Hugging Face's logo

ValiantLabs
/
Llama2-70B-ShiningValiant

Text Generation
Transformers
Safetensors
English
llama
shining-valiant
valiant
valiant-labs
llama-2
llama-2-chat
70b
text-generation-inference
Inference Endpoints
Model card Files
zoeywin sequelbox commited on
Commit
8b68c26
•
1 Parent(s): 0d12f60

Upload folder using huggingface_hub (#4)

Browse files

- 17aa7ff87e68f7acadc4b7572d777233c27f708be40e5f8796246035b57f9161 (92392fbccb9f5efef50703e469c8d7746a1f41ae)
- 777badc2c709127fb5a862033d789fda71a1e2354096ffd39aee61b3840908be (16817c85a20d111dac7e5a5417a8262d1f93cbf1)
- c72540b9eecd75060c0b4a63d241824a67d9f8551ec8737fd409e71c18036419 (2a3c8045d4bbddaab7b86053f28a543610877776)
- 434888aafd99db6d8e0940f8fc437b8b9c1b5dacdb6b0bb914e3ab318918552d (4fb504780bca28930b8aa0c1de8e0ff7347f34ba)
- dc748e29be45ac9b37eb20573a70a28ac57e1ec5992f1752cf6c11ed31838acd (10ff19e3f9ae63c9e961fc0823818f7a941509e1)
- 81765136d1dcca010eb757c67c82f12c512113baa059483523d1ddc4aaa65aa0 (b84cb049ca9d80e7f10e80db3977d6acc017eac5)
- 1c06fe3272ae28639c783a614b37e4e1d2c90afccfa64a0753ca57465fe76413 (963a8353d404bc129cfb3936d7f7db1d41d985d0)
- 28048e6366cbac1c62bc5322064d7139989276555dd52334ba1d762056828d08 (f5cdbd95f3b3705fd5716820dd6a19ad7d8b0311)
- cbe4f46e84734d29aa19cb1f369b4b13e4af573684f8304da55d961ce7db73b6 (b14c3818f299f96bf1ee68a1aeb20430964390b3)
- 038fa2d4b9dca28a48e9aad3542693d50df5aa9f151d9195e51640263e0fed98 (47e6b2ff2d7a6a2e4fd818c9320411e7254199f6)
- 34556752584aea75bc4f936b3f739b2f5e599c2555db6198f7499b15336977f7 (ee5ac2fd909068bfeda27e2e8b0501c4aaf9c88f)
- 9dd63a24a0007b5cafb5d955164417b7ce37634741a7dfb313094aff4dcd31bc (7d0149081da61caebdef5a8efc966647e6073f68)
- b3ba1dca54dc5bebe46db874318b4ecd77c412c7cc61b4fa4899ff392e008de8 (a671cb587179395aecd346993e5b5a7116676ef4)
- 4203475105cb8e9c365b3eea6ee394842810def5f006f13a82db248dae7d8eab (4b5a24d6e31530d0514a2b113eb2890c1165fb52)
- a692e041cbfb0a1b0d64771677ff6aa4fce724f1008fc564e9d24048c3511df6 (a04a60a152d0150335af2321275ef1553cb04d58)
- 62d30b12bdcb23b2da5683b85ab98c113fe325e4ba630f1c8db9c6e3dfb735de (ed9a0f1f0e8328228dbc6adb73d047feb72d504a)
- 6fb6edcfe32ab58c69e23d0461de570d342a89df1eb47867468cb414fdf67dc9 (cc28d86de29540479b7afe09ebfffb3456b52a41)
- c400db79014d82ef01ccd62c671919dcae94c8cbe3f825fec25a426873a354dc (2a1d40f1d53e8063193aeda31c398c2b0f4d350d)
- ce50161f9fef7f66f6fa0b265f4abd3d343a062a1d93306fae8a73a731113d88 (98b002955838a4fb90168c610e218bb5e8a82538)
- 2c105bb48dd4d8fe11c69b2a9302a3abffe36f95feb99c21c4f53c7bc931da52 (83aec7498ba6599f2e344cd7bdfc712e648ceea0)
- 4e5862652a9a1e6adbec34453147b8a8ee84cbc417f21a35ca3b6d644a1aa279 (c8fb61cd2259b5b06a7b5984a20664a7f76cc9b8)
- 020da57794d21d144cdeee732c4f954d42e1043117dfeff63f6d5ec5ffb49155 (d99713c23a467f819eaef658f6b82bd2074c3f69)
- 7d73137f5c51585d03a7d456ff315a05923c3280a3bc39e9fb90ad5351a7b0ec (2660e540b7d8b24f893d5a7320979be274a597b9)
- b0dab79b505b50f8bad4a3d12568b8e5494ab344a5efadcef404a282905fb00e (173d1afa4117f6a2202d8209f1a68cf8b471d511)
- f3e5c7857ed52e998c0dae9762783a41cbcdfd5a37d6cd9d9453e1629419e292 (f35a351731359588616e6deaf212d2e540038f37)
- 8d689f40d716793574fd75588e6cb31b92c5d6e71ef4d0439cc9280edc593042 (6d0dbcf0654d412f6e55e657b8dacb7231e96fe6)
- 9cb4fea84f418926d2198d58c5e054484c48672b3339d112f2415014145d9002 (058d94878d3ee1984c85d1a325a6820122083af6)
- d9403962b94b08c38dddf41a64188904cda9adf3d195e271897e2b0dbd75208a (7c4b79668b1eba8a852674208aa86e077dcd10e1)
- f309b6b0be921d84979972ba46694937c97d76478a1625c7da01ed2bb0c9bd61 (2bfe5db8e1065be7be6acab04222fdc0fb36d9f6)
- 1374e546e4607a18291f9de895730112c0c26de2e13051590914fa2a50480ff4 (c2f8d8b76b071dd67646415a1b38a5a8589b75ec)
- 0e99b8354c7d27ee420c8acd7f65221953112aa5ab34286cda8a6d5e9c31524f (28bbac59b99a902491b1fc5f97caaffd0d1c8d1d)


