Upload folder using huggingface_hub
Browse files- config.json +56 -0
- generation_config.json +6 -0
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +202 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +215 -0
config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MptForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attn_config": {
|
| 6 |
+
"alibi": true,
|
| 7 |
+
"alibi_bias_max": 8,
|
| 8 |
+
"attn_impl": "torch",
|
| 9 |
+
"attn_pdrop": 0,
|
| 10 |
+
"attn_type": "multihead_attention",
|
| 11 |
+
"attn_uses_sequence_id": false,
|
| 12 |
+
"clip_qkv": null,
|
| 13 |
+
"dtype": "float32",
|
| 14 |
+
"model_type": "",
|
| 15 |
+
"prefix_lm": false,
|
| 16 |
+
"qk_ln": false,
|
| 17 |
+
"softmax_scale": null
|
| 18 |
+
},
|
| 19 |
+
"auto_map": {
|
| 20 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
| 21 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
| 22 |
+
},
|
| 23 |
+
"d_model": 4096,
|
| 24 |
+
"dtype": "float32",
|
| 25 |
+
"emb_pdrop": 0,
|
| 26 |
+
"embedding_fraction": 1.0,
|
| 27 |
+
"expansion_ratio": 4,
|
| 28 |
+
"init_config": {
|
| 29 |
+
"emb_init_std": null,
|
| 30 |
+
"emb_init_uniform_lim": null,
|
| 31 |
+
"fan_mode": "fan_in",
|
| 32 |
+
"init_div_is_residual": true,
|
| 33 |
+
"init_gain": 0,
|
| 34 |
+
"init_nonlinearity": "relu",
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"name": "kaiming_normal_",
|
| 37 |
+
"verbose": 0
|
| 38 |
+
},
|
| 39 |
+
"init_device": "cpu",
|
| 40 |
+
"initializer_range": 0.02,
|
| 41 |
+
"layer_norm_epsilon": 1e-05,
|
| 42 |
+
"learned_pos_emb": true,
|
| 43 |
+
"logit_scale": null,
|
| 44 |
+
"max_seq_len": 2048,
|
| 45 |
+
"model_type": "mpt",
|
| 46 |
+
"n_heads": 32,
|
| 47 |
+
"n_layers": 32,
|
| 48 |
+
"no_bias": true,
|
| 49 |
+
"norm_type": "low_precision_layernorm",
|
| 50 |
+
"resid_pdrop": 0,
|
| 51 |
+
"tokenizer_name": "EleutherAI/gpt-neox-20b",
|
| 52 |
+
"transformers_version": "4.57.1",
|
| 53 |
+
"use_cache": false,
|
| 54 |
+
"verbose": 0,
|
| 55 |
+
"vocab_size": 50432
|
| 56 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 0,
|
| 4 |
+
"transformers_version": "4.57.1",
|
| 5 |
+
"use_cache": false
|
| 6 |
+
}
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f7c37ba572e91af1d644fb4d01daec97508d625c4f5b9100113cf54ffd79cb3
|
| 3 |
+
size 4852993616
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94e98ff04165b5bc67e983684112690465ac36714f7cf4c6fc880a7dbade009c
|
| 3 |
+
size 4832038968
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3a2fe766c89bec0f29f87f8d72f2c74159f1623671efebc7470526159f74090
|
| 3 |
+
size 4832039000
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5febb0f2ea629fa2bb33de68d09d2df5374136ea390839a652aa3a14d0e49a1
|
| 3 |
+
size 4832039000
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:034c23ee98e8a2e592901d911def4e5d110d163ea4ba03a3f6b1c8ad0dd39535
|
| 3 |
+
size 4832039000
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db2803c8946e7977efe98d119d9e90fab85ea6e7345f7ef11a66c264e767ea48
|
| 3 |
+
size 2416019504
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 6649286656,
|
| 4 |
+
"total_size": 26597146624
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"transformer.blocks.0.attn.Wqkv.weight": "model-00001-of-00006.safetensors",
|
| 8 |
+
"transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 9 |
+
"transformer.blocks.0.ffn.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 10 |
+
"transformer.blocks.0.ffn.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 11 |
+
"transformer.blocks.0.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 12 |
+
"transformer.blocks.0.norm_2.weight": "model-00001-of-00006.safetensors",
|
| 13 |
+
"transformer.blocks.1.attn.Wqkv.weight": "model-00001-of-00006.safetensors",
|
| 14 |
+
"transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 15 |
+
"transformer.blocks.1.ffn.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 16 |
+
"transformer.blocks.1.ffn.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 17 |
+
"transformer.blocks.1.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 18 |
+
"transformer.blocks.1.norm_2.weight": "model-00001-of-00006.safetensors",
|
| 19 |
+
"transformer.blocks.10.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 20 |
+
"transformer.blocks.10.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 21 |
+
"transformer.blocks.10.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 22 |
+
"transformer.blocks.10.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 23 |
+
"transformer.blocks.10.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 24 |
+
"transformer.blocks.10.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 25 |
+
"transformer.blocks.11.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 26 |
+
"transformer.blocks.11.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 27 |
+
"transformer.blocks.11.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 28 |
+
"transformer.blocks.11.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 29 |
+
