BramVanroy commited on
Commit
675468f
1 Parent(s): 1b96c9e

Training in progress, step 4500, checkpoint

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-4500/added_tokens.json +40 -0
  2. checkpoint-4500/config.json +34 -0
  3. checkpoint-4500/generation_config.json +6 -0
  4. checkpoint-4500/global_step4500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  5. checkpoint-4500/global_step4500/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt +3 -0
  6. checkpoint-4500/global_step4500/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt +3 -0
  7. checkpoint-4500/global_step4500/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt +3 -0
  8. checkpoint-4500/global_step4500/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt +3 -0
  9. checkpoint-4500/global_step4500/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt +3 -0
  10. checkpoint-4500/global_step4500/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt +3 -0
  11. checkpoint-4500/global_step4500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  12. checkpoint-4500/global_step4500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  13. checkpoint-4500/global_step4500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  14. checkpoint-4500/global_step4500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  15. checkpoint-4500/global_step4500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  16. checkpoint-4500/global_step4500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  17. checkpoint-4500/global_step4500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  18. checkpoint-4500/global_step4500/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt +3 -0
  19. checkpoint-4500/global_step4500/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt +3 -0
  20. checkpoint-4500/global_step4500/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  21. checkpoint-4500/global_step4500/zero_pp_rank_10_mp_rank_00_model_states.pt +3 -0
  22. checkpoint-4500/global_step4500/zero_pp_rank_11_mp_rank_00_model_states.pt +3 -0
  23. checkpoint-4500/global_step4500/zero_pp_rank_12_mp_rank_00_model_states.pt +3 -0
  24. checkpoint-4500/global_step4500/zero_pp_rank_13_mp_rank_00_model_states.pt +3 -0
  25. checkpoint-4500/global_step4500/zero_pp_rank_14_mp_rank_00_model_states.pt +3 -0
  26. checkpoint-4500/global_step4500/zero_pp_rank_15_mp_rank_00_model_states.pt +3 -0
  27. checkpoint-4500/global_step4500/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  28. checkpoint-4500/global_step4500/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  29. checkpoint-4500/global_step4500/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  30. checkpoint-4500/global_step4500/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  31. checkpoint-4500/global_step4500/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  32. checkpoint-4500/global_step4500/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  33. checkpoint-4500/global_step4500/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  34. checkpoint-4500/global_step4500/zero_pp_rank_8_mp_rank_00_model_states.pt +3 -0
  35. checkpoint-4500/global_step4500/zero_pp_rank_9_mp_rank_00_model_states.pt +3 -0
  36. checkpoint-4500/latest +1 -0
  37. checkpoint-4500/merges.txt +0 -0
  38. checkpoint-4500/model-00001-of-00002.safetensors +3 -0
  39. checkpoint-4500/model-00002-of-00002.safetensors +3 -0
  40. checkpoint-4500/model.safetensors.index.json +460 -0
  41. checkpoint-4500/rng_state_0.pth +3 -0
  42. checkpoint-4500/rng_state_1.pth +3 -0
  43. checkpoint-4500/rng_state_10.pth +3 -0
  44. checkpoint-4500/rng_state_11.pth +3 -0
  45. checkpoint-4500/rng_state_12.pth +3 -0
  46. checkpoint-4500/rng_state_13.pth +3 -0
  47. checkpoint-4500/rng_state_14.pth +3 -0
  48. checkpoint-4500/rng_state_15.pth +3 -0
  49. checkpoint-4500/rng_state_2.pth +3 -0
  50. checkpoint-4500/rng_state_3.pth +3 -0
checkpoint-4500/added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4500/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.39.1"
6
+ }
checkpoint-4500/global_step4500/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84ca5b72070d7d87d18a952ac6ab4ad78064596e26ebc17e23029cffca544156
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_10_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadf14e2cdc6e12beca6d50efca2a464c45d43838b7a6fee4bf55f19ff491337
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_11_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ac48468cd892a8f728a12208626308240b43e0e4d4a3348bcbded475a35fb5
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_12_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c485ee943f4a098dc47839953847934b04db6b81ea7e38fe54271e46fb85fa
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_13_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a11dc6a5782607ce400eb70a02986e6647423dd233b2fd016805dad6c79ad835
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_14_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c308642a693ea3297dbec0103da2d76bf883f7f365512875b327eac2a106af13
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_15_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea18bd7c42b31de854cbf0ef9b77901c4a8f71dbda777642fd8d9abcf11abe4
3
+ size 2084767612
checkpoint-4500/global_step4500/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39345fd1c993f9454bc4173fd58d9586823f2c117655def720f25b90665f9ff2