Co-authored-by: scott <sequelbox@users.noreply.huggingface.co>

Files changed (41) hide show
  1. .ipynb_checkpoints/config-checkpoint.json +28 -0
  2. .ipynb_checkpoints/generation_config-checkpoint.json +8 -0
  3. .ipynb_checkpoints/model.safetensors.index-checkpoint.json +1050 -0
  4. .ipynb_checkpoints/special_tokens_map-checkpoint.json +11 -0
  5. .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
  6. .ipynb_checkpoints/tokenizer_config-checkpoint.json +48 -0
  7. config.json +3 -2
  8. generation_config.json +2 -1
  9. model-00001-of-00030.safetensors +1 -1
  10. model-00002-of-00030.safetensors +1 -1
  11. model-00003-of-00030.safetensors +1 -1
  12. model-00004-of-00030.safetensors +1 -1
  13. model-00005-of-00030.safetensors +1 -1
  14. model-00006-of-00030.safetensors +1 -1
  15. model-00007-of-00030.safetensors +1 -1
  16. model-00008-of-00030.safetensors +1 -1
  17. model-00009-of-00030.safetensors +1 -1
  18. model-00010-of-00030.safetensors +1 -1
  19. model-00011-of-00030.safetensors +1 -1
  20. model-00012-of-00030.safetensors +1 -1
  21. model-00013-of-00030.safetensors +1 -1
  22. model-00014-of-00030.safetensors +1 -1
  23. model-00015-of-00030.safetensors +1 -1
  24. model-00016-of-00030.safetensors +1 -1
  25. model-00017-of-00030.safetensors +1 -1
  26. model-00018-of-00030.safetensors +1 -1
  27. model-00019-of-00030.safetensors +1 -1
  28. model-00020-of-00030.safetensors +1 -1
  29. model-00021-of-00030.safetensors +1 -1
  30. model-00022-of-00030.safetensors +1 -1
  31. model-00023-of-00030.safetensors +1 -1
  32. model-00024-of-00030.safetensors +1 -1
  33. model-00025-of-00030.safetensors +1 -1
  34. model-00026-of-00030.safetensors +1 -1
  35. model-00027-of-00030.safetensors +1 -1
  36. model-00028-of-00030.safetensors +1 -1
  37. model-00029-of-00030.safetensors +1 -1
  38. model-00030-of-00030.safetensors +1 -1
  39. special_tokens_map.json +8 -21
  40. tokenizer.json +1 -1
  41. tokenizer_config.json +34 -24
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./sv_one",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 10000.0,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "4.34.0",
26
+ "use_cache": false,
27
+ "vocab_size": 32000
28
+ }
.ipynb_checkpoints/generation_config-checkpoint.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.34.0",
7
+ "use_cache": false
8
+ }
.ipynb_checkpoints/model.safetensors.index-checkpoint.json ADDED
@@ -0,0 +1,1050 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 276955168768
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00030-of-00030.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
15
+ "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
16
+ "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
18
+ "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
19
+ "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00030.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
28
+ "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
29
+ "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
31
+ "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
32
+ "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
33
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
34
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
35
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
36
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
37
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
38
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
41
+ "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
42
+ "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
43
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
44
+ "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
45
+ "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
46
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
47
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
48
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
49
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
50
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
51
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
53
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
54
+ "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
55
+ "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
56
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
57
+ "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
58
+ "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
59
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
60
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00030.safetensors",
61
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
62
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
63
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
64
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
65
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
66
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
67
+ "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
68
+ "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
69
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
70
+ "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
71
+ "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
72
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
73
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
74
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
75
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
76
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
77
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
78
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
79
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
80
+ "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
81
+ "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
82
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
83
+ "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00030.safetensors",
84
+ "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00030.safetensors",
85
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
86
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
87
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
88
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
89
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
90
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
91
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
92
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
93
+ "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
94
+ "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
95
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
96
+ "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
97
+ "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
98
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
99
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00030.safetensors",
100
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
101
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
102
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
103
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
104
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
105
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
106
+ "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
107
+ "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
108
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
109
+ "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
110
+ "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
111
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
112
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
113
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
114
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
115
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
116
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
117
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
118
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
119
+ "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
120
+ "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
121
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
122
+ "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00030.safetensors",
123
+ "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00030.safetensors",
124
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
125
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
126
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
127
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
128
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
129
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
130
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
131
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
132
+ "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
133
+ "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
134
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
135
+ "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
136
+ "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
137
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
138
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00030.safetensors",
139
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
140
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
141
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
142
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
143
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
144
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
145
+ "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
146
+ "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
147
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
148
+ "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
149
+ "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
150
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
151
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
152
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
153
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
154
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
155
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
156
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
157
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
158
+ "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00030.safetensors",
159
+ "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00030.safetensors",
160
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
161
+ "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
162
+ "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
163
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
164
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
165
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
166
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
167
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
168
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
169
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
170
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
171
+ "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
172
+ "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
173
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
174
+ "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00030.safetensors",
175
+ "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00030.safetensors",
176
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
177
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
178
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
179
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
180
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
181
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
182
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
183
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
184
+ "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
185
+ "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
186
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
187
+ "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
188
+ "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
189
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
190
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
191
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
192
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
193
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
194
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
195
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
196
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
197
+ "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
198
+ "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
199
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
200
+ "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00008-of-00030.safetensors",
201
+ "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00008-of-00030.safetensors",
202
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
203
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
204
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
205
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
206
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
207
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
208
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
209
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
210
+ "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
211
