tsavage68 commited on
Commit
d18768e
·
verified ·
1 Parent(s): 2ce4afe

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: apache-2.0
3
- base_model: mistralai/Mistral-7B-Instruct-v0.1
4
  tags:
5
  - trl
6
  - dpo
@@ -15,17 +15,17 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # v1_1000_STEPS_1e6_rate_03_beta_DPO
17
 
18
- This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.8487
21
- - Rewards/chosen: -2.2151
22
- - Rewards/rejected: -3.0240
23
- - Rewards/accuracies: 0.5758
24
- - Rewards/margins: 0.8089
25
- - Logps/rejected: -26.9594
26
- - Logps/chosen: -22.6366
27
- - Logits/rejected: -3.2869
28
- - Logits/chosen: -3.2870
29
 
30
  ## Model description
31
 
@@ -59,26 +59,26 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
62
- | 0.7016 | 0.05 | 50 | 0.6686 | -0.1010 | -0.1780 | 0.5516 | 0.0771 | -17.4730 | -15.5896 | -3.3830 | -3.3830 |
63
- | 0.6727 | 0.1 | 100 | 0.7732 | -1.2186 | -1.6229 | 0.5275 | 0.4043 | -22.2891 | -19.3150 | -3.3350 | -3.3352 |
64
- | 1.2098 | 0.15 | 150 | 0.9205 | -1.6685 | -2.0242 | 0.5209 | 0.3558 | -23.6270 | -20.8147 | -3.3998 | -3.4000 |
65
- | 0.8607 | 0.2 | 200 | 0.9312 | -1.7362 | -2.0915 | 0.5099 | 0.3553 | -23.8513 | -21.0405 | -3.3324 | -3.3326 |
66
- | 0.896 | 0.24 | 250 | 0.9765 | -1.8658 | -2.0921 | 0.5011 | 0.2263 | -23.8533 | -21.4723 | -3.2214 | -3.2215 |
67
- | 0.9783 | 0.29 | 300 | 0.9234 | -1.9658 | -2.3835 | 0.5165 | 0.4177 | -24.8244 | -21.8057 | -3.3158 | -3.3160 |
68
- | 1.0592 | 0.34 | 350 | 0.9509 | -3.1300 | -3.4037 | 0.5033 | 0.2738 | -28.2253 | -25.6863 | -3.2697 | -3.2698 |
69
- | 1.0391 | 0.39 | 400 | 0.9067 | -2.4562 | -2.8182 | 0.5231 | 0.3619 | -26.2735 | -23.4405 | -3.3616 | -3.3617 |
70
- | 0.9409 | 0.44 | 450 | 0.9081 | -2.8095 | -3.1865 | 0.5231 | 0.3771 | -27.5014 | -24.6179 | -3.3324 | -3.3325 |
71
- | 0.8139 | 0.49 | 500 | 0.9131 | -2.8071 | -3.2564 | 0.5560 | 0.4493 | -27.7343 | -24.6100 | -3.3362 | -3.3363 |
72
- | 0.8732 | 0.54 | 550 | 0.8745 | -2.3409 | -3.0357 | 0.5516 | 0.6948 | -26.9986 | -23.0562 | -3.3124 | -3.3125 |
73
- | 0.8179 | 0.59 | 600 | 0.8632 | -2.1460 | -2.9478 | 0.5692 | 0.8018 | -26.7055 | -22.4063 | -3.3039 | -3.3040 |
74
- | 0.825 | 0.64 | 650 | 0.8769 | -1.9605 | -2.7326 | 0.5626 | 0.7721 | -25.9882 | -21.7879 | -3.3006 | -3.3007 |
75
- | 0.7539 | 0.68 | 700 | 0.8600 | -2.1758 | -2.9531 | 0.5714 | 0.7773 | -26.7232 | -22.5059 | -3.2794 | -3.2795 |
76
- | 0.7835 | 0.73 | 750 | 0.8551 | -2.2525 | -3.0394 | 0.5692 | 0.7868 | -27.0107 | -22.7614 | -3.2905 | -3.2906 |
77
- | 0.925 | 0.78 | 800 | 0.8479 | -2.2131 | -3.0235 | 0.5736 | 0.8105 | -26.9579 | -22.6299 | -3.2902 | -3.2903 |
78
- | 1.0166 | 0.83 | 850 | 0.8493 | -2.2090 | -3.0157 | 0.5780 | 0.8067 | -26.9319 | -22.6164 | -3.2872 | -3.2873 |
79
- | 1.0711 | 0.88 | 900 | 0.8480 | -2.2126 | -3.0221 | 0.5758 | 0.8095 | -26.9532 | -22.6283 | -3.2869 | -3.2870 |
80
- | 0.9928 | 0.93 | 950 | 0.8487 | -2.2161 | -3.0255 | 0.5802 | 0.8094 | -26.9646 | -22.6400 | -3.2869 | -3.2870 |
81
- | 0.6707 | 0.98 | 1000 | 0.8487 | -2.2151 | -3.0240 | 0.5758 | 0.8089 | -26.9594 | -22.6366 | -3.2869 | -3.2870 |
82
 