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedf40ba239e3172d5463c8c7325bb5dd438d7907741dd496bb09e8fe8983ef4
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfeec07b8ef324ec7e5492b4bb9a6fa1ce8cfe6655bd27380d337c9e4184707d
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17ef37f35b79cdcd3e9e886ac943369425af7cb4da36fd9f82255a747090639b
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90fd8d56eaeab2a34500014baa3471790d0879b135fd45aaa27572ba03e3d0af
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8e9071e65fa96d007999c422fef3da1416104920d3dd9bd8d95c1c7b8110910
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb74296a51d1bbacda164eed3b0d1bc777d3c32e7aa68289c06c98dc7290906a
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_8_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:694acd51df3844bb6cd3238714f5067df153e5a399b8ccdf15bf7840b1b7b3e0
3
+ size 2084767600
checkpoint-4500/global_step4500/bf16_zero_pp_rank_9_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3e3d8525744017396b1d4a7e31902c7c73b8b076b1fc07a3309535ee20b0e1b
3
+ size 2084767600
checkpoint-4500/global_step4500/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ba5ce3b72ae4d2e0db5091877126a78385a358d64b49f464e6de54223ddee32
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_10_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd3d0f2a492b32d839679231153698fead536f634f094a47d58b05f08bc411e
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_11_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae19a12a53af0c95e27107aceeaa89b88c4c9075471ecbc1c741310fe6d1b16e
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_12_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:637fa2a79d32d2b7b6d0efd4a6d7d6132fcd303e10c6387425b5d9b0c4a72cec
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_13_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:719fe13aee9c0fcecae8888ba02c06123bc8b08651d4096254a4f0dcfd805c08
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_14_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7908d902892ae4d82abe0c7a974cd1756b59db766a51173141a2620ff0f9796
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_15_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d399b50e4feca299fa6248f5b0c8eb39fb8602ea78f7c27e55b4c8c2886f77c0
3
+ size 215368
checkpoint-4500/global_step4500/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e350d3c4cc9cd06173a5f07e60d55ffbf0fbbf486254aa28d8e1dccfb31516
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfff9f4a5d5b983c5198c1009ef43d19ae42684dca6bfa8f5f9b08c06eb7cc5e
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af539617693b8adc62260c41d473f3728fe5d0874d4511019dbf86b15eeb3276
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d6364b63ba4ff87da504877ab810707d001cd6e25b6e07c882e0676b54f71e
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194b228e21e6f2e4111c23f6fcd1b30d2e6b3f0573a17f48e53ff1990b00e27e
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f97d364c7af69c826f10118c90e1ae515c05c88dc02ab2a1ffeedce98fea1c
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906125f74e6c7c47b763b12c4f3ae26cc76217fac42a42d383633109150fdd9d
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_8_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3e0ee991e350d8b36a7240d480ec9c8cc20080358880ee4658f3bcc1ebfb7d5
3
+ size 214911
checkpoint-4500/global_step4500/zero_pp_rank_9_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04e63a40dfb0b61149cc36558e3806241eab1ae94308d6abc706ce06dcd7354
3
+ size 214911
checkpoint-4500/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step4500
checkpoint-4500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da8659dd6139c6040322878b8e35045e91ed8beb0fc02dfa5e192d400e3e90f0
3
+ size 4995584848
checkpoint-4500/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:615f2b007b11f701d2a69d98bd230f210f3e2e7397ed9afa2a69196cb09d6745
3
+ size 563833008
checkpoint-4500/model.safetensors.index.json ADDED
@@ -0,0 +1,460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-4500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9298d61fc9834a182b97a2e19f69308c3b483011b074f3665606e374cb64ae11
3
+ size 14960
checkpoint-4500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e52c4f24a51bffa0b3bba0abb769e2d75f4b187544e9e80cc35cdf0fcdfa37
3
+ size 14960
checkpoint-4500/rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88c8f9b228c2f61043b8dd9d3a76428b403f0ad6587c18ea665a3f05062aaae
3
+ size 14969
checkpoint-4500/rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:966160208eb4bdaa55793341a31e08b1ca0457a5db721acc01cf2a523ae5efa9
3
+ size 14969
checkpoint-4500/rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6a53c7f5db589d5e13fb8fce846f8d143a209105db0abf70421a7e9a20e109
3
+ size 14969
checkpoint-4500/rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce5a015a151cd872805b9dd2d8b92910a133cb8fcbcbf71a61e94e33569336b
3
+ size 14969
checkpoint-4500/rng_state_14.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7ac7c12ad0ecdf1d0846270f4727964391d049ae068a1f72e2ae84c61f6e3c
3
+ size 14969
checkpoint-4500/rng_state_15.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6674105a344332f3407a0a91f9db0cccb301e4c3f92ec34c24f7ed6d4eb761
3
+ size 14969
checkpoint-4500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55cee1a37c85ad984253684c7a2b878bed0ef7167419b0dff5f141a1dead6cd
3
+ size 14960
checkpoint-4500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92afaa3afb018b261fae085e103a7e1b97a0c918e9565ec85a7d0b38d73350ef
3
+ size 14960