+ "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
212
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
213
+ "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
214
+ "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
215
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
216
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
217
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
218
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
219
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
220
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
221
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
222
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
223
+ "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
224
+ "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
225
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
226
+ "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
227
+ "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
228
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
229
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
230
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
231
+ "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
232
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
233
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
234
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
235
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
236
+ "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
237
+ "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
238
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
239
+ "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00009-of-00030.safetensors",
240
+ "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00009-of-00030.safetensors",
241
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
242
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
243
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
244
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
245
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
246
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
247
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
248
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
249
+ "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
250
+ "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
251
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
252
+ "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
253
+ "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
254
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
255
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00030.safetensors",
256
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
257
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
258
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
259
+ "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
260
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
261
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
262
+ "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
263
+ "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
264
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
265
+ "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
266
+ "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
267
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
268
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
269
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
270
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
271
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
272
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
273
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
274
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
275
+ "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
276
+ "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
277
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
278
+ "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00010-of-00030.safetensors",
279
+ "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00010-of-00030.safetensors",
280
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
281
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
282
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
283
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
284
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
285
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
286
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
287
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
288
+ "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
289
+ "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
290
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
291
+ "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
292
+ "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
293
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
294
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00030.safetensors",
295
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
296
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
297
+ "model.layers.29.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
298
+ "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
299
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
300
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
301
+ "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
302
+ "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
303
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
304
+ "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
305
+ "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
306
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
307
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
308
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
309
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
310
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
311
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
312
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
313
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
314
+ "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
315
+ "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
316
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
317
+ "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
318
+ "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
319
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
320
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
321
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
322
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
323
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
324
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
325
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
326
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
327
+ "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00011-of-00030.safetensors",
328
+ "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00011-of-00030.safetensors",
329
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
330
+ "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
331
+ "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
332
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
333
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
334
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
335
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
336
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
337
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
338
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
339
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
340
+ "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
341
+ "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
342
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
343
+ "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
344
+ "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
345
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
346
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
347
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
348
+ "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
349
+ "model.layers.32.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
350
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
351
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
352
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
353
+ "model.layers.32.self_attn.q_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
354
+ "model.layers.32.self_attn.q_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
355
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
356
+ "model.layers.32.self_attn.v_proj.lora_A.default.weight": "model-00012-of-00030.safetensors",
357
+ "model.layers.32.self_attn.v_proj.lora_B.default.weight": "model-00012-of-00030.safetensors",
358
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
359
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
360
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
361
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
362
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
363
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
364
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
365
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
366
+ "model.layers.33.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
367
+ "model.layers.33.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
368
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
369
+ "model.layers.33.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
370
+ "model.layers.33.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
371
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
372
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
373
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
374
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
375
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
376
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
377
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
378
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
379
+ "model.layers.34.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
380
+ "model.layers.34.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
381
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
382
+ "model.layers.34.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
383
+ "model.layers.34.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
384
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
385
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
386
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
387
+ "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
388
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
389
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
390
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
391
+ "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
392
+ "model.layers.35.self_attn.q_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
393
+ "model.layers.35.self_attn.q_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
394
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
395
+ "model.layers.35.self_attn.v_proj.lora_A.default.weight": "model-00013-of-00030.safetensors",
396
+ "model.layers.35.self_attn.v_proj.lora_B.default.weight": "model-00013-of-00030.safetensors",
397
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
398
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
399
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
400
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
401
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
402
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
403
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
404
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
405
+ "model.layers.36.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
406
+ "model.layers.36.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
407
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
408
+ "model.layers.36.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
409
+ "model.layers.36.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
410
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
411
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
412
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
413
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
414
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
415
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
416
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
417
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
418
+ "model.layers.37.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
419
+ "model.layers.37.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
420
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
421
+ "model.layers.37.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
422
+ "model.layers.37.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
423
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
424
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
425
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
426
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
427
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
428
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
429
+ "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
430