83
 
84
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: mosaicml/mpt-7b-instruct
4
  tags:
5
  - trl
6
  - dpo
 
15
 
16
  # v1_1000_STEPS_1e6_rate_03_beta_DPO
17
 
18
+ This model is a fine-tuned version of [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.6641
21
+ - Rewards/chosen: -1.4066
22
+ - Rewards/rejected: -1.6576
23
+ - Rewards/accuracies: 0.6198
24
+ - Rewards/margins: 0.2510
25
+ - Logps/rejected: -27.0829
26
+ - Logps/chosen: -25.4808
27
+ - Logits/rejected: 13.3887
28
+ - Logits/chosen: 13.3921
29
 
30
  ## Model description
31
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
61
  |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
62
+ | 0.6901 | 0.05 | 50 | 0.6931 | 0.0510 | 0.0490 | 0.5253 | 0.0019 | -21.3940 | -20.6223 | 14.3181 | 14.3207 |
63
+ | 0.7257 | 0.1 | 100 | 0.6841 | 0.0934 | 0.0501 | 0.5692 | 0.0433 | -21.3906 | -20.4809 | 14.1613 | 14.1641 |
64
+ | 0.7259 | 0.15 | 150 | 0.6925 | -0.0147 | -0.0834 | 0.5451 | 0.0688 | -21.8355 | -20.8411 | 13.9200 | 13.9229 |
65
+ | 0.6593 | 0.2 | 200 | 0.7118 | 0.4903 | 0.3962 | 0.5802 | 0.0941 | -20.2368 | -19.1579 | 13.7791 | 13.7821 |
66
+ | 0.7282 | 0.24 | 250 | 0.7093 | -1.2326 | -1.3686 | 0.5648 | 0.1360 | -26.1195 | -24.9010 | 13.8037 | 13.8067 |
67
+ | 0.6924 | 0.29 | 300 | 0.6944 | -0.7898 | -0.9655 | 0.5626 | 0.1757 | -24.7758 | -23.4250 | 14.0496 | 14.0528 |
68
+ | 0.7523 | 0.34 | 350 | 0.6909 | -0.9371 | -1.1226 | 0.5626 | 0.1855 | -25.2994 | -23.9158 | 14.0003 | 14.0037 |
69
+ | 0.7276 | 0.39 | 400 | 0.6918 | -1.8471 | -2.0415 | 0.5868 | 0.1944 | -28.3625 | -26.9492 | 13.3382 | 13.3414 |
70
+ | 0.6255 | 0.44 | 450 | 0.6860 | -1.5470 | -1.7599 | 0.5934 | 0.2129 | -27.4236 | -25.9489 | 13.2551 | 13.2584 |
71
+ | 0.7342 | 0.49 | 500 | 0.6801 | -1.5841 | -1.7888 | 0.5758 | 0.2046 | -27.5199 | -26.0726 | 13.4186 | 13.4219 |
72
+ | 0.568 | 0.54 | 550 | 0.6694 | -1.5101 | -1.7458 | 0.6022 | 0.2356 | -27.3766 | -25.8260 | 13.5776 | 13.5810 |
73
+ | 0.6217 | 0.59 | 600 | 0.6645 | -1.4050 | -1.6543 | 0.6110 | 0.2492 | -27.0716 | -25.4756 | 13.6337 | 13.6371 |
74
+ | 0.6186 | 0.64 | 650 | 0.6682 | -1.3826 | -1.6291 | 0.5978 | 0.2465 | -26.9876 | -25.4007 | 13.4204 | 13.4237 |
75
+ | 0.6637 | 0.68 | 700 | 0.6633 | -1.3994 | -1.6501 | 0.6220 | 0.2507 | -27.0576 | -25.4569 | 13.4574 | 13.4608 |
76
+ | 0.7482 | 0.73 | 750 | 0.6632 | -1.3772 | -1.6269 | 0.6198 | 0.2497 | -26.9804 | -25.3829 | 13.4047 | 13.4081 |
77
+ | 0.6597 | 0.78 | 800 | 0.6627 | -1.3970 | -1.6527 | 0.6198 | 0.2557 | -27.0664 | -25.4489 | 13.3914 | 13.3948 |
78
+ | 0.7206 | 0.83 | 850 | 0.6613 | -1.4018 | -1.6593 | 0.6220 | 0.2575 | -27.0885 | -25.4648 | 13.3862 | 13.3896 |
79
+ | 0.6715 | 0.88 | 900 | 0.6633 | -1.4047 | -1.6584 | 0.6220 | 0.2537 | -27.0856 | -25.4746 | 13.3969 | 13.4003 |
80
+ | 0.6108 | 0.93 | 950 | 0.6633 | -1.4042 | -1.6585 | 0.6242 | 0.2543 | -27.0857 | -25.4727 | 13.3883 | 13.3917 |
81
+ | 0.5964 | 0.98 | 1000 | 0.6641 | -1.4066 | -1.6576 | 0.6198 | 0.2510 | -27.0829 | -25.4808 | 13.3887 | 13.3921 |
82
 