"transformer.blocks.11.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 30 |
+
"transformer.blocks.11.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 31 |
+
"transformer.blocks.12.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 32 |
+
"transformer.blocks.12.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 33 |
+
"transformer.blocks.12.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 34 |
+
"transformer.blocks.12.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 35 |
+
"transformer.blocks.12.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 36 |
+
"transformer.blocks.12.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 37 |
+
"transformer.blocks.13.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 38 |
+
"transformer.blocks.13.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 39 |
+
"transformer.blocks.13.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 40 |
+
"transformer.blocks.13.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 41 |
+
"transformer.blocks.13.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 42 |
+
"transformer.blocks.13.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 43 |
+
"transformer.blocks.14.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 44 |
+
"transformer.blocks.14.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 45 |
+
"transformer.blocks.14.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 46 |
+
"transformer.blocks.14.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 47 |
+
"transformer.blocks.14.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 48 |
+
"transformer.blocks.14.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 49 |
+
"transformer.blocks.15.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 50 |
+
"transformer.blocks.15.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 51 |
+
"transformer.blocks.15.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 52 |
+
"transformer.blocks.15.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 53 |
+
"transformer.blocks.15.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 54 |
+
"transformer.blocks.15.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 55 |
+
"transformer.blocks.16.attn.Wqkv.weight": "model-00003-of-00006.safetensors",
|
| 56 |
+
"transformer.blocks.16.attn.out_proj.weight": "model-00003-of-00006.safetensors",
|
| 57 |
+
"transformer.blocks.16.ffn.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 58 |
+
"transformer.blocks.16.ffn.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 59 |
+
"transformer.blocks.16.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 60 |
+
"transformer.blocks.16.norm_2.weight": "model-00003-of-00006.safetensors",
|
| 61 |
+
"transformer.blocks.17.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 62 |
+
"transformer.blocks.17.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 63 |
+
"transformer.blocks.17.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 64 |
+
"transformer.blocks.17.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 65 |
+
"transformer.blocks.17.norm_1.weight": "model-00003-of-00006.safetensors",
|
| 66 |
+
"transformer.blocks.17.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 67 |
+
"transformer.blocks.18.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 68 |
+
"transformer.blocks.18.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 69 |
+
"transformer.blocks.18.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 70 |
+
"transformer.blocks.18.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 71 |
+
"transformer.blocks.18.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 72 |
+
"transformer.blocks.18.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 73 |
+
"transformer.blocks.19.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 74 |
+
"transformer.blocks.19.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 75 |
+
"transformer.blocks.19.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 76 |
+
"transformer.blocks.19.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 77 |
+
"transformer.blocks.19.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 78 |
+
"transformer.blocks.19.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 79 |
+
"transformer.blocks.2.attn.Wqkv.weight": "model-00001-of-00006.safetensors",
|
| 80 |
+
"transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 81 |
+
"transformer.blocks.2.ffn.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 82 |
+
"transformer.blocks.2.ffn.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 83 |
+
"transformer.blocks.2.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 84 |
+
"transformer.blocks.2.norm_2.weight": "model-00001-of-00006.safetensors",
|
| 85 |
+
"transformer.blocks.20.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 86 |
+
"transformer.blocks.20.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 87 |
+
"transformer.blocks.20.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 88 |
+
"transformer.blocks.20.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 89 |