+ "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
431
+ "model.layers.38.self_attn.q_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
432
+ "model.layers.38.self_attn.q_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
433
+ "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
434
+ "model.layers.38.self_attn.v_proj.lora_A.default.weight": "model-00014-of-00030.safetensors",
435
+ "model.layers.38.self_attn.v_proj.lora_B.default.weight": "model-00014-of-00030.safetensors",
436
+ "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
437
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
438
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
439
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
440
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
441
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
442
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
443
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
444
+ "model.layers.39.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
445
+ "model.layers.39.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
446
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
447
+ "model.layers.39.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
448
+ "model.layers.39.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
449
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
450
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00030.safetensors",
451
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
452
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
453
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
454
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
455
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
456
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
457
+ "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
458
+ "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
459
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
460
+ "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
461
+ "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
462
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
463
+ "model.layers.40.input_layernorm.weight": "model-00015-of-00030.safetensors",
464
+ "model.layers.40.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
465
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
466
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
467
+ "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
468
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
469
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
470
+ "model.layers.40.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
471
+ "model.layers.40.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
472
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
473
+ "model.layers.40.self_attn.v_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
474
+ "model.layers.40.self_attn.v_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
475
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
476
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
477
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
478
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
479
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
480
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
481
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
482
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
483
+ "model.layers.41.self_attn.q_proj.lora_A.default.weight": "model-00015-of-00030.safetensors",
484
+ "model.layers.41.self_attn.q_proj.lora_B.default.weight": "model-00015-of-00030.safetensors",
485
+ "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
486
+ "model.layers.41.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
487
+ "model.layers.41.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
488
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
489
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
490
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
491
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
492
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
493
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
494
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
495
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
496
+ "model.layers.42.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
497
+ "model.layers.42.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
498
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
499
+ "model.layers.42.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
500
+ "model.layers.42.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
501
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
502
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
503
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
504
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
505
+ "model.layers.43.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
506
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
507
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
508
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
509
+ "model.layers.43.self_attn.q_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
510
+ "model.layers.43.self_attn.q_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
511
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
512
+ "model.layers.43.self_attn.v_proj.lora_A.default.weight": "model-00016-of-00030.safetensors",
513
+ "model.layers.43.self_attn.v_proj.lora_B.default.weight": "model-00016-of-00030.safetensors",
514
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
515
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
516
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
517
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
518
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
519
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
520
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
521
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
522
+ "model.layers.44.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
523
+ "model.layers.44.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
524
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
525
+ "model.layers.44.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
526
+ "model.layers.44.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
527
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
528
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
529
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
530
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
531
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
532
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
533
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
534
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
535
+ "model.layers.45.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
536
+ "model.layers.45.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
537
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
538
+ "model.layers.45.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
539
+ "model.layers.45.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
540
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
541
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
542
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
543
+ "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
544
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
545
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
546
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
547
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
548
+ "model.layers.46.self_attn.q_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
549
+ "model.layers.46.self_attn.q_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
550
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
551
+ "model.layers.46.self_attn.v_proj.lora_A.default.weight": "model-00017-of-00030.safetensors",
552
+ "model.layers.46.self_attn.v_proj.lora_B.default.weight": "model-00017-of-00030.safetensors",
553
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
554
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
555
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
556
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
557
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
558
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
559
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
560
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
561
+ "model.layers.47.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
562
+ "model.layers.47.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
563
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
564
+ "model.layers.47.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
565
+ "model.layers.47.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
566
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
567
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
568
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
569
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
570
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
571
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
572
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
573
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
574
+ "model.layers.48.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
575
+ "model.layers.48.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
576
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
577
+ "model.layers.48.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
578
+ "model.layers.48.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
579
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
580
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
581
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
582
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
583
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
584
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
585
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
586
+ "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
587
+ "model.layers.49.self_attn.q_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
588
+ "model.layers.49.self_attn.q_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
589
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
590
+ "model.layers.49.self_attn.v_proj.lora_A.default.weight": "model-00018-of-00030.safetensors",
591
+ "model.layers.49.self_attn.v_proj.lora_B.default.weight": "model-00018-of-00030.safetensors",
592
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
593
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
594
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
595
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
596
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
597
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
598
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
599
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
600
+ "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
601
+ "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
602
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
603
+ "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00030.safetensors",
604
+ "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00030.safetensors",
605
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
606
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
607
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
608
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
609
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
610
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
611
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
612
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
613
+ "model.layers.50.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
614
+ "model.layers.50.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
615
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
616
+ "model.layers.50.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
617
+ "model.layers.50.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
618
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
619
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
620
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
621
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
622
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
623
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
624
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
625
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
626
+ "model.layers.51.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
627
+ "model.layers.51.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
628
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
629
+ "model.layers.51.self_attn.v_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
630
+ "model.layers.51.self_attn.v_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
631
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
632
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
633
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
634
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
635
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
636
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
637
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
638
