Vihang D commited on
Commit
241166f
·
1 Parent(s): d5c8a4f

initial import of fine tuned mistrel 7b

Browse files
Files changed (48) hide show
  1. config.json +25 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00042.bin +3 -0
  4. pytorch_model-00002-of-00042.bin +3 -0
  5. pytorch_model-00003-of-00042.bin +3 -0
  6. pytorch_model-00004-of-00042.bin +3 -0
  7. pytorch_model-00005-of-00042.bin +3 -0
  8. pytorch_model-00006-of-00042.bin +3 -0
  9. pytorch_model-00007-of-00042.bin +3 -0
  10. pytorch_model-00008-of-00042.bin +3 -0
  11. pytorch_model-00009-of-00042.bin +3 -0
  12. pytorch_model-00010-of-00042.bin +3 -0
  13. pytorch_model-00011-of-00042.bin +3 -0
  14. pytorch_model-00012-of-00042.bin +3 -0
  15. pytorch_model-00013-of-00042.bin +3 -0
  16. pytorch_model-00014-of-00042.bin +3 -0
  17. pytorch_model-00015-of-00042.bin +3 -0
  18. pytorch_model-00016-of-00042.bin +3 -0
  19. pytorch_model-00017-of-00042.bin +3 -0
  20. pytorch_model-00018-of-00042.bin +3 -0
  21. pytorch_model-00019-of-00042.bin +3 -0
  22. pytorch_model-00020-of-00042.bin +3 -0
  23. pytorch_model-00021-of-00042.bin +3 -0
  24. pytorch_model-00022-of-00042.bin +3 -0
  25. pytorch_model-00023-of-00042.bin +3 -0
  26. pytorch_model-00024-of-00042.bin +3 -0
  27. pytorch_model-00025-of-00042.bin +3 -0
  28. pytorch_model-00026-of-00042.bin +3 -0
  29. pytorch_model-00027-of-00042.bin +3 -0
  30. pytorch_model-00028-of-00042.bin +3 -0
  31. pytorch_model-00029-of-00042.bin +3 -0
  32. pytorch_model-00030-of-00042.bin +3 -0
  33. pytorch_model-00031-of-00042.bin +3 -0
  34. pytorch_model-00032-of-00042.bin +3 -0
  35. pytorch_model-00033-of-00042.bin +3 -0
  36. pytorch_model-00034-of-00042.bin +3 -0
  37. pytorch_model-00035-of-00042.bin +3 -0
  38. pytorch_model-00036-of-00042.bin +3 -0
  39. pytorch_model-00037-of-00042.bin +3 -0
  40. pytorch_model-00038-of-00042.bin +3 -0
  41. pytorch_model-00039-of-00042.bin +3 -0
  42. pytorch_model-00040-of-00042.bin +3 -0
  43. pytorch_model-00041-of-00042.bin +3 -0
  44. pytorch_model-00042-of-00042.bin +3 -0
  45. pytorch_model.bin.index.json +298 -0
  46. tokenizer.json +0 -0
  47. tokenizer.model +3 -0
  48. tokenizer_config.json +40 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "../alpaca-qlora/smartyplats-7b-v2",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 4096,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 32,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 4096,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.35.0.dev0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.35.0.dev0"
6
+ }
pytorch_model-00001-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb01660ef4916e36a696565de9ec529c4701924110b0ab094c5734f5b5ffeb1
3
+ size 346032713
pytorch_model-00002-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0d6e54fa699918fde76080c8a02a67a2c4aa15806b899f43e2723d43c95279
3
+ size 394284267
pytorch_model-00003-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249b69253fe26489a12283ddcabea151cce789452bf1611d7273d6bcb38b9e93
3
+ size 394284267
pytorch_model-00004-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfcc388e55b3b58e44d15a57eba94e965ce458f875de5bd3b5b6dc5a331a800c
3
+ size 318770074
pytorch_model-00005-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02b6e482f45ff4bb1be3a71d4b8a230d9a75023d2e2839612c337d68966e586
3
+ size 318787068
pytorch_model-00006-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b51300a12087cd7f62e4778de0525bb847bfaae48f954cd0fe5f79caa137d7
3
+ size 318787068
pytorch_model-00007-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5fc11db3dd9485b36602a8521d976d841d971a99ea231390d9fad2555fb0fb0
3
+ size 394284267
pytorch_model-00008-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c55baa15ee7dbc5936d4556051c64ba5f1b349ea2c4d0d6b87e2f65125972dab
3
+ size 394284267
pytorch_model-00009-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9afe708e7a6dde5f57089f9a88f435772b637892db56c2eeecaf5a49354b74
3
+ size 318770074
pytorch_model-00010-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f13884078f1cb4b917907e21b6d9bd674f5a9f624e31ec608c60187cb39b5ca
3
+ size 318787068
pytorch_model-00011-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:630d13f57dee95e9b7cf023369ff0fe152ea878b9e301f5d6ac10363b9e48c67
3
+ size 318787068
pytorch_model-00012-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:856ac3613f7ad070c11794fd47a1e772107f43afb3758b14e120bd8637a76712
3
+ size 394284267
pytorch_model-00013-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d41ddb47f347871bae5cfd750576c8dce01eaba6136d95c83937e9a05cf23c4
3
+ size 394284267
pytorch_model-00014-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2108878bac09ca9face0468aae6ebfbc9c043fd3723e4244e647ca69a9bbb93
3
+ size 318770074
pytorch_model-00015-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9561acefed07cd764476ccbf1355491647360a69bb294703cba44ed3a3a4cbf
3
+ size 318787068
pytorch_model-00016-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec102bc2116c3f9f9b114311f9bcf033e56921e359ee4cd0d3c082f89574b4fb
3
+ size 318787068
pytorch_model-00017-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a814544849be2516f28275c96d373ee2e45d546b685908cdf48e353808df96e
3
+ size 394284267
pytorch_model-00018-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adca7e78aaef8818724e88dc4ab562aedf83fa4cc527cc853f7e4376211c07f4
3
+ size 394284267
pytorch_model-00019-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:126357d3c3b549e448ed4a2bea4d9b5c46fcc4fdfc00b738710605373c20a37a
3
+ size 318770074
pytorch_model-00020-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b7dca1d2750a2c1eb1be37894e42621b99f46d0717b3a3335aab1c0f602339
3
+ size 318787068
pytorch_model-00021-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17163a60e8ea05dd4aeec038dcf641b69c2009064f3baddbf17b512eb354508a
3
+ size 318787068
pytorch_model-00022-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbfd36a417bd830e50b5fc7f937ab191672b95bad74dd230db63abf8d43802a
3
+ size 394284267
pytorch_model-00023-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4300a5f62846d21cfce3147ebbc4cf6e3a3f6ad189a1b5eff07cbec6f035e661
3
+ size 394284267
pytorch_model-00024-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1aa078d8eccfd622354258ded773eb4f9684a20588cf05dff37d656c03ec05
3
+ size 318770074
pytorch_model-00025-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa80e6c346d64df7115dc5709537d6e0c69174afda6ad1b4d7b15e099e65a4fb
3
+ size 318787068
pytorch_model-00026-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c16ae149337d2c7dd54f96f54c2beffba6cef5d728fdc3432f935fe636d42c
3
+ size 318787068
pytorch_model-00027-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522894f4f003687daf901f7f8e38147357dc5686d7751811e99f0d25724b43c3
3
+ size 394284267
pytorch_model-00028-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f8ffb7150a9895ebe23b6881f40623adfa8463522aec671230add89f0e74fc7
3
+ size 394284267
pytorch_model-00029-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81cd2ec4bd563235298d38201664be2ea88b2f1b2a9ff8cd0c4a45c077af7b1a
3
+ size 318770074
