.layers.17.mlp.experts.down_proj": "model-00037-of-00073.safetensors", + "model.layers.17.mlp.experts.down_proj_bias": "model-00037-of-00073.safetensors", + "model.layers.17.mlp.experts.gate_up_proj": "model-00036-of-00073.safetensors", + "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00036-of-00073.safetensors", + "model.layers.17.mlp.router.bias": "model-00035-of-00073.safetensors", + "model.layers.17.mlp.router.weight": "model-00035-of-00073.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00037-of-00073.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.o_proj.bias": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.sinks": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00035-of-00073.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00035-of-00073.safetensors", + "model.layers.18.input_layernorm.weight": "model-00039-of-00073.safetensors", + "model.layers.18.mlp.experts.down_proj": "model-00039-of-00073.safetensors", + "model.layers.18.mlp.experts.down_proj_bias": "model-00039-of-00073.safetensors", + "model.layers.18.mlp.experts.gate_up_proj": "model-00038-of-00073.safetensors", + "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00038-of-00073.safetensors", + "model.layers.18.mlp.router.bias": "model-00037-of-00073.safetensors", + "model.layers.18.mlp.router.weight": "model-00037-of-00073.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00039-of-00073.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.o_proj.bias": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.sinks": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00037-of-00073.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00037-of-00073.safetensors", + "model.layers.19.input_layernorm.weight": "model-00041-of-00073.safetensors", + "model.layers.19.mlp.experts.down_proj": "model-00041-of-00073.safetensors", + "model.layers.19.mlp.experts.down_proj_bias": "model-00041-of-00073.safetensors", + "model.layers.19.mlp.experts.gate_up_proj": "model-00040-of-00073.safetensors", + "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00040-of-00073.safetensors", + "model.layers.19.mlp.router.bias": "model-00039-of-00073.safetensors", + "model.layers.19.mlp.router.weight": "model-00039-of-00073.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00041-of-00073.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.o_proj.bias": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.sinks": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00039-of-00073.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00039-of-00073.safetensors", + "model.layers.2.input_layernorm.weight": "model-00007-of-00073.safetensors", + "model.layers.2.mlp.experts.down_proj": "model-00007-of-00073.safetensors", + "model.layers.2.mlp.experts.down_proj_bias": "model-00007-of-00073.safetensors", + "model.layers.2.mlp.experts.gate_up_proj": "model-00006-of-00073.safetensors", + "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00006-of-00073.safetensors", + "model.layers.2.mlp.router.bias": "model-00005-of-00073.safetensors", + "model.layers.2.mlp.router.weight": "model-00005-of-00073.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00073.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.o_proj.bias": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.sinks": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00073.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00073.safetensors", + "model.layers.20.input_layernorm.weight": "model-00043-of-00073.safetensors", + "model.layers.20.mlp.experts.down_proj": "model-00043-of-00073.safetensors", + "model.layers.20.mlp.experts.down_proj_bias": "model-00043-of-00073.safetensors", + "model.layers.20.mlp.experts.gate_up_proj": "model-00042-of-00073.safetensors", + "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00042-of-00073.safetensors", + "model.layers.20.mlp.router.bias": "model-00041-of-00073.safetensors", + "model.layers.20.mlp.router.weight": "model-00041-of-00073.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00043-of-00073.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.o_proj.bias": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.sinks": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00041-of-00073.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00041-of-00073.safetensors", + "model.layers.21.input_layernorm.weight": "model-00045-of-00073.safetensors", + "model.layers.21.mlp.experts.down_proj": "model-00045-of-00073.safetensors", + "model.layers.21.mlp.experts.down_proj_bias": "model-00045-of-00073.safetensors", + "model.layers.21.mlp.experts.gate_up_proj": "model-00044-of-00073.safetensors", + "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00044-of-00073.safetensors", + "model.layers.21.mlp.router.bias": "model-00043-of-00073.safetensors", + "model.layers.21.mlp.router.weight": "model-00043-of-00073.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00045-of-00073.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.o_proj.bias": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.sinks": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00043-of-00073.