Hugging Face's logo

BramVanroy
/
fietje-2

Text Generation
Transformers
Safetensors
Dutch
phi
trl
fietje
alignment-handbook
text-generation-inference
Model card Files Community
BramVanroy commited on
Commit
006f4d6
•
1 Parent(s): 72d1e14

Delete checkpoint-3600

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-3600/added_tokens.json +0 -40
  2. checkpoint-3600/config.json +0 -34
  3. checkpoint-3600/generation_config.json +0 -6
  4. checkpoint-3600/global_step3600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +0 -3
  5. checkpoint-3600/global_step3600/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +0 -3
  6. checkpoint-3600/global_step3600/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +0 -3
  7. checkpoint-3600/global_step3600/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +0 -3
  8. checkpoint-3600/global_step3600/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +0 -3
  9. checkpoint-3600/global_step3600/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +0 -3
  10. checkpoint-3600/global_step3600/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +0 -3
  11. checkpoint-3600/global_step3600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +0 -3
  12. checkpoint-3600/global_step3600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +0 -3
  13. checkpoint-3600/global_step3600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +0 -3
  14. checkpoint-3600/global_step3600/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +0 -3
  15. checkpoint-3600/global_step3600/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +0 -3
  16. checkpoint-3600/global_step3600/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +0 -3
  17. checkpoint-3600/global_step3600/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +0 -3
  18. checkpoint-3600/global_step3600/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +0 -3
  19. checkpoint-3600/global_step3600/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +0 -3
  20. checkpoint-3600/global_step3600/zero_pp_rank_0_mp_rank_00_model_states.pt +0 -3
  21. checkpoint-3600/global_step3600/zero_pp_rank_10_mp_rank_00_model_states.pt +0 -3
  22. checkpoint-3600/global_step3600/zero_pp_rank_11_mp_rank_00_model_states.pt +0 -3
  23. checkpoint-3600/global_step3600/zero_pp_rank_12_mp_rank_00_model_states.pt +0 -3
  24. checkpoint-3600/global_step3600/zero_pp_rank_13_mp_rank_00_model_states.pt +0 -3
  25. checkpoint-3600/global_step3600/zero_pp_rank_14_mp_rank_00_model_states.pt +0 -3
  26. checkpoint-3600/global_step3600/zero_pp_rank_15_mp_rank_00_model_states.pt +0 -3
  27. checkpoint-3600/global_step3600/zero_pp_rank_1_mp_rank_00_model_states.pt +0 -3
  28. checkpoint-3600/global_step3600/zero_pp_rank_2_mp_rank_00_model_states.pt +0 -3
  29. checkpoint-3600/global_step3600/zero_pp_rank_3_mp_rank_00_model_states.pt +0 -3
  30. checkpoint-3600/global_step3600/zero_pp_rank_4_mp_rank_00_model_states.pt +0 -3
  31. checkpoint-3600/global_step3600/zero_pp_rank_5_mp_rank_00_model_states.pt +0 -3
  32. checkpoint-3600/global_step3600/zero_pp_rank_6_mp_rank_00_model_states.pt +0 -3
  33. checkpoint-3600/global_step3600/zero_pp_rank_7_mp_rank_00_model_states.pt +0 -3
  34. checkpoint-3600/global_step3600/zero_pp_rank_8_mp_rank_00_model_states.pt +0 -3
  35. checkpoint-3600/global_step3600/zero_pp_rank_9_mp_rank_00_model_states.pt +0 -3
  36. checkpoint-3600/latest +0 -1
  37. checkpoint-3600/merges.txt +0 -0
  38. checkpoint-3600/model-00001-of-00002.safetensors +0 -3
  39. checkpoint-3600/model-00002-of-00002.safetensors +0 -3
  40. checkpoint-3600/model.safetensors.index.json +0 -460
  41. checkpoint-3600/rng_state_0.pth +0 -3
  42. checkpoint-3600/rng_state_1.pth +0 -3
  43. checkpoint-3600/rng_state_10.pth +0 -3
  44. checkpoint-3600/rng_state_11.pth +0 -3
  45. checkpoint-3600/rng_state_12.pth +0 -3
  46. checkpoint-3600/rng_state_13.pth +0 -3
  47. checkpoint-3600/rng_state_14.pth +0 -3
  48. checkpoint-3600/rng_state_15.pth +0 -3
  49. checkpoint-3600/rng_state_2.pth +0 -3
  50. checkpoint-3600/rng_state_3.pth +0 -3
checkpoint-3600/added_tokens.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "\t\t": 50294,
3
- "\t\t\t": 50293,
4
- "\t\t\t\t": 50292,
5
- "\t\t\t\t\t": 50291,
6
- "\t\t\t\t\t\t": 50290,
7
- "\t\t\t\t\t\t\t": 50289,
8
- "\t\t\t\t\t\t\t\t": 50288,
9
- "\t\t\t\t\t\t\t\t\t": 50287,
10
- " ": 50286,
11
- " ": 50285,
12
- " ": 50284,
13
- " ": 50283,
14
- " ": 50282,
15
- " ": 50281,
16
- " ": 50280,
17
- " ": 50279,
18
- " ": 50278,
19
- " ": 50277,
20
- " ": 50276,
21
- " ": 50275,
22
- " ": 50274,
23
- " ": 50273,
24
- " ": 50272,
25
- " ": 50271,
26
- " ": 50270,
27
- " ": 50269,
28
- " ": 50268,
29
- " ": 50267,
30
- " ": 50266,
31
- " ": 50265,
32
- " ": 50264,
33
- " ": 50263,
34
- " ": 50262,
35
- " ": 50261,
36
- " ": 50260,
37
- " ": 50259,
38
- " ": 50258,
39
- " ": 50257
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3600/config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "_name_or_path": "microsoft/phi-2",
3
- "architectures": [
4
- "PhiForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "auto_map": {
8
- "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
- "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
- },
11
- "bos_token_id": 50256,
12
- "embd_pdrop": 0.0,
13
- "eos_token_id": 50256,
14
- "hidden_act": "gelu_new",
15
- "hidden_size": 2560,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 10240,
18
- "layer_norm_eps": 1e-05,
19
- "max_position_embeddings": 2048,
20
- "model_type": "phi",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 32,
23
- "num_key_value_heads": 32,
24
- "partial_rotary_factor": 0.4,
25
- "qk_layernorm": false,
26
- "resid_pdrop": 0.1,
27
- "rope_scaling": null,
28
- "rope_theta": 10000.0,
29
- "tie_word_embeddings": false,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.39.1",
32
- "use_cache": false,
33
- "vocab_size": 51200
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3600/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.39.1"
6
- }
 
 
 
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfba96200f0e780ba5eb2e25c1132d8f534661dda95a9599dfc3177e005961a6
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ff2bdad4512e566edb535def7acaad3f1acddd8afd620c8d30313a22cbc54ae
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d88bafa49d3324acb91aef6f223ca411773b42fac147a385e68a232d82716352
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca53d8ec41723866edb44adf2292eb7ab9b2d4f919e8f0fc595307d5784e17c5
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b191d0dc5ee2f850d869f9987e9c38698ba77cbad18d932b0d01329672ac7317
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d045e12f0934cd81be1142b41335d95891766a7ce41369f605d03a907aa955
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1136f912d5b8c0fd6259a6f091ba892c9b8709598695f8e2855b712e64b2f287
3
- size 2084767612
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dbd915f830bcab3b015a787dcae10493dc77270e5ac427c5ea09ca5d9f95ae6
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:497bb3644cae25b3d1fe6d2b552f7ce50ef11fc5d040743a6e61f688a720493e
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5304392b22f6fa40ff6c97caf2711d9dcce607f34e2a8280ca96a412ba488ef
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:16e934d6f5dec1692b4825ef2e46e875a2742ea3125cb21ecf01bb0d17681c09
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab6a70269ed642e201cc9870dea95adc45a55b80507b1719428842241e103ce3
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a57b2bc628e5ad3277da5f77eab07a21f7e88c29c22d7d6e1cd6cdf5c85d8385
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c001dffb74607d1f9dff796a0a7f1320a36046f4ab5da2cc6d776023d95f8c3
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f0e195da9e9fa821d9180a32aed15d50d99422e2f109504097c2571ebce9a48
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fc39f9107d27e0f1d77a1b59a02fdda9432e47972e588e967b2b1a7b6c0d0a2
3
- size 2084767600
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_0_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7490a2a8e396b0d33e9a0af258cdda5d0df829613f808750703e98e48dca0cda
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_10_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:42990e42f57f129d0b6c32f1dca51c3f8c77347a4f797235136597373efdbab6
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_11_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:abeac953041dd44d5130e36b6410c27c589265bc7ed47a09538442b06ff3ccb6
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_12_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0436eb4874d41b6659339b6f5c1a954d57a3aacd23d8cec223ac8a817e46d09e
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_13_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c694bfbe9064441116e960fcfbd57eab4356aa2e4bc099324e014a47f056ee80
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_14_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:679112096993966127cb3a02da00fc7a98c98f38c2e6fa8034f08ba21271e318
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_15_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b3d303ba7120c8f23c488c348b1028339c6d72d1ffdd2fd2f73d239fabd8b52
3
- size 215368
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_1_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:636adf7c70830ea81e3afb6fd0431fb33a8621f7b50c6f0f1f17f7fc91c6784c
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_2_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f390ecf745827c14fe8b2b2882785d0b6578167f4562912a0de2c7218fa5a2
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_3_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e609277d6c77d01f38a133bf4f0952fe3d55d344a13a6f9102951d0bd12a1d32
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_4_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2a0ad14608fe37c493f7e8dd6bc21049ce9f2fc05c5f437432311a2cf17e3f8
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_5_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a10efc1d14c3b5ad5269547f5f39f80b08d9444ae707befb062a5c82f771e5b
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_6_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:089eda45fbfd05c529a9a48e57d108ac53c0521a6b4799f30d4931d8f9c2ed4f
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_7_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b2e7a0d51455cbf1e863a18cd8a6a10419679b74601fcab7e01b4eba353aa56
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_8_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ed42f7bf263e6a868f04c1e1937963e019d9b5d26961984330f6424396fc0c5
3
- size 214911
 
 
 
 
checkpoint-3600/global_step3600/zero_pp_rank_9_mp_rank_00_model_states.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:296da4f5d9689deed75d07e2a3ad2d27a676d73580c3482c746a389bc2bf0754
3
- size 214911
 
 
 
 
checkpoint-3600/latest DELETED
@@ -1 +0,0 @@
1
- global_step3600
 
 
checkpoint-3600/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-3600/model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a525a331e989f48182267f2ce863ee0a203a2a6f5297c529ae76953167c12e
3
- size 4995584848
 
 
 
 
checkpoint-3600/model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c936d6cfe8053a3a07c5bf309f1edb10456b1f84bee5b5af7ddccc6ba172dc7c
3
- size 563833008
 
 
 
 
checkpoint-3600/model.safetensors.index.json DELETED
@@ -1,460 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 5559367680
4
- },
5
- "weight_map": {
6
- "lm_head.bias": "model-00002-of-00002.safetensors",
7
- "lm_head.weight": "model-00002-of-00002.safetensors",
8
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
- "model.final_layernorm.bias": "model-00002-of-00002.safetensors",
10
- "model.final_layernorm.weight": "model-00002-of-00002.safetensors",
11
- "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
12
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
16
- "model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
18
- "model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
20
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
22
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
24
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
26
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
28
- "model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
30
- "model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
32
- "model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
34
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
36
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
38
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
40
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
42
- "model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
44
- "model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
46
- "model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
48
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
50
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
52
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
54
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
56
- "model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
58
- "model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
60
- "model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
62
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
68
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
70
- "model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
72
- "model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
74
- "model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
76
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
82
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
84
- "model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
86
- "model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
88
- "model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
90
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
92
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
94
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
96
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
98
- "model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
100
- "model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
102
- "model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
104
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
106
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
108
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
110
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
112
- "model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
114
- "model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
116
- "model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
118
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
120
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
122
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
124
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
126
- "model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
128
- "model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
129
- "model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
130
- "model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
132
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
134
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
135
- "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
136
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
137
- "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
138
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
140
- "model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
142
- "model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
144
- "model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
145
- "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
146
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
- "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
152
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
154
- "model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
156
- "model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
158
- "model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
160
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
- "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
- "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
166
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
167
- "model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
168
- "model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
170
- "model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
171
- "model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
172
- "model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
174
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
176
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
178
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
179
- "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
180
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
181
- "model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
182
- "model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
184
- "model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
185
- "model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
186
- "model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
188
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
190
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
192
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
194
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
- "model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
196
- "model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
198
- "model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
200
- "model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
202
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
204
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
206
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
208
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
210
- "model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
212
- "model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
214
- "model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
216
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
218
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
220
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
222
- "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
224
- "model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
225
- "model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
226
- "model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
228
- "model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
230
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
232
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
234
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
235
- "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
236
- "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
238
- "model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
240
- "model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
242
- "model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
244
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
246
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
248
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
250
- "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
252
- "model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
254
- "model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
256
- "model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
258
- "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
260
- "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
261
- "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
262
- "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
263
- "model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
264
- "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
266
- "model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
267
- "model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
268
- "model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
270
- "model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
271
- "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
272
- "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
273
- "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
274
- "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
276
- "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
277
- "model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
278
- "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
- "model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
280
- "model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
281
- "model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
282
- "model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
283
- "model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
284
- "model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
285
- "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
286
- "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
287
- "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
288
- "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
290
- "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
291
- "model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
292
- "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
- "model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
294
- "model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
295
- "model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
296
- "model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
297
- "model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
298
- "model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
299
- "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
300
- "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
301
- "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
302
- "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
303
- "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
304
- "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
305
- "model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
306
- "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
307
- "model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
308
- "model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
309
- "model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
310
- "model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
311
- "model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
312
- "model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
313
- "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
314
- "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
315
- "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
316
- "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
317
- "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
318
- "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
- "model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
320
- "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
321
- "model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
322
- "model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
323
- "model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
324
- "model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
325
- "model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
326
- "model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
327
- "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
328
- "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
329
- "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
330
- "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
- "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
332
- "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
333
- "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
334
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
335
- "model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
336
- "model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
337
- "model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
338
- "model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
339
- "model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
340
- "model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
341
- "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
342
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
- "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
344
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
- "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
346
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
347
- "model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
348
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
350
- "model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
351
- "model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
352
- "model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
353
- "model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
354
- "model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
355
- "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
356
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
357
- "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
358
- "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
- "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
360
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
361
- "model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
362
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
363
- "model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
364
- "model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
365
- "model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
366
- "model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
367
- "model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
368
- "model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
369
- "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
370
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
371
- "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
372
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
373
- "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
374
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
375
- "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
376
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
378
- "model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
379
- "model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
380
- "model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
381
- "model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
382
- "model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
383
- "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
384
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
385
- "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
386
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
387
- "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
388
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
389
- "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
390
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
391
- "model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
392
- "model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
393
- "model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
394
- "model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
395
- "model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
396
- "model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
397
- "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
398
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
399
- "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
- "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
404
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
405
- "model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
406
- "model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
407
- "model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
408
- "model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
409
- "model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
410
- "model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
411
- "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
412
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
413
- "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
- "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
- "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
418
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
419
- "model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
420
- "model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
421
- "model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
422
- "model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
424
- "model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
426
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
428
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
430
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
431
- "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
432
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
434
- "model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
435
- "model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
436
- "model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
437
- "model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
438
- "model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
439
- "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
440
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
441
- "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
442
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
444
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
445
- "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
446
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
447
- "model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
448
- "model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
449
- "model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
450
- "model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
451
- "model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
452
- "model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
453
- "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
454
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
455
- "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
456
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
457
- "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
458
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
459
- }
460
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-3600/rng_state_0.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b9c8985631678e48f1b388dff693886f59a2896c357d8dcf7eaf376b5cf596d
3
- size 14960
 
 
 
 
checkpoint-3600/rng_state_1.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1167c2d232fb9c41c9a881daf5754ea0f6e5d46207f6610e428f17780f6c328
3
- size 14960
 
 
 
 
checkpoint-3600/rng_state_10.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9981daf0e5643492d6386a1de623f30608242231c03a0bbf73f5a8fdab32cd8
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_11.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c290d76854254e35871f151f1d4c8845eb80fd5c34f229046cb063cc91455fc
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_12.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:99880e80a886d657b30d47bd4a3aa6ebf56bbdd0804e47fdd8772fdf3a271b5a
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_13.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:51c5668792b6bc653e65fa6c6312bba2a43bf130c5f41b3f772ac8154b8b4253
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_14.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:820b04fddbd9268fbed54f176954f85a3d0d57f0eb7a94eb4e7676ef57ba41ec
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_15.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae30cc6b0d4455172460c783c2d837f6b5e245f38d55b7e1e36f7490712d0422
3
- size 14969
 
 
 
 
checkpoint-3600/rng_state_2.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca1ca2afe2d6463421df080fc6fe1927f8a4c816beafcc8fde7234c297c44594
3
- size 14960
 
 
 
 
checkpoint-3600/rng_state_3.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ef9bcceb964f85b72c51ead2f6cb4e18928e7c4d451dc27dccc22b299c2e7f
3
- size 14960