+
"transformer.blocks.20.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 90 |
+
"transformer.blocks.20.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 91 |
+
"transformer.blocks.21.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 92 |
+
"transformer.blocks.21.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 93 |
+
"transformer.blocks.21.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 94 |
+
"transformer.blocks.21.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 95 |
+
"transformer.blocks.21.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 96 |
+
"transformer.blocks.21.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 97 |
+
"transformer.blocks.22.attn.Wqkv.weight": "model-00004-of-00006.safetensors",
|
| 98 |
+
"transformer.blocks.22.attn.out_proj.weight": "model-00004-of-00006.safetensors",
|
| 99 |
+
"transformer.blocks.22.ffn.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 100 |
+
"transformer.blocks.22.ffn.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 101 |
+
"transformer.blocks.22.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 102 |
+
"transformer.blocks.22.norm_2.weight": "model-00004-of-00006.safetensors",
|
| 103 |
+
"transformer.blocks.23.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 104 |
+
"transformer.blocks.23.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 105 |
+
"transformer.blocks.23.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 106 |
+
"transformer.blocks.23.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 107 |
+
"transformer.blocks.23.norm_1.weight": "model-00004-of-00006.safetensors",
|
| 108 |
+
"transformer.blocks.23.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 109 |
+
"transformer.blocks.24.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 110 |
+
"transformer.blocks.24.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 111 |
+
"transformer.blocks.24.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 112 |
+
"transformer.blocks.24.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 113 |
+
"transformer.blocks.24.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 114 |
+
"transformer.blocks.24.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 115 |
+
"transformer.blocks.25.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 116 |
+
"transformer.blocks.25.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 117 |
+
"transformer.blocks.25.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 118 |
+
"transformer.blocks.25.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 119 |
+
"transformer.blocks.25.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 120 |
+
"transformer.blocks.25.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 121 |
+
"transformer.blocks.26.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 122 |
+
"transformer.blocks.26.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 123 |
+
"transformer.blocks.26.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 124 |
+
"transformer.blocks.26.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 125 |
+
"transformer.blocks.26.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 126 |
+
"transformer.blocks.26.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 127 |
+
"transformer.blocks.27.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 128 |
+
"transformer.blocks.27.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 129 |
+
"transformer.blocks.27.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 130 |
+
"transformer.blocks.27.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 131 |
+
"transformer.blocks.27.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 132 |
+
"transformer.blocks.27.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 133 |
+
"transformer.blocks.28.attn.Wqkv.weight": "model-00005-of-00006.safetensors",
|
| 134 |
+
"transformer.blocks.28.attn.out_proj.weight": "model-00005-of-00006.safetensors",
|
| 135 |
+
"transformer.blocks.28.ffn.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 136 |
+
"transformer.blocks.28.ffn.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 137 |
+
"transformer.blocks.28.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 138 |
+
"transformer.blocks.28.norm_2.weight": "model-00005-of-00006.safetensors",
|
| 139 |
+
"transformer.blocks.29.attn.Wqkv.weight": "model-00006-of-00006.safetensors",
|
| 140 |
+
"transformer.blocks.29.attn.out_proj.weight": "model-00006-of-00006.safetensors",
|
| 141 |
+
"transformer.blocks.29.ffn.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 142 |
+
"transformer.blocks.29.ffn.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 143 |
+
"transformer.blocks.29.norm_1.weight": "model-00005-of-00006.safetensors",
|
| 144 |
+
"transformer.blocks.29.norm_2.weight": "model-00006-of-00006.safetensors",
|
| 145 |
+
"transformer.blocks.3.attn.Wqkv.weight": "model-00001-of-00006.safetensors",
|
| 146 |
+
"transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 147 |