pytorch_model-00030-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be51be2bcf7c972566b65609591a65d82489c2ede405eca2aa56e74dd19bf1
3
+ size 318787068
pytorch_model-00031-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3063ebffc49c3abce3283a50dfdb2bdcb7ac07a3bd1019416eaba4f4cbaee4
3
+ size 318787068
pytorch_model-00032-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec236fcbf407315dfa4d4939e40f9e2e0909cd3610bdb01fe89dea82612b12af
3
+ size 394284267
pytorch_model-00033-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2786abfbbc995832feb308855300c51c001f17f189f49188750baca152093edb
3
+ size 394284267
pytorch_model-00034-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e123964eaa9692dbfbb7af16ab8d39c8647fe7467e02767dc299357c8c7c088
3
+ size 318770074
pytorch_model-00035-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ba597adb38c9e2697f61ef8abe17e73ef4f85152c275c17ba9ee94851adc530
3
+ size 318787068
pytorch_model-00036-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e76abc8b6dedd4c2efe3a4cfa8b8226d98b892660e5100349beb6c14cdd10a51
3
+ size 318787068
pytorch_model-00037-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09b97b10a7a55b20a9a189cc84056b6576511dd93a942b1ac4a91915b59b2bc1
3
+ size 394284267
pytorch_model-00038-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c541f2ba420a54c40d61a238395ef80f32468cd93d723becb4d18cf352ef206a
3
+ size 394284267
pytorch_model-00039-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b181d65e7b1f3623258a7a77e85dec66a39713f0ab0c24fa25485366a910a2
3
+ size 318770074
pytorch_model-00040-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81fcf33655b841eed3b21373f0974976357409db46eb857370b8809ef3a8cf7
3
+ size 318787068
pytorch_model-00041-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d465ba911b93ac63ef293378820ea5338b6f42337e98820df8ebd48b881866c
3
+ size 234908233
pytorch_model-00042-of-00042.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3745cd4d751227cc3179b3f06c0b84d80bb2a1436c638c854a4bfbc0712666
3
+ size 262145413
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 14483464192
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00042-of-00042.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00042.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00042.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00042.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00042.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00042.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00042.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00042.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00042.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00042.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00042.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00042.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00042.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00042.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00042.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00042.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00042.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00042.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00042.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00042.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00015-of-00042.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00015-of-00042.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00014-of-00042.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00042.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00015-of-00042.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00014-of-00042.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00014-of-00042.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00014-of-00042.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00014-of-00042.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00016-of-00042.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00016-of-00042.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00015-of-00042.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00016-of-00042.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00016-of-00042.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00015-of-00042.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00015-of-00042.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00015-of-00042.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00015-of-00042.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00017-of-00042.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00017-of-00042.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00017-of-00042.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00017-of-00042.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00017-of-00042.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00016-of-00042.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00016-of-00042.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00016-of-00042.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00016-of-00042.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00018-of-00042.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00018-of-00042.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00018-of-00042.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00018-of-00042.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00018-of-00042.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00017-of-00042.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00018-of-00042.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00017-of-00042.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00018-of-00042.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00020-of-00042.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00020-of-00042.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00019-of-00042.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00019-of-00042.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00020-of-00042.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00019-of-00042.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00019-of-00042.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00019-of-00042.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00019-of-00042.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00021-of-00042.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00021-of-00042.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00020-of-00042.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00021-of-00042.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00021-of-00042.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00020-of-00042.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00020-of-00042.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00020-of-00042.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00020-of-00042.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00022-of-00042.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00022-of-00042.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00022-of-00042.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00022-of-00042.