83
 
84
  ### Framework versions
config.json CHANGED
@@ -1,26 +1,46 @@
1
  {
2
- "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
- "tie_word_embeddings": false,
 
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.39.1",
24
  "use_cache": false,
25
- "vocab_size": 32000
 
26
  }
 
1
  {
2
+ "_name_or_path": "mosaicml/mpt-7b-instruct",
3
  "architectures": [
4
+ "MptForCausalLM"
5
  ],
6
+ "attn_config": {
7
+ "model_type": ""
8
+ },
9
+ "auto_map": {
10
+ "AutoConfig": "mosaicml/mpt-7b-instruct--configuration_mpt.MPTConfig",
11
+ "AutoModelForCausalLM": "mosaicml/mpt-7b-instruct--modeling_mpt.MPTForCausalLM"
12
+ },
13
+ "d_model": 4096,
14
+ "emb_pdrop": 0,
15
+ "embedding_fraction": 1.0,
16
+ "expansion_ratio": 4,
17
+ "init_config": {
18
+ "emb_init_std": null,
19
+ "emb_init_uniform_lim": null,
20
+ "fan_mode": "fan_in",
21
+ "init_div_is_residual": true,
22
+ "init_gain": 0,
23
+ "init_nonlinearity": "relu",
24
+ "init_std": 0.02,
25
+ "name": "kaiming_normal_",
26
+ "verbose": 0
27
+ },
28
+ "init_device": "cpu",
29
  "initializer_range": 0.02,
30
+ "layer_norm_epsilon": 1e-05,
31
+ "learned_pos_emb": true,
32
+ "logit_scale": null,
33
+ "max_seq_len": 2048,
34
+ "model_type": "mpt",
35
+ "n_heads": 32,
36
+ "n_layers": 32,
37
+ "no_bias": true,
38
+ "norm_type": "low_precision_layernorm",
39
+ "resid_pdrop": 0,
40
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
41
  "torch_dtype": "float16",
42
  "transformers_version": "4.39.1",
43
  "use_cache": false,
44
+ "verbose": 0,
45
+ "vocab_size": 50432
46
  }
final_checkpoint/config.json CHANGED
@@ -1,26 +1,46 @@
1
  {
2
- "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "rms_norm_eps": 1e-05,
19
- "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
- "tie_word_embeddings": false,
 
22
  "torch_dtype": "float16",
23
  "transformers_version": "4.39.1",
24
  "use_cache": false,
25
- "vocab_size": 32000
 