+
"transformer.blocks.3.ffn.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 148 |
+
"transformer.blocks.3.ffn.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 149 |
+
"transformer.blocks.3.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 150 |
+
"transformer.blocks.3.norm_2.weight": "model-00001-of-00006.safetensors",
|
| 151 |
+
"transformer.blocks.30.attn.Wqkv.weight": "model-00006-of-00006.safetensors",
|
| 152 |
+
"transformer.blocks.30.attn.out_proj.weight": "model-00006-of-00006.safetensors",
|
| 153 |
+
"transformer.blocks.30.ffn.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 154 |
+
"transformer.blocks.30.ffn.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 155 |
+
"transformer.blocks.30.norm_1.weight": "model-00006-of-00006.safetensors",
|
| 156 |
+
"transformer.blocks.30.norm_2.weight": "model-00006-of-00006.safetensors",
|
| 157 |
+
"transformer.blocks.31.attn.Wqkv.weight": "model-00006-of-00006.safetensors",
|
| 158 |
+
"transformer.blocks.31.attn.out_proj.weight": "model-00006-of-00006.safetensors",
|
| 159 |
+
"transformer.blocks.31.ffn.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 160 |
+
"transformer.blocks.31.ffn.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 161 |
+
"transformer.blocks.31.norm_1.weight": "model-00006-of-00006.safetensors",
|
| 162 |
+
"transformer.blocks.31.norm_2.weight": "model-00006-of-00006.safetensors",
|
| 163 |
+
"transformer.blocks.4.attn.Wqkv.weight": "model-00001-of-00006.safetensors",
|
| 164 |
+
"transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00006.safetensors",
|
| 165 |
+
"transformer.blocks.4.ffn.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 166 |
+
"transformer.blocks.4.ffn.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 167 |
+
"transformer.blocks.4.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 168 |
+
"transformer.blocks.4.norm_2.weight": "model-00001-of-00006.safetensors",
|
| 169 |
+
"transformer.blocks.5.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 170 |
+
"transformer.blocks.5.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 171 |
+
"transformer.blocks.5.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 172 |
+
"transformer.blocks.5.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 173 |
+
"transformer.blocks.5.norm_1.weight": "model-00001-of-00006.safetensors",
|
| 174 |
+
"transformer.blocks.5.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 175 |
+
"transformer.blocks.6.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 176 |
+
"transformer.blocks.6.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 177 |
+
"transformer.blocks.6.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 178 |
+
"transformer.blocks.6.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 179 |
+
"transformer.blocks.6.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 180 |
+
"transformer.blocks.6.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 181 |
+
"transformer.blocks.7.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 182 |
+
"transformer.blocks.7.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 183 |
+
"transformer.blocks.7.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 184 |
+
"transformer.blocks.7.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 185 |
+
"transformer.blocks.7.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 186 |
+
"transformer.blocks.7.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 187 |
+
"transformer.blocks.8.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 188 |
+
"transformer.blocks.8.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 189 |
+
"transformer.blocks.8.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 190 |
+
"transformer.blocks.8.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 191 |
+
"transformer.blocks.8.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 192 |
+
"transformer.blocks.8.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 193 |
+
"transformer.blocks.9.attn.Wqkv.weight": "model-00002-of-00006.safetensors",
|
| 194 |
+
"transformer.blocks.9.attn.out_proj.weight": "model-00002-of-00006.safetensors",
|
| 195 |
+
"transformer.blocks.9.ffn.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 196 |
+
"transformer.blocks.9.ffn.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 197 |
+
"transformer.blocks.9.norm_1.weight": "model-00002-of-00006.safetensors",
|
| 198 |
+
"transformer.blocks.9.norm_2.weight": "model-00002-of-00006.safetensors",
|
| 199 |
+
"transformer.norm_f.weight": "model-00006-of-00006.safetensors",
|
| 200 |
+
"transformer.wte.weight": "model-00001-of-00006.safetensors"
|
| 201 |
+
}
|
| 202 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"clean_up_tokenization_spaces": true,
|
| 209 |
+
"eos_token": "<|endoftext|>",
|
| 210 |
+
"extra_special_tokens": {},
|
| 211 |
+
"model_max_length": 2048,
|
| 212 |
+
"pad_token": null,
|
| 213 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 214 |
+
"unk_token": "<|endoftext|>"
|
| 215 |
+
}
|