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00043-of-00073.safetensors", + "model.layers.22.input_layernorm.weight": "model-00047-of-00073.safetensors", + "model.layers.22.mlp.experts.down_proj": "model-00047-of-00073.safetensors", + "model.layers.22.mlp.experts.down_proj_bias": "model-00047-of-00073.safetensors", + "model.layers.22.mlp.experts.gate_up_proj": "model-00046-of-00073.safetensors", + "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00046-of-00073.safetensors", + "model.layers.22.mlp.router.bias": "model-00045-of-00073.safetensors", + "model.layers.22.mlp.router.weight": "model-00045-of-00073.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00047-of-00073.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.o_proj.bias": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.sinks": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00045-of-00073.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00045-of-00073.safetensors", + "model.layers.23.input_layernorm.weight": "model-00049-of-00073.safetensors", + "model.layers.23.mlp.experts.down_proj": "model-00049-of-00073.safetensors", + "model.layers.23.mlp.experts.down_proj_bias": "model-00049-of-00073.safetensors", + "model.layers.23.mlp.experts.gate_up_proj": "model-00048-of-00073.safetensors", + "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00048-of-00073.safetensors", + "model.layers.23.mlp.router.bias": "model-00047-of-00073.safetensors", + "model.layers.23.mlp.router.weight": "model-00047-of-00073.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00049-of-00073.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.o_proj.bias": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.sinks": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00047-of-00073.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00047-of-00073.safetensors", + "model.layers.24.input_layernorm.weight": "model-00051-of-00073.safetensors", + "model.layers.24.mlp.experts.down_proj": "model-00051-of-00073.safetensors", + "model.layers.24.mlp.experts.down_proj_bias": "model-00051-of-00073.safetensors", + "model.layers.24.mlp.experts.gate_up_proj": "model-00050-of-00073.safetensors", + "model.layers.24.mlp.experts.gate_up_proj_bias": "model-00050-of-00073.safetensors", + "model.layers.24.mlp.router.bias": "model-00049-of-00073.safetensors", + "model.layers.24.mlp.router.weight": "model-00049-of-00073.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00051-of-00073.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.o_proj.bias": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.sinks": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00049-of-00073.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00049-of-00073.safetensors", + "model.layers.25.input_layernorm.weight": "model-00053-of-00073.safetensors", + "model.layers.25.mlp.experts.down_proj": "model-00053-of-00073.safetensors", + "model.layers.25.mlp.experts.down_proj_bias": "model-00053-of-00073.safetensors", + "model.layers.25.mlp.experts.gate_up_proj": "model-00052-of-00073.safetensors", + "model.layers.25.mlp.experts.gate_up_proj_bias": "model-00052-of-00073.safetensors", + "model.layers.25.mlp.router.bias": "model-00051-of-00073.safetensors", + "model.layers.25.mlp.router.weight": "model-00051-of-00073.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00053-of-00073.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.o_proj.bias": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.sinks": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00051-of-00073.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00051-of-00073.safetensors", + "model.layers.26.input_layernorm.weight": "model-00055-of-00073.safetensors", + "model.layers.26.mlp.experts.down_proj": "model-00055-of-00073.safetensors", + "model.layers.26.mlp.experts.down_proj_bias": "model-00055-of-00073.safetensors", + "model.layers.26.mlp.experts.gate_up_proj": "model-00054-of-00073.safetensors", + "model.layers.26.mlp.experts.gate_up_proj_bias": "model-00054-of-00073.safetensors", + "model.layers.26.mlp.router.bias": "model-00053-of-00073.safetensors", + "model.layers.26.mlp.router.weight": "model-00053-of-00073.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00055-of-00073.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.o_proj.bias": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.sinks": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00053-of-00073.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00053-of-00073.safetensors", + "model.layers.27.input_layernorm.weight": "model-00057-of-00073.safetensors", + "model.layers.27.mlp.experts.down_proj": "model-00057-of-00073.safetensors", + "model.layers.27.mlp.experts.down_proj_bias": "model-00057-of-00073.safetensors", + "model.layers.27.mlp.experts.gate_up_proj": "model-00056-of-00073.safetensors", + "model.layers.27.mlp.experts.gate_up_proj_bias": "model-00056-of-00073.safetensors", + "model.layers.27.mlp.router.bias": "model-00055-of-00073.safetensors", + "model.layers.27.mlp.router.weight": "model-00055-of-00073.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00057-of-00073.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.o_proj.bias": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.sinks": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00055-of-00073.