26
  }
 
1
  {
2
+ "_name_or_path": "mosaicml/mpt-7b-instruct",
3
  "architectures": [
4
+ "MptForCausalLM"
5
  ],
6
+ "attn_config": {
7
+ "model_type": ""
8
+ },
9
+ "auto_map": {
10
+ "AutoConfig": "mosaicml/mpt-7b-instruct--configuration_mpt.MPTConfig",
11
+ "AutoModelForCausalLM": "mosaicml/mpt-7b-instruct--modeling_mpt.MPTForCausalLM"
12
+ },
13
+ "d_model": 4096,
14
+ "emb_pdrop": 0,
15
+ "embedding_fraction": 1.0,
16
+ "expansion_ratio": 4,
17
+ "init_config": {
18
+ "emb_init_std": null,
19
+ "emb_init_uniform_lim": null,
20
+ "fan_mode": "fan_in",
21
+ "init_div_is_residual": true,
22
+ "init_gain": 0,
23
+ "init_nonlinearity": "relu",
24
+ "init_std": 0.02,
25
+ "name": "kaiming_normal_",
26
+ "verbose": 0
27
+ },
28
+ "init_device": "cpu",
29
  "initializer_range": 0.02,
30
+ "layer_norm_epsilon": 1e-05,
31
+ "learned_pos_emb": true,
32
+ "logit_scale": null,
33
+ "max_seq_len": 2048,
34
+ "model_type": "mpt",
35
+ "n_heads": 32,
36
+ "n_layers": 32,
37
+ "no_bias": true,
38
+ "norm_type": "low_precision_layernorm",
39
+ "resid_pdrop": 0,
40
+ "tokenizer_name": "EleutherAI/gpt-neox-20b",
41
  "torch_dtype": "float16",
42
  "transformers_version": "4.39.1",
43
  "use_cache": false,
44
+ "verbose": 0,
45
+ "vocab_size": 50432
46
  }
final_checkpoint/generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.39.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "transformers_version": "4.39.1",
5
+ "use_cache": false
6
  }
final_checkpoint/model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24c2fee5f0076d795e1d2e566234ccadc4c0d14c80165d25ce332a7e3ca020c9
3
- size 4943162240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aef2d0bb5b9f576cd1873ec9de034fac83e25af00d50919492ddf51431a2114
3
+ size 4976746424
final_checkpoint/model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db1ad22f00f3fe464724da3116b00376748f9f9c2e53fc3bd1758472e5e73706
3
- size 4999819232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0494df8dc581f6d568140d4a3d0961d84abfc239aa2b155e682064f04e5b9ab7
3
+ size 2386755584
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.39.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "transformers_version": "4.39.1",
5
+ "use_cache": false
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24c2fee5f0076d795e1d2e566234ccadc4c0d14c80165d25ce332a7e3ca020c9
3
- size 4943162240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aef2d0bb5b9f576cd1873ec9de034fac83e25af00d50919492ddf51431a2114
3
+ size 4976746424
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db1ad22f00f3fe464724da3116b00376748f9f9c2e53fc3bd1758472e5e73706
3
- size 4999819232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14b36e78d8fb271835ecc916c45a4c949f6f210664b73a5a8118bdd8690949e0
3
+ size 4966260992
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:917200ffa3d6b6845f1707495e775c884a6bc1be4fef156dc3d383adebce1e63
3
- size 4540516256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8dd232e235e5190c9b5d9bb3080d51e9c2304e42dde3b47aea255f0e44f0b0b
3
+ size 3355588232
model.safetensors.index.json CHANGED
@@ -1,298 +1,201 @@
1
  {
2
  "metadata": {
3
- "total_size": 14483464192
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 13298573312
4
  },
5
  "weight_map": {
6
+ "transformer.blocks.0.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.blocks.0.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.blocks.0.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.blocks.0.norm_1.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.blocks.0.norm_2.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.blocks.1.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00003.safetensors",
14
+ "transformer.blocks.1.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.blocks.1.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.blocks.1.norm_1.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.blocks.1.norm_2.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.blocks.10.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.blocks.10.attn.out_proj.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.blocks.10.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.blocks.10.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.blocks.10.norm_1.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.blocks.10.norm_2.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.blocks.11.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
25
+ "transformer.blocks.11.attn.out_proj.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.blocks.11.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
27
+ "transformer.blocks.11.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
28
+ "transformer.blocks.11.norm_1.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.blocks.11.norm_2.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.blocks.12.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
31
+ "transformer.blocks.12.attn.out_proj.weight": "model-00002-of-00003.safetensors",
32
+ "transformer.blocks.12.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
33
+ "transformer.blocks.12.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
34
+ "transformer.blocks.12.norm_1.weight": "model-00002-of-00003.safetensors",
35
+ "transformer.blocks.12.norm_2.weight": "model-00002-of-00003.safetensors",
36
+ "transformer.blocks.13.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
37
+ "transformer.blocks.13.attn.out_proj.weight": "model-00002-of-00003.safetensors",
38
+ "transformer.blocks.13.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
39
+ "transformer.blocks.13.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
40
+ "transformer.blocks.13.norm_1.weight": "model-00002-of-00003.safetensors",
41
+ "transformer.blocks.13.norm_2.weight": "model-00002-of-00003.safetensors",
42
+ "transformer.blocks.14.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
43
+ "transformer.blocks.14.attn.out_proj.weight": "model-00002-of-00003.safetensors",
44
+ "transformer.blocks.14.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
45
+ "transformer.blocks.14.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
46
+ "transformer.blocks.14.norm_1.weight": "model-00002-of-00003.safetensors",
47
+ "transformer.blocks.14.norm_2.weight": "model-00002-of-00003.safetensors",
48
+ "transformer.blocks.15.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
49
+ "transformer.blocks.15.attn.out_proj.weight": "model-00002-of-00003.safetensors",
50
+ "transformer.blocks.15.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
51
+ "transformer.blocks.15.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
52
+ "transformer.blocks.15.norm_1.weight": "model-00002-of-00003.safetensors",
53
+ "transformer.blocks.15.norm_2.weight": "model-00002-of-00003.safetensors",
54
+ "transformer.blocks.16.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
55
+ "transformer.blocks.16.attn.out_proj.weight": "model-00002-of-00003.safetensors",
56
+ "transformer.blocks.16.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
57
+ "transformer.blocks.16.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
58
+ "transformer.blocks.16.norm_1.weight": "model-00002-of-00003.safetensors",
59
+ "transformer.blocks.16.norm_2.weight": "model-00002-of-00003.safetensors",
60
+ "transformer.blocks.17.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
61
+ "transformer.blocks.17.attn.out_proj.weight": "model-00002-of-00003.safetensors",
62
+ "transformer.blocks.17.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
63
+ "transformer.blocks.17.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
64
+ "transformer.blocks.17.norm_1.weight": "model-00002-of-00003.safetensors",
65
+ "transformer.blocks.17.norm_2.weight": "model-00002-of-00003.safetensors",
66
+ "transformer.blocks.18.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
67
+ "transformer.blocks.18.attn.out_proj.weight": "model-00002-of-00003.safetensors",
68
+ "transformer.blocks.18.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
69
+ "transformer.blocks.18.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
70
+ "transformer.blocks.18.norm_1.weight": "model-00002-of-00003.safetensors",
71
+ "transformer.blocks.18.norm_2.weight": "model-00002-of-00003.safetensors",
72
+ "transformer.blocks.19.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
73
+ "transformer.blocks.19.attn.out_proj.weight": "model-00002-of-00003.safetensors",
74
+ "transformer.blocks.19.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
75
+ "transformer.blocks.19.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
76
+ "transformer.blocks.19.norm_1.weight": "model-00002-of-00003.safetensors",
77
+ "transformer.blocks.19.norm_2.weight": "model-00002-of-00003.safetensors",
78
+ "transformer.blocks.2.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
79
+ "transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.blocks.2.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
81
+ "transformer.blocks.2.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.blocks.2.norm_1.weight": "model-00001-of-00003.safetensors",
83
+ "transformer.blocks.2.norm_2.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.blocks.20.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
85
+ "transformer.blocks.20.attn.out_proj.weight": "model-00002-of-00003.safetensors",
86
+ "transformer.blocks.20.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.blocks.20.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.blocks.20.norm_1.weight": "model-00002-of-00003.safetensors",
89
+ "transformer.blocks.20.norm_2.weight": "model-00002-of-00003.safetensors",
90
+ "transformer.blocks.21.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
91
+ "transformer.blocks.21.attn.out_proj.weight": "model-00002-of-00003.safetensors",
92
+ "transformer.blocks.21.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.blocks.21.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
94
+ "transformer.blocks.21.norm_1.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.blocks.21.norm_2.weight": "model-00002-of-00003.safetensors",
96
+ "transformer.blocks.22.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.blocks.22.attn.out_proj.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.blocks.22.ffn.down_proj.weight": "model-00002-of-00003.safetensors",
99
+ "transformer.blocks.22.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.blocks.22.norm_1.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.blocks.22.norm_2.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.blocks.23.attn.Wqkv.weight": "model-00002-of-00003.safetensors",
103
+ "transformer.blocks.23.attn.out_proj.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.blocks.23.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
105
+ "transformer.blocks.23.ffn.up_proj.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.blocks.23.norm_1.weight": "model-00002-of-00003.safetensors",
107
+ "transformer.blocks.23.norm_2.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.blocks.24.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
109
+ "transformer.blocks.24.attn.out_proj.weight": "model-00003-of-00003.safetensors",
110
+ "transformer.blocks.24.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
111
+ "transformer.blocks.24.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
112
+ "transformer.blocks.24.norm_1.weight": "model-00003-of-00003.safetensors",
113
+ "transformer.blocks.24.norm_2.weight": "model-00003-of-00003.safetensors",
114
+ "transformer.blocks.25.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
115
+ "transformer.blocks.25.attn.out_proj.weight": "model-00003-of-00003.safetensors",
116
+ "transformer.blocks.25.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
117
+ "transformer.blocks.25.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
118
+ "transformer.blocks.25.norm_1.weight": "model-00003-of-00003.safetensors",
119
+ "transformer.blocks.25.norm_2.weight": "model-00003-of-00003.safetensors",
120
+ "transformer.blocks.26.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
121
+ "transformer.blocks.26.attn.out_proj.weight": "model-00003-of-00003.safetensors",
122
+ "transformer.blocks.26.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
123
+ "transformer.blocks.26.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
124
+ "transformer.blocks.26.norm_1.weight": "model-00003-of-00003.safetensors",
125
+ "transformer.blocks.26.norm_2.weight": "model-00003-of-00003.safetensors",
126
+ "transformer.blocks.27.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
127
+ "transformer.blocks.27.attn.out_proj.weight": "model-00003-of-00003.safetensors",
128
+ "transformer.blocks.27.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
129
+ "transformer.blocks.27.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
130
+ "transformer.blocks.27.norm_1.weight": "model-00003-of-00003.safetensors",
131
+ "transformer.blocks.27.norm_2.weight": "model-00003-of-00003.safetensors",
132
+ "transformer.blocks.28.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
133
+ "transformer.blocks.28.attn.out_proj.weight": "model-00003-of-00003.safetensors",
134
+ "transformer.blocks.28.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
135
+ "transformer.blocks.28.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
136
+ "transformer.blocks.28.norm_1.weight": "model-00003-of-00003.safetensors",
137
+ "transformer.blocks.28.norm_2.weight": "model-00003-of-00003.safetensors",
138
+ "transformer.blocks.29.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
139
+ "transformer.blocks.29.attn.out_proj.weight": "model-00003-of-00003.safetensors",
140
+ "transformer.blocks.29.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
141
+ "transformer.blocks.29.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
142
+ "transformer.blocks.29.norm_1.weight": "model-00003-of-00003.safetensors",
143
+ "transformer.blocks.29.norm_2.weight": "model-00003-of-00003.safetensors",
144
+ "transformer.blocks.3.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
145
+ "transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00003.safetensors",
146
+ "transformer.blocks.3.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
147
+ "transformer.blocks.3.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
148
+ "transformer.blocks.3.norm_1.weight": "model-00001-of-00003.safetensors",
149
+ "transformer.blocks.3.norm_2.weight": "model-00001-of-00003.safetensors",
150
+ "transformer.blocks.30.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
151
+ "transformer.blocks.30.attn.out_proj.weight": "model-00003-of-00003.safetensors",
152
+ "transformer.blocks.30.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
153
+ "transformer.blocks.30.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
154
+ "transformer.blocks.30.norm_1.weight": "model-00003-of-00003.safetensors",
155
+ "transformer.blocks.30.norm_2.weight": "model-00003-of-00003.safetensors",
156
+ "transformer.blocks.31.attn.Wqkv.weight": "model-00003-of-00003.safetensors",
157
+ "transformer.blocks.31.attn.out_proj.weight": "model-00003-of-00003.safetensors",
158
+ "transformer.blocks.31.ffn.down_proj.weight": "model-00003-of-00003.safetensors",
159
+ "transformer.blocks.31.ffn.up_proj.weight": "model-00003-of-00003.safetensors",
160
+ "transformer.blocks.31.norm_1.weight": "model-00003-of-00003.safetensors",
161
+ "transformer.blocks.31.norm_2.weight": "model-00003-of-00003.safetensors",
162
+ "transformer.blocks.4.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
163
+ "transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00003.safetensors",
164
+ "transformer.blocks.4.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.blocks.4.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.blocks.4.norm_1.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.blocks.4.norm_2.weight": "model-00001-of-00003.safetensors",
168
+ "transformer.blocks.5.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
169
+ "transformer.blocks.5.attn.out_proj.weight": "model-00001-of-00003.safetensors",
170
+ "transformer.blocks.5.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.blocks.5.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
172
+ "transformer.blocks.5.norm_1.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.blocks.5.norm_2.weight": "model-00001-of-00003.safetensors",
174
+ "transformer.blocks.6.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
175
+ "transformer.blocks.6.attn.out_proj.weight": "model-00001-of-00003.safetensors",
176
+ "transformer.blocks.6.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
177
+ "transformer.blocks.6.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
178
+ "transformer.blocks.6.norm_1.weight": "model-00001-of-00003.safetensors",
179
+ "transformer.blocks.6.norm_2.weight": "model-00001-of-00003.safetensors",
180
+ "transformer.blocks.7.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
181
+ "transformer.blocks.7.attn.out_proj.weight": "model-00001-of-00003.safetensors",
182
+ "transformer.blocks.7.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
183
+ "transformer.blocks.7.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
184
+ "transformer.blocks.7.norm_1.weight": "model-00001-of-00003.safetensors",
185
+ "transformer.blocks.7.norm_2.weight": "model-00001-of-00003.safetensors",
186
+ "transformer.blocks.8.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
187
+ "transformer.blocks.8.attn.out_proj.weight": "model-00001-of-00003.safetensors",
188
+ "transformer.blocks.8.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
189
+ "transformer.blocks.8.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
190
+ "transformer.blocks.8.norm_1.weight": "model-00001-of-00003.safetensors",
191
+ "transformer.blocks.8.norm_2.weight": "model-00001-of-00003.safetensors",
192
+ "transformer.blocks.9.attn.Wqkv.weight": "model-00001-of-00003.safetensors",
193
+ "transformer.blocks.9.attn.out_proj.weight": "model-00001-of-00003.safetensors",
194
+ "transformer.blocks.9.ffn.down_proj.weight": "model-00001-of-00003.safetensors",
195
+ "transformer.blocks.9.ffn.up_proj.weight": "model-00001-of-00003.safetensors",
196
+ "transformer.blocks.9.norm_1.weight": "model-00001-of-00003.safetensors",
197
+ "transformer.blocks.9.norm_2.weight": "model-00001-of-00003.safetensors",
198
+ "transformer.norm_f.weight": "model-00003-of-00003.safetensors",
199
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
200
  }
201
  }
special_tokens_map.json CHANGED
@@ -1,21 +1,21 @@
1
  {
2
  "bos_token": {
3
- "content": "<s>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "</s>",
17
  "unk_token": {
18
- "content": "<unk>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,9 +1,8 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
- "content": "<unk>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
@@ -11,33 +10,203 @@
11
  "special": true
12
  },
13
  "1": {
14
- "content": "<s>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
- "2": {
22
- "content": "</s>",
23
  "lstrip": false,
24
- "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
- "additional_special_tokens": [],
31
- "bos_token": "<s>",
32
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
- "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
- "legacy": true,
36
- "model_max_length": 1000000000000000019884624838656,
37
- "pad_token": "</s>",
38
- "sp_model_kwargs": {},
39
- "spaces_between_special_tokens": false,
40
- "tokenizer_class": "LlamaTokenizer",
41
- "unk_token": "<unk>",
42
- "use_default_system_prompt": false
43
  }
 
1
  {
2
+ "add_prefix_space": false,
 
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
 
10
  "special": true
11
  },
12
  "1": {
13
+ "content": "<|padding|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "50254": {
21
+ "content": " ",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
  }
204
  },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "model_max_length": 2048,
209
+ "pad_token": "<|endoftext|>",
210
+ "tokenizer_class": "GPTNeoXTokenizer",
211
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
212
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab87f356e42dafed061e95415a2fec2d2467604663a2ab3281cc53ad51cedba1
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a468d1102d1d9c46447bce3b5a0a66d05ed25a247c1bee457c1a3971d444fa
3
  size 4475