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00022-of-00042.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00021-of-00042.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00021-of-00042.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00021-of-00042.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00021-of-00042.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00023-of-00042.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00023-of-00042.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00023-of-00042.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00023-of-00042.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00023-of-00042.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00022-of-00042.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00023-of-00042.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00022-of-00042.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00023-of-00042.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00025-of-00042.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00025-of-00042.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00024-of-00042.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00024-of-00042.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00025-of-00042.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00024-of-00042.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00024-of-00042.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00024-of-00042.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00024-of-00042.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00026-of-00042.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00026-of-00042.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00025-of-00042.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00026-of-00042.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00026-of-00042.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00025-of-00042.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00025-of-00042.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00025-of-00042.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00025-of-00042.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00005-of-00042.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00005-of-00042.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00042.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00042.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00005-of-00042.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00004-of-00042.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00042.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00004-of-00042.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00042.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00027-of-00042.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00027-of-00042.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00027-of-00042.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00027-of-00042.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00027-of-00042.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00026-of-00042.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00026-of-00042.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00026-of-00042.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00026-of-00042.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00028-of-00042.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00028-of-00042.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00028-of-00042.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00028-of-00042.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00028-of-00042.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00027-of-00042.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00028-of-00042.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00027-of-00042.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00028-of-00042.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00030-of-00042.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00030-of-00042.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00029-of-00042.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00029-of-00042.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00030-of-00042.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00029-of-00042.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00029-of-00042.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00029-of-00042.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00029-of-00042.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00031-of-00042.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00031-of-00042.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00030-of-00042.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00031-of-00042.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00031-of-00042.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00030-of-00042.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00030-of-00042.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00030-of-00042.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00030-of-00042.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00032-of-00042.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00032-of-00042.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00032-of-00042.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00032-of-00042.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00032-of-00042.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00031-of-00042.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00031-of-00042.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00031-of-00042.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00031-of-00042.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00033-of-00042.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00033-of-00042.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00033-of-00042.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00033-of-00042.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00033-of-00042.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00032-of-00042.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00033-of-00042.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00032-of-00042.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00033-of-00042.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00035-of-00042.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00035-of-00042.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00034-of-00042.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00034-of-00042.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00035-of-00042.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00034-of-00042.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00034-of-00042.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00034-of-00042.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00034-of-00042.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00036-of-00042.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00036-of-00042.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00035-of-00042.