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00055-of-00073.safetensors", + "model.layers.28.input_layernorm.weight": "model-00059-of-00073.safetensors", + "model.layers.28.mlp.experts.down_proj": "model-00059-of-00073.safetensors", + "model.layers.28.mlp.experts.down_proj_bias": "model-00059-of-00073.safetensors", + "model.layers.28.mlp.experts.gate_up_proj": "model-00058-of-00073.safetensors", + "model.layers.28.mlp.experts.gate_up_proj_bias": "model-00058-of-00073.safetensors", + "model.layers.28.mlp.router.bias": "model-00057-of-00073.safetensors", + "model.layers.28.mlp.router.weight": "model-00057-of-00073.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00059-of-00073.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.o_proj.bias": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.sinks": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00057-of-00073.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00057-of-00073.safetensors", + "model.layers.29.input_layernorm.weight": "model-00061-of-00073.safetensors", + "model.layers.29.mlp.experts.down_proj": "model-00061-of-00073.safetensors", + "model.layers.29.mlp.experts.down_proj_bias": "model-00061-of-00073.safetensors", + "model.layers.29.mlp.experts.gate_up_proj": "model-00060-of-00073.safetensors", + "model.layers.29.mlp.experts.gate_up_proj_bias": "model-00060-of-00073.safetensors", + "model.layers.29.mlp.router.bias": "model-00059-of-00073.safetensors", + "model.layers.29.mlp.router.weight": "model-00059-of-00073.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00061-of-00073.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.o_proj.bias": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.sinks": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00059-of-00073.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00059-of-00073.safetensors", + "model.layers.3.input_layernorm.weight": "model-00009-of-00073.safetensors", + "model.layers.3.mlp.experts.down_proj": "model-00009-of-00073.safetensors", + "model.layers.3.mlp.experts.down_proj_bias": "model-00009-of-00073.safetensors", + "model.layers.3.mlp.experts.gate_up_proj": "model-00008-of-00073.safetensors", + "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00008-of-00073.safetensors", + "model.layers.3.mlp.router.bias": "model-00007-of-00073.safetensors", + "model.layers.3.mlp.router.weight": "model-00007-of-00073.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00073.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.o_proj.bias": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.sinks": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00073.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00073.safetensors", + "model.layers.30.input_layernorm.weight": "model-00063-of-00073.safetensors", + "model.layers.30.mlp.experts.down_proj": "model-00063-of-00073.safetensors", + "model.layers.30.mlp.experts.down_proj_bias": "model-00063-of-00073.safetensors", + "model.layers.30.mlp.experts.gate_up_proj": "model-00062-of-00073.safetensors", + "model.layers.30.mlp.experts.gate_up_proj_bias": "model-00062-of-00073.safetensors", + "model.layers.30.mlp.router.bias": "model-00061-of-00073.safetensors", + "model.layers.30.mlp.router.weight": "model-00061-of-00073.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00063-of-00073.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.o_proj.bias": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.sinks": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00061-of-00073.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00061-of-00073.safetensors", + "model.layers.31.input_layernorm.weight": "model-00065-of-00073.safetensors", + "model.layers.31.mlp.experts.down_proj": "model-00065-of-00073.safetensors", + "model.layers.31.mlp.experts.down_proj_bias": "model-00065-of-00073.safetensors", + "model.layers.31.mlp.experts.gate_up_proj": "model-00064-of-00073.safetensors", + "model.layers.31.mlp.experts.gate_up_proj_bias": "model-00064-of-00073.safetensors", + "model.layers.31.mlp.router.bias": "model-00063-of-00073.safetensors", + "model.layers.31.mlp.router.weight": "model-00063-of-00073.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00065-of-00073.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.o_proj.bias": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.sinks": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00063-of-00073.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00063-of-00073.safetensors", + "model.layers.32.input_layernorm.weight": "model-00067-of-00073.safetensors", + "model.layers.32.mlp.experts.down_proj": "model-00067-of-00073.safetensors", + "model.layers.32.mlp.experts.down_proj_bias": "model-00067-of-00073.safetensors", + "model.layers.32.mlp.experts.gate_up_proj": "model-00066-of-00073.safetensors", + "model.layers.32.mlp.experts.gate_up_proj_bias": "model-00066-of-00073.safetensors", + "model.layers.32.mlp.router.bias": "model-00065-of-00073.safetensors", + "model.layers.32.mlp.router.weight": "model-00065-of-00073.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00067-of-00073.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.o_proj.bias": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.sinks": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00065-of-00073.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00065-of-00073.safetensors", + "model.layers.33.input_layernorm.weight": "model-00069-of-00073.safetensors", + "model.layers.33.mlp.experts.down_proj": "model-00069-of-00073.safetensors", + "model.layers.33.mlp.experts.down_proj_bias": "model-00069-of-00073.safetensors", + "model.layers.33.mlp.experts.gate_up_proj": "model-00068-of-00073.safetensors", + "model.layers.33.mlp.experts.gate_up_proj_bias": "model-00068-of-00073.safetensors", + "model.layers.33.mlp.router.bias": "model-00067-of-00073.safetensors", + "model.layers.33.mlp.router.weight": "model-00067-of-00073.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00069-of-00073.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.o_proj.bias": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.sinks": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00067-of-00073.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00067-of-00073.safetensors", + "model.layers.34.input_layernorm.weight": "model-00071-of-00073.safetensors", + "model.layers.34.mlp.experts.down_proj": "model-00071-of-00073.safetensors", + "model.layers.34.mlp.experts.down_proj_bias": "model-00071-of-00073.safetensors", + "model.layers.34.mlp.experts.gate_up_proj": "model-00070-of-00073.safetensors", + "model.layers.34.mlp.experts.gate_up_proj_bias": "model-00070-of-00073.safetensors", + "model.layers.34.mlp.router.bias": "model-00069-of-00073.safetensors", + "model.layers.34.mlp.router.weight": "model-00069-of-00073.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00071-of-00073.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.o_proj.bias": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.sinks": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00069-of-00073.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00069-of-00073.safetensors", + "model.layers.35.input_layernorm.weight": "model-00073-of-00073.safetensors", + "model.layers.35.mlp.experts.down_proj": "model-00073-of-00073.safetensors", + "model.layers.35.mlp.experts.down_proj_bias": "model-00073-of-00073.safetensors", + "model.layers.35.mlp.experts.gate_up_proj": "model-00072-of-00073.safetensors", + "model.layers.35.mlp.experts.gate_up_proj_bias": "model-00072-of-00073.safetensors", + "model.layers.35.mlp.router.bias": "model-00071-of-00073.safetensors", + "model.layers.35.mlp.router.weight": "model-00071-of-00073.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00073-of-00073.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.o_proj.bias": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.sinks": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00071-of-00073.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00071-of-00073.safetensors", + "model.layers.4.input_layernorm.weight": "model-00011-of-00073.safetensors", + "model.layers.4.mlp.experts.down_proj": "model-00011-of-00073.safetensors", + "model.layers.4.mlp.experts.down_proj_bias": "model-00011-of-00073.safetensors", + "model.layers.4.mlp.experts.gate_up_proj": "model-00010-of-00073.safetensors", + "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00010-of-00073.safetensors", + "model.layers.4.mlp.router.bias": "model-00009-of-00073.safetensors", + "model.layers.4.mlp.router.weight": "model-00009-of-00073.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00073.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.o_proj.bias": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.sinks": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00009-of-00073.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00073.safetensors", + "model.layers.5.input_layernorm.weight": "model-00013-of-00073.safetensors", + "model.layers.5.mlp.experts.down_proj": "model-00013-of-00073.safetensors", + "model.layers.5.mlp.experts.down_proj_bias": "model-00013-of-00073.safetensors", + "model.layers.5.mlp.experts.gate_up_proj": "model-00012-of-00073.safetensors", + "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00012-of-00073.safetensors", + "model.layers.5.mlp.router.bias": "model-00011-of-00073.safetensors", + "model.layers.5.mlp.router.weight": "model-00011-of-00073.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00073.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.o_proj.bias": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.sinks": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00011-of-00073.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00073.safetensors", + "model.layers.6.input_layernorm.weight": "model-00015-of-00073.safetensors", + "model.layers.6.mlp.experts.down_proj": "model-00015-of-00073.safetensors", + "model.layers.6.mlp.experts.down_proj_bias": "model-00015-of-00073.safetensors", + "model.layers.6.mlp.experts.gate_up_proj": "model-00014-of-00073.safetensors", + "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00014-of-00073.safetensors", + "model.layers.6.mlp.router.bias": "model-00013-of-00073.safetensors", + "model.layers.6.mlp.router.weight": "model-00013-of-00073.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00073.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.o_proj.bias": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.sinks": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00013-of-00073.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00073.safetensors", + "model.layers.7.input_layernorm.weight": "model-00017-of-00073.safetensors", + "model.layers.7.mlp.experts.down_proj": "model-00017-of-00073.safetensors", + "model.layers.7.mlp.experts.down_proj_bias": "model-00017-of-00073.safetensors", + "model.layers.7.mlp.experts.gate_up_proj": "model-00016-of-00073.safetensors", + "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00016-of-00073.safetensors", + "model.layers.7.mlp.router.bias": "model-00015-of-00073.safetensors", + "model.layers.7.mlp.router.weight": "model-00015-of-00073.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00017-of-00073.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.o_proj.bias": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.sinks": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00015-of-00073.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00073.safetensors", + "model.layers.8.input_layernorm.weight": "model-00019-of-00073.safetensors", + "model.layers.8.mlp.experts.down_proj": "model-00019-of-00073.safetensors", + "model.layers.8.mlp.experts.down_proj_bias": "model-00019-of-00073.safetensors", + "model.layers.8.mlp.experts.gate_up_proj": "model-00018-of-00073.safetensors", + "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00018-of-00073.safetensors", + "model.layers.8.mlp.router.bias": "model-00017-of-00073.safetensors", + "model.layers.8.mlp.router.weight": "model-00017-of-00073.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00019-of-00073.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.o_proj.bias": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.sinks": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00017-of-00073.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00017-of-00073.safetensors", + "model.layers.9.input_layernorm.weight": "model-00021-of-00073.safetensors", + "model.layers.9.mlp.experts.down_proj": "model-00021-of-00073.safetensors", + "model.layers.9.mlp.experts.down_proj_bias": "model-00021-of-00073.safetensors", + "model.layers.9.mlp.experts.gate_up_proj": "model-00020-of-00073.safetensors", + "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00020-of-00073.safetensors", + "model.layers.9.mlp.router.bias": "model-00019-of-00073.safetensors", + "model.layers.9.mlp.router.weight": "model-00019-of-00073.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00021-of-00073.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.o_proj.bias": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.sinks": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00019-of-00073.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00073.safetensors", + "model.norm.weight": "model-00073-of-00073.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..6274cc1bd159aa75de771315558e5cac7dd8bea0 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|return|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..6ec3ef1795cbbda6b7cb7d1f114919cbe3fdd647 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3 +size 27868174 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c021cddb0a9dd35b1bf83a9f145be2d9b3757891 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,183 @@ +{ + "added_tokens_decoder": { + "199998": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "199999": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200000": { + "content": "<|reserved_200000|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200001": { + "content": "<|reserved_200001|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200002": { + "content": "<|return|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200003": { + "content": "<|constrain|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200004": { + "content": "<|reserved_200004|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200005": { + "content": "<|channel|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200006": { + "content": "<|start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200007": { + "content": "<|end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200008": { + "content": "<|message|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200009": { + "content": "<|reserved_200009|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200010": { + "content": "<|reserved_200010|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200011": { + "content": "<|reserved_200011|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200012": { + "content": "<|call|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200013": { + "content": "<|reserved_200013|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200014": { + "content": "<|reserved_200014|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200015": { + "content": "<|reserved_200015|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200016": { + "content": "<|reserved_200016|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200017": { + "content": "<|reserved_200017|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "200018": { + "content": "<|endofprompt|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": false, + "eos_token": "<|return|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|endoftext|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}