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
639
+ "model.layers.52.self_attn.q_proj.lora_A.default.weight": "model-00019-of-00030.safetensors",
640
+ "model.layers.52.self_attn.q_proj.lora_B.default.weight": "model-00019-of-00030.safetensors",
641
+ "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
642
+ "model.layers.52.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
643
+ "model.layers.52.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
644
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
645
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
646
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
647
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
648
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
649
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
650
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
651
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
652
+ "model.layers.53.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
653
+ "model.layers.53.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
654
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
655
+ "model.layers.53.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
656
+ "model.layers.53.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
657
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
658
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
659
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
660
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
661
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
662
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
663
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
664
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
665
+ "model.layers.54.self_attn.q_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
666
+ "model.layers.54.self_attn.q_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
667
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
668
+ "model.layers.54.self_attn.v_proj.lora_A.default.weight": "model-00020-of-00030.safetensors",
669
+ "model.layers.54.self_attn.v_proj.lora_B.default.weight": "model-00020-of-00030.safetensors",
670
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
671
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
672
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
673
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
674
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
675
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
676
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
677
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
678
+ "model.layers.55.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
679
+ "model.layers.55.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
680
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
681
+ "model.layers.55.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
682
+ "model.layers.55.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
683
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
684
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
685
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
686
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
687
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
688
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
689
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
690
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
691
+ "model.layers.56.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
692
+ "model.layers.56.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
693
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
694
+ "model.layers.56.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
695
+ "model.layers.56.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
696
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
697
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
698
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
699
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
700
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
701
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
702
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
703
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
704
+ "model.layers.57.self_attn.q_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
705
+ "model.layers.57.self_attn.q_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
706
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
707
+ "model.layers.57.self_attn.v_proj.lora_A.default.weight": "model-00021-of-00030.safetensors",
708
+ "model.layers.57.self_attn.v_proj.lora_B.default.weight": "model-00021-of-00030.safetensors",
709
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
710
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
711
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
712
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
713
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
714
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
715
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
716
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
717
+ "model.layers.58.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
718
+ "model.layers.58.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
719
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
720
+ "model.layers.58.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
721
+ "model.layers.58.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
722
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
723
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
724
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
725
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
726
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
727
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
728
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
729
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
730
+ "model.layers.59.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
731
+ "model.layers.59.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
732
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
733
+ "model.layers.59.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
734
+ "model.layers.59.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
735
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
736
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
737
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
738
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
739
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
740
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
741
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
742
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
743
+ "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
744
+ "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
745
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
746
+ "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
747
+ "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
748
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
749
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
750
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
751
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
752
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
753
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
754
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
755
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
756
+ "model.layers.60.self_attn.q_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
757
+ "model.layers.60.self_attn.q_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
758
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
759
+ "model.layers.60.self_attn.v_proj.lora_A.default.weight": "model-00022-of-00030.safetensors",
760
+ "model.layers.60.self_attn.v_proj.lora_B.default.weight": "model-00022-of-00030.safetensors",
761
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
762
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
763
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
764
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
765
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
766
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
767
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
768
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
769
+ "model.layers.61.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
770
+ "model.layers.61.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
771
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
772
+ "model.layers.61.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
773
+ "model.layers.61.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
774
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
775
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
776
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
777
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
778
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
779
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
780
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
781
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
782
+ "model.layers.62.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
783
+ "model.layers.62.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
784
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
785
+ "model.layers.62.self_attn.v_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
786
+ "model.layers.62.self_attn.v_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
787
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
788
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
789
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
790
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
791
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
792
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
793
+ "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
794
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
795
+ "model.layers.63.self_attn.q_proj.lora_A.default.weight": "model-00023-of-00030.safetensors",
796
+ "model.layers.63.self_attn.q_proj.lora_B.default.weight": "model-00023-of-00030.safetensors",
797
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
798
+ "model.layers.63.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
799
+ "model.layers.63.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
800
+ "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
801
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
802
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
803
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
804
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
805
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
806
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
807
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
808
+ "model.layers.64.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
809
+ "model.layers.64.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
810
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
811
+ "model.layers.64.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
812
+ "model.layers.64.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
813
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
814
+ "model.layers.65.input_layernorm.weight": "model-00025-of-00030.safetensors",
815
+ "model.layers.65.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
816
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
817
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
818
+ "model.layers.65.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
819
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
820
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
821
+ "model.layers.65.self_attn.q_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
822
+ "model.layers.65.self_attn.q_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
823
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
824
+ "model.layers.65.self_attn.v_proj.lora_A.default.weight": "model-00024-of-00030.safetensors",
825
+ "model.layers.65.self_attn.v_proj.lora_B.default.weight": "model-00024-of-00030.safetensors",
826
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
827
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
828
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
829
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
830
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
831
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
832
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
833
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
834
+ "model.layers.66.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
835
+ "model.layers.66.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
836
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
837
+ "model.layers.66.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
838
+ "model.layers.66.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
839
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
840
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
841
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
842
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
843
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
844
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
845
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
846
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