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00036-of-00042.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00036-of-00042.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00035-of-00042.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00035-of-00042.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00035-of-00042.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00035-of-00042.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00037-of-00042.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00037-of-00042.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00037-of-00042.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00037-of-00042.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00037-of-00042.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00036-of-00042.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00036-of-00042.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00036-of-00042.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00036-of-00042.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00038-of-00042.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00038-of-00042.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00038-of-00042.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00038-of-00042.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00038-of-00042.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00037-of-00042.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00038-of-00042.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00037-of-00042.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00038-of-00042.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00006-of-00042.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00006-of-00042.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00042.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00006-of-00042.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00006-of-00042.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00042.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00042.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00005-of-00042.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00042.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00040-of-00042.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00040-of-00042.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00039-of-00042.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00039-of-00042.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00040-of-00042.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00039-of-00042.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00039-of-00042.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00039-of-00042.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00039-of-00042.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00041-of-00042.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00041-of-00042.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00040-of-00042.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00041-of-00042.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00041-of-00042.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00040-of-00042.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00040-of-00042.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00040-of-00042.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00040-of-00042.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00042.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00007-of-00042.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00007-of-00042.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00042.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00042.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00042.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00042.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00042.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00042.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00042.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00042.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00008-of-00042.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00042.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00042.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00042.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00008-of-00042.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00042.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00008-of-00042.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00010-of-00042.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00010-of-00042.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00042.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00042.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00010-of-00042.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00009-of-00042.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00009-of-00042.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00009-of-00042.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00009-of-00042.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00011-of-00042.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00011-of-00042.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00042.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00011-of-00042.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00011-of-00042.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00010-of-00042.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00042.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00010-of-00042.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00010-of-00042.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00012-of-00042.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00012-of-00042.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00012-of-00042.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00012-of-00042.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00012-of-00042.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00011-of-00042.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00042.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00011-of-00042.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00042.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00013-of-00042.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00013-of-00042.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00013-of-00042.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00013-of-00042.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00013-of-00042.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00042.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00013-of-00042.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00012-of-00042.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00013-of-00042.bin",
296
+ "model.norm.weight": "pytorch_model-00041-of-00042.bin"
297
+ }
298
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": true,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": null,
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }