Text Generation
Transformers
PyTorch
Thai
English
llama
openthaigpt
Inference Endpoints
text-generation-inference
kobkrit commited on
Commit
26c184e
1 Parent(s): f29dd21

Initial version

Browse files
Files changed (45) hide show
  1. config.json +24 -0
  2. generation_config.json +7 -0
  3. pytorch_model-00001-of-00039.bin +3 -0
  4. pytorch_model-00002-of-00039.bin +3 -0
  5. pytorch_model-00003-of-00039.bin +3 -0
  6. pytorch_model-00004-of-00039.bin +3 -0
  7. pytorch_model-00005-of-00039.bin +3 -0
  8. pytorch_model-00006-of-00039.bin +3 -0
  9. pytorch_model-00007-of-00039.bin +3 -0
  10. pytorch_model-00008-of-00039.bin +3 -0
  11. pytorch_model-00009-of-00039.bin +3 -0
  12. pytorch_model-00010-of-00039.bin +3 -0
  13. pytorch_model-00011-of-00039.bin +3 -0
  14. pytorch_model-00012-of-00039.bin +3 -0
  15. pytorch_model-00013-of-00039.bin +3 -0
  16. pytorch_model-00014-of-00039.bin +3 -0
  17. pytorch_model-00015-of-00039.bin +3 -0
  18. pytorch_model-00016-of-00039.bin +3 -0
  19. pytorch_model-00017-of-00039.bin +3 -0
  20. pytorch_model-00018-of-00039.bin +3 -0
  21. pytorch_model-00019-of-00039.bin +3 -0
  22. pytorch_model-00020-of-00039.bin +3 -0
  23. pytorch_model-00021-of-00039.bin +3 -0
  24. pytorch_model-00022-of-00039.bin +3 -0
  25. pytorch_model-00023-of-00039.bin +3 -0
  26. pytorch_model-00024-of-00039.bin +3 -0
  27. pytorch_model-00025-of-00039.bin +3 -0
  28. pytorch_model-00026-of-00039.bin +3 -0
  29. pytorch_model-00027-of-00039.bin +3 -0
  30. pytorch_model-00028-of-00039.bin +3 -0
  31. pytorch_model-00029-of-00039.bin +3 -0
  32. pytorch_model-00030-of-00039.bin +3 -0
  33. pytorch_model-00031-of-00039.bin +3 -0
  34. pytorch_model-00032-of-00039.bin +3 -0
  35. pytorch_model-00033-of-00039.bin +3 -0
  36. pytorch_model-00034-of-00039.bin +3 -0
  37. pytorch_model-00035-of-00039.bin +3 -0
  38. pytorch_model-00036-of-00039.bin +3 -0
  39. pytorch_model-00037-of-00039.bin +3 -0
  40. pytorch_model-00038-of-00039.bin +3 -0
  41. pytorch_model-00039-of-00039.bin +3 -0
  42. pytorch_model.bin.index.json +330 -0
  43. special_tokens_map.json +1 -0
  44. tokenizer.model +3 -0
  45. tokenizer_config.json +1 -0
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "decapoda-research/llama-7b-hf",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 1,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 11008,
12
+ "max_position_embeddings": 2048,
13
+ "max_sequence_length": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "pad_token_id": -1,
18
+ "rms_norm_eps": 1e-06,
19
+ "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
+ "transformers_version": "4.29.0",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.29.0"
7
+ }
pytorch_model-00001-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9850a8787e03b2ab7dea7af6e50348b9b4bef388e4149c512304773e7bdd3a16
3
+ size 396364479
pytorch_model-00002-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:561a2a3237b6b9939348ff86ab82a278ed20af978be1086ed4f61d67dc574ecc
3
+ size 371215393
pytorch_model-00003-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30519c3ac058690398e8fcd4888ccf83fa26b46470e218cc508930b042f88d3
3
+ size 371215986
pytorch_model-00004-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df12eec44b9f3f4f38f8358dc55760577eb35b55d37069a19aa5e3f47d7cd584
3
+ size 371215986
pytorch_model-00005-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e883c2610f00b637c0d64be1f8711789b64e440164f08d4ca5578ec511eef153
3
+ size 371215986
pytorch_model-00006-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9481a588920b42e03b5d1aa100876150b164d1950d15d4cfb83152ca80c9f56c
3
+ size 314575888
pytorch_model-00007-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfd204ad61e308b0faf1a2c751a94b8f9b193ceea762fbede4d2ef2150dc6ea0
3
+ size 314592882
pytorch_model-00008-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13e2433c051c296d236cf50248fbefcd599de07bf07d65b2beb8a6b819c3580
3
+ size 314592882
pytorch_model-00009-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:374f2d876ce3fe4f56dc2f36ade05ef70061179c9eb4e6adfa4e6d511505c5a5
3
+ size 371215393
pytorch_model-00010-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7dd827ca82bd87799140ffc78018d67ccffee0ff1548d8975acf0c4ab1e12a
3
+ size 371215986
pytorch_model-00011-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5121192968886a6e88e86ee6a7d33888b67e7056d47ea3a55dea313ed2481530
3
+ size 371215986
pytorch_model-00012-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071e64de373d635911535890d032fda082b1a4be6d5e9250ce59d743c50d8780
3
+ size 371215986
pytorch_model-00013-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5827a380833ab9e7f168f345d6848d368aef33e407a32c922186437155f1f82
3
+ size 314575888
pytorch_model-00014-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f770bf35c784d981ff60ada53ce79c5123def708e6df3d6490395d18a6d2fe78
3
+ size 314592882
pytorch_model-00015-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1a670ce9458b2190613411ab5e542ea7c653aba68dbab12df9102c639a2ac2
3
+ size 314592882
pytorch_model-00016-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea96f0e48ac009a05540763b456d7d02c734d55b47c611aff1c44b957eee8568
3
+ size 371215393
pytorch_model-00017-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad81e3ff739523ecdeb0ad10660711c2d922a17a20ec8f4dc2552af058673c1b
3
+ size 371215986
pytorch_model-00018-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0601398234285351b322a64038b045ec938a3e0bf1a849f6070e4cca3fcb961
3
+ size 371215986
pytorch_model-00019-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78743eb5c3bccba659589e29390aa902e2099a3c3bbc1233483e2860c646e1f
3
+ size 371215986
pytorch_model-00020-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80e4331fb55b6e1cb249d7c0a2e5f9c03a4efe0f39fc878b3cd7ba918d3794de
3
+ size 314575888
pytorch_model-00021-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf0710e68fc8a76e8626920b768a224c12518cd31ea27eaef849fcc3759181d
3
+ size 314592882
pytorch_model-00022-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f87a7b888afb09cf547753f8a33330cf3e97bb8df4f94fec469d0008da56f1
3
+ size 314592882
pytorch_model-00023-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a7db184acbbd4d1d3e90518718a2ed449007e35cee7b882b51e593f7ce08cdb
3
+ size 371215393
pytorch_model-00024-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5178edd7e9bddf9dbaebe2f7973f6a5a089457bccea56275a004bb961f928c80
3
+ size 371215986
pytorch_model-00025-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6318f340b18fd190ffeefef13c661de25bf118041c44a4548e801d412e3969b9
3
+ size 371215986
pytorch_model-00026-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7093cfa1da103309ee91b8c0122fd3f069b0095d055c6e29d9a0b1923467947e
3
+ size 371215986
pytorch_model-00027-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e9f7ee3b5dcbb814f50737f6f2b5a55b5879431979f725ca82211893568299
3
+ size 314575888
pytorch_model-00028-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9da98d15238c1a35cc1252e6fd38b66b39cd2a7563e055943aa696b8c8dedc73
3
+ size 314592882
pytorch_model-00029-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c012c131f435357857a2b7499792060a11c5f04e20f5be45c1c2e59d478e5c
3
+ size 314592882
pytorch_model-00030-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4bdb9251d924e13f1b1d36996b211f51747dddcf09bd4ce1d684205c27303e5
3
+ size 371215393
pytorch_model-00031-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8577adb697a13d4a62dfe2fc26ed2d3690fa4a7b83e247009719cef340b9a002
3
+ size 371215986
pytorch_model-00032-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c759d93e9af0f89b492b17e16fd91aa019ad590e6796648fdfe9e8132484e9e
3
+ size 371215986
pytorch_model-00033-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce964a32c4620ea8fb1988325724b39a2eceda538566a9ded22367f41205e298
3
+ size 371215986
pytorch_model-00034-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288cda9620cffd1d2cbfb2a3308d42777329ee980e3d9c87b71f555431f0301d
3
+ size 314575888
pytorch_model-00035-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234b83e1f84af32b46112a7224a69764e8f7ca0d43546708d0adea94d575328a
3
+ size 314592882
pytorch_model-00036-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6bde1f7e79fe4a2bd473507eb2cd878db7d28c1d0734dcc07f74f8e28b4275
3
+ size 314592882
pytorch_model-00037-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cf2f80d2f6f5b05f3fbc6f5f72abf4f545f468ca3356b4e2091a63775aa096
3
+ size 371215393
pytorch_model-00038-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96dd48dd85332e0789443798e4758c140a31663977eb23844d5f4b81536b822f
3
+ size 304114977
pytorch_model-00039-of-00039.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3350fb71c2bc1e88d77d9685716fd2759e879137814a4120d98265a43f405919
3
+ size 262144938
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13476839424
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00039-of-00039.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
328
+ "model.norm.weight": "pytorch_model-00038-of-00039.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LLaMATokenizer", "unk_token": ""}