847
+ "model.layers.67.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
848
+ "model.layers.67.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
849
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
850
+ "model.layers.67.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
851
+ "model.layers.67.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
852
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
853
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
854
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
855
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
856
+ "model.layers.68.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
857
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
858
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
859
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
860
+ "model.layers.68.self_attn.q_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
861
+ "model.layers.68.self_attn.q_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
862
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
863
+ "model.layers.68.self_attn.v_proj.lora_A.default.weight": "model-00025-of-00030.safetensors",
864
+ "model.layers.68.self_attn.v_proj.lora_B.default.weight": "model-00025-of-00030.safetensors",
865
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
866
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
867
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
868
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
869
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
870
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
871
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
872
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
873
+ "model.layers.69.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
874
+ "model.layers.69.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
875
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
876
+ "model.layers.69.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
877
+ "model.layers.69.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
878
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
879
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00030.safetensors",
880
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
881
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
882
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
883
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
884
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
885
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
886
+ "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
887
+ "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
888
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
889
+ "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
890
+ "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
891
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
892
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
893
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
894
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
895
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
896
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
897
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
898
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
899
+ "model.layers.70.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
900
+ "model.layers.70.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
901
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
902
+ "model.layers.70.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
903
+ "model.layers.70.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
904
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
905
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
906
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
907
+ "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
908
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
909
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
910
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
911
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
912
+ "model.layers.71.self_attn.q_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
913
+ "model.layers.71.self_attn.q_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
914
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
915
+ "model.layers.71.self_attn.v_proj.lora_A.default.weight": "model-00026-of-00030.safetensors",
916
+ "model.layers.71.self_attn.v_proj.lora_B.default.weight": "model-00026-of-00030.safetensors",
917
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
918
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
919
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
920
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
921
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
922
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
923
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
924
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
925
+ "model.layers.72.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
926
+ "model.layers.72.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
927
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
928
+ "model.layers.72.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
929
+ "model.layers.72.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
930
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
931
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
932
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
933
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
934
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
935
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
936
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
937
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
938
+ "model.layers.73.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
939
+ "model.layers.73.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
940
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
941
+ "model.layers.73.self_attn.v_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
942
+ "model.layers.73.self_attn.v_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
943
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
944
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
945
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
946
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
947
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
948
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
949
+ "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
950
+ "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
951
+ "model.layers.74.self_attn.q_proj.lora_A.default.weight": "model-00027-of-00030.safetensors",
952
+ "model.layers.74.self_attn.q_proj.lora_B.default.weight": "model-00027-of-00030.safetensors",
953
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
954
+ "model.layers.74.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
955
+ "model.layers.74.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
956
+ "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
957
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
958
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
959
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
960
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
961
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
962
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
963
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
964
+ "model.layers.75.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
965
+ "model.layers.75.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
966
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
967
+ "model.layers.75.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
968
+ "model.layers.75.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
969
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
970
+ "model.layers.76.input_layernorm.weight": "model-00029-of-00030.safetensors",
971
+ "model.layers.76.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
972
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
973
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
974
+ "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
975
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
976
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
977
+ "model.layers.76.self_attn.q_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
978
+ "model.layers.76.self_attn.q_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
979
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
980
+ "model.layers.76.self_attn.v_proj.lora_A.default.weight": "model-00028-of-00030.safetensors",
981
+ "model.layers.76.self_attn.v_proj.lora_B.default.weight": "model-00028-of-00030.safetensors",
982
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
983
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
984
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
985
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
986
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
987
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
988
+ "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
989
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
990
+ "model.layers.77.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
991
+ "model.layers.77.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
992
+ "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
993
+ "model.layers.77.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
994
+ "model.layers.77.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
995
+ "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
996
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
997
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
998
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
999
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
1000
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
1001
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1002
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1003
+ "model.layers.78.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1004
+ "model.layers.78.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1005
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1006
+ "model.layers.78.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1007
+ "model.layers.78.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1008
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1009
+ "model.layers.79.input_layernorm.weight": "model-00030-of-00030.safetensors",
1010
+ "model.layers.79.mlp.down_proj.weight": "model-00030-of-00030.safetensors",
1011
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
1012
+ "model.layers.79.mlp.up_proj.weight": "model-00030-of-00030.safetensors",
1013
+ "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
1014
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
1015
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
1016
+ "model.layers.79.self_attn.q_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1017
+ "model.layers.79.self_attn.q_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1018
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
1019
+ "model.layers.79.self_attn.v_proj.lora_A.default.weight": "model-00029-of-00030.safetensors",
1020
+ "model.layers.79.self_attn.v_proj.lora_B.default.weight": "model-00029-of-00030.safetensors",
1021
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
1022
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
1023
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
1024
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1025
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1026
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
1027
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1028
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1029
+ "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00030.safetensors",
1030
+ "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00030.safetensors",
1031
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
1032
+ "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1033
+ "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1034
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1035
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
1036
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
1037
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
1038
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
1039
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
1040
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
1041
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
1042
+ "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1043
+ "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1044
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
1045
+ "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00030.safetensors",
1046
+ "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00030.safetensors",
1047
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
1048
+ "model.norm.weight": "model-00030-of-00030.safetensors"
1049
+ }
1050
+ }
.ipynb_checkpoints/special_tokens_map-checkpoint.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "pad_token": "</s>",
10
+ "unk_token": "<unk>"
11
+ }
.ipynb_checkpoints/tokenizer-checkpoint.json ADDED
The diff for this file is too large to render. See raw diff
 
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "legacy": false,
37
+ "max_length": 2048,
38
+ "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "</s>",
40
+ "padding_side": "right",
41
+ "sp_model_kwargs": {},
42
+ "stride": 0,
43
+ "tokenizer_class": "LlamaTokenizer",
44
+ "truncation_side": "right",
45
+ "truncation_strategy": "longest_first",
46
+ "unk_token": "<unk>",
47
+ "use_default_system_prompt": true
48
+ }
config.json CHANGED
@@ -3,6 +3,7 @@
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
@@ -21,7 +22,7 @@
21
  "rope_theta": 10000.0,
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.33.1",
25
- "use_cache": true,
26
  "vocab_size": 32000
27
  }
 
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
9
  "hidden_act": "silu",
 
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
+ "transformers_version": "4.34.0",
26
+ "use_cache": false,
27
  "vocab_size": 32000
28
  }
generation_config.json CHANGED
@@ -3,5 +3,6 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.33.1"
 
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.34.0",
7
+ "use_cache": false
8
  }
model-00001-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b546700bbaf1b2534634c1d9b6d80da07e652331d6871444c7015a1ea204ef09
3
  size 9476641016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580c488fb0690719b236cd6b353647f008a0d2f7b64b99c17dd2faf1efba2db5
3
  size 9476641016
model-00002-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef7f9e746b091642c5fc40bbc3fefd37c1e4300dba3a1b4b4e04183ae1a2f6e4
3
  size 9367654872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:171362ba5f5fbdfb8748a896ffe6d9046c028c831d639748831bc4a983955a72
3
  size 9367654872
model-00003-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b0a7a420e7fd24e84f4851eed2274b937beac85ab9663375160eb23b1ecb56b
3
  size 9966915560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fd932a5e2314e22cb8d685e1fe017bdd940af6abc9f50b1e4cdaaec554ce1e
3
  size 9966915560
model-00004-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d1f5fc7fecb953460f5532aad8bc5264e3ab992771e79bd7677ed66c6748e9b
3
  size 9090764688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d535e997465729b02d6d5a8f9c8f8b3c56680293f5f9aebf73a1fc035877ec9
3
  size 9090764688
model-00005-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:786d7670c9243cfc47a52e3d0431b61ab4e689372f664f24144951a9f20ef4b8
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f50a45c461a67a34ce48b6c8e69924a49a7e0662b4dab8f058ce2648528141
3
  size 9367654904
model-00006-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21b027c3faed3ec5dc89b9606e748289c7ab958c70104205d937dd51145dd7b3
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd1788892370f8c768ac36bc1b8177546762d89818df3645241193ee92e872c4
3
  size 9367654912
model-00007-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a80a1d8d1e0682a9467cf4c2a9d2c9cd46bde66308382e0906e376030b4a3f42
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc109827e1007e83b9d8615700a55f8f015b9e71fc263daf72d17982b02b1117
3
  size 9966915592
model-00008-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db6925be38517398dda4ed8f848342d47f82423e9296b50150f8c545a2094ed5
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190037456d36fa00f6a4d7ee09c34dcf5835b244ea48df221311522a33a5c93c
3
  size 9090764696
model-00009-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f78045860cc46aa30deb1c7953ab9a172325fe5ccb8425b488341d6f5639e08a
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6cf64e5fee6337efd4501d6eed92dea7224d5d1e6f443e8cd89b1f6902a74a0
3
  size 9367654904
model-00010-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:319aa4aa5dffbd715f6aa1615dc0257d4400053f2c50632dca9c8c918b4764f4
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:153ae7ef378f1160dd9371c39e1c43c17d5167813cca12a7dfc86381f19de764
3
  size 9367654912
model-00011-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:666db7443e7e3640218e35927088476a4060508e5f539c9c44ecc10bbf0f582c
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31196e1ade022876859439d557c795e3e8fde667e7676c2592ce4229968759f5
3
  size 9966915592
model-00012-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a307ad59d0eeeeffce201349082f0d0d641bba8e618c7efdde2cf47a5405bbb
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:546013f7c34c421e5642ab00eae79437aa6f1a72b33d62a63aa078be93d27abf
3
  size 9090764696
model-00013-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a9ddb22cd84c2ff70504b40294747cad9e5e183d23bc31543204d17b416b70
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c22252c0b2af1860d0debb05e9dc3186840756ca78a71a87adeeebc5d6be5358
3
  size 9367654904
model-00014-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c58e12f47060c1a0e3ac021b91e31d7b5e3b67554e376612fe722c1e914d5c4
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23a1362603304e2dbb152066752a98240631e9d7b7870b4984c044a54376420
3
  size 9367654912
model-00015-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4227c2ad95ada6a5b9fbedad53e7732ace7b30d3983f3c3ea0dc4774ac0fc2f3
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48e772c7cbd6ba6d7ef06ca26078fae5870fea5e5214a878016259d683583d85
3
  size 9966915592
model-00016-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:770082dbf72ef5caa984bb04964feb2b3d39a260072a77731a8b94ed0170b397
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e3ea8796ee8236432845783b2f5a81187e8298ed908fbe2222f2a938ff506e
3
  size 9090764696
model-00017-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52c0713fa3611ecac4e1b792abfd2b5acbfe4b9a13f40d1f64b9942c3baeec68
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e194160d2b5e3928de3c4d7580bfea01c02c819a961d5053761fe16a4f8d7fbd
3
  size 9367654904
model-00018-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a81eb1cc806d394215775e2e749251bd555cdfe94dc19f2ae42c3802fff3854b
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e7a8fb80ba3cf4e7ec1d5be79dca363fad46bc29661f8c3bc7919b3d17d340
3
  size 9367654912
model-00019-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e93263c8d6ff2adf46c3f4a78dd2a11c0384d5eb8d64ea4a3077fd31b56bdead
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcfcad18d5ef41ff492b96ce98e42a630f25132600f6606472b56a08d2d444cd
3
  size 9966915592
model-00020-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa3cf99f94dcf1822892e869633d5ecc47232b4fa9dd2674a6f15ef4062300ef
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9455432be86d22abbf4ed5ce9ee7c964627a0bcfa978d0aea59ddfbb5ab8da6b
3
  size 9090764696
model-00021-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:180d2b10ff1f2184d9f4e1c1b26d1612092c73e879d31e3126956ae50ad83dfe
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11a174a2a207347f1342e26ccd82e4e46c6ef7489672234b87e44e178328bd6
3
  size 9367654904
model-00022-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b7aab2de2795c56daf8fe51244c2848f61eede39faf26751f6375f4eabe9181
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a9ca7dc3bbdcbca26e06e0af0149551c599d7555f3459ccfd8499bf92a030d
3
  size 9367654912
model-00023-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8037098d6e5b4941d445212deaff6f778dc763eca77d0da85068ddd3f6b413af
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbf1e2e05d8a7f7a48ca3d4dcf4f734860495c7e7d2e5b2241fb4f8c4e4fc99
3
  size 9966915592
model-00024-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc69649d6f8dc3f5c36713eedf7601928a421773dcda9f3b56958c3bc2a8e915
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2af5bd75ee7fb288c2858581b691eacd19188e8f9c5e6ba11bc850025ab2586d
3
  size 9090764696
model-00025-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24e6d8b8575643f7feb78f289fc0fe51b5eafc793d061358fe6bd1a34a59532a
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ed803c78b77a8487f9d11faa8538c53871a1c1e2f5008aca70b676549303df
3
  size 9367654904
model-00026-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3030e55ddbd7df9a81ba330a88867384c940fed6199557ab22d814e9318fd115
3
  size 9367654912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556b927745287f43dc08043b4bbce69e1b2ad29a44f789aa2b68e7d5437684fe
3
  size 9367654912
model-00027-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:750bd7b5c019d18a212dabf2b56f248b775f6dbc2180420333c6959c3895dcb0
3
  size 9966915592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e98eb615b5a099e77f0ed62155f275c4b763f15189c4e2ab1b8febae1ff6ea1
3
  size 9966915592
model-00028-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc842f63d6d270787961fa59793a8396a9bb8fbcb03cd568bb0f2412f0e10bf
3
  size 9090764696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f783e824899079e59ffce3f9661a0e36bce839b8088ce63bed8ec6bc580d61a9
3
  size 9090764696
model-00029-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b692da475cf7ccf9db531d748852c89aa7a950ca30d01c9a070f5702e1759c5
3
  size 9367654904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d065c2f09f9227061f14083a6d8dc0e8b33d48ebff958c933aed12f6869bfe70
3
  size 9367654904
model-00030-of-00030.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83854a1537c0617afa4bdffdd710e7a21557e25e7280a920ce199a78af40cce4
3
  size 2927723176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0634c43a1572b20414b3482c52735f3ac42307d55311dc190020173b315abd17
3
  size 2927723176
special_tokens_map.json CHANGED
@@ -1,24 +1,11 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
  "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
 
 
 
 
 
 
 
9
  "pad_token": "</s>",
10
+ "unk_token": "<unk>"
 
 
 
 
 
 
11
  }
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 2048,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -1,38 +1,48 @@
1
  {
2
- "bos_token": {
3
- "__type": "AddedToken",
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
 
 
 
 
 
 
10
  "clean_up_tokenization_spaces": false,
11
- "eos_token": {
12
- "__type": "AddedToken",
13
- "content": "</s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
  "legacy": false,
20
  "max_length": 2048,
21
  "model_max_length": 1000000000000000019884624838656,
22
- "pad_token": null,
23
  "padding_side": "right",
24
  "sp_model_kwargs": {},
25
  "stride": 0,
26
  "tokenizer_class": "LlamaTokenizer",
27
  "truncation_side": "right",
28
  "truncation_strategy": "longest_first",
29
- "unk_token": {
30
- "__type": "AddedToken",
31
- "content": "<unk>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
  "use_default_system_prompt": true
38
  }
 
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
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
  "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
 
 
 
 
 
 
 
36
  "legacy": false,
37
  "max_length": 2048,
38
  "model_max_length": 1000000000000000019884624838656,
39
+ "pad_token": "</s>",
40
  "padding_side": "right",
41
  "sp_model_kwargs": {},
42
  "stride": 0,
43
  "tokenizer_class": "LlamaTokenizer",
44
  "truncation_side": "right",
45
  "truncation_strategy": "longest_first",
46
+ "unk_token": "<unk>",
 
 
 
 
 
 
 
47
  "use_default_system_prompt": true
48
  }