ybelkada/falcon-7b-sharded-bf16
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: ybelkada/falcon-7b-sharded-bf16
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-28 21:41:01 +08:00
commit 1d4e74bfc6
24 changed files with 130513 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -0,0 +1,34 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

25
config.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "tiiuae/falcon-7b",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"FalconForCausalLM"
],
"attention_dropout": 0.0,
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 4544,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "falcon",
"multi_query": true,
"n_head": 71,
"n_layer": 32,
"parallel_attn": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.30.0.dev0",
"use_cache": true,
"vocab_size": 65024
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.30.0.dev0"
}

3
model-00001-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:256586f41e894087ca3b02830874f02cfe93b95566b17c4f93d4e63c7f188502
size 1917134504

3
model-00002-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa1e17ea4569d52e86c8ac4db4cd5b73af15954b133adf8ffb3d44f5c00296f5
size 1986949128

3
model-00003-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c9730b1c37671eab931db772ab8d6dc36eb0e136fad27a3e858e65c7c481cd15
size 1905502376

3
model-00004-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02d890951f7f34723009796a6a2cd6f10311dd0c0b72a914fb8749dc7bd8316a
size 1905520808

3
model-00005-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a49cc2958d851e0a13fed56073df3ed987a1b1130af74047653c7fbb701ea0d0
size 1986949160

3
model-00006-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f7a41129382c2aaeb800d551ec655b7c09b2211bd8d03c640c932163deed162b
size 1905502408

3
model-00007-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9443bfbbf8ebb44b0fb84f579c509134fb555353b3d90cb8ea0cf7943e3160ec
size 1905520808

3
model-00008-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b671c8df63598a21bdf2432bb8934a639bfcafc8be68a9965b58fa24d7daf6d
size 921323816

203
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,203 @@
{
"metadata": {
"total_size": 14434379520
},
"weight_map": {
"lm_head.weight": "model-00008-of-00008.safetensors",
"transformer.h.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
"transformer.h.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
"transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
"transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
"transformer.h.0.self_attention.dense.weight": "model-00001-of-00008.safetensors",
"transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
"transformer.h.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
"transformer.h.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
"transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
"transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
"transformer.h.1.self_attention.dense.weight": "model-00001-of-00008.safetensors",
"transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
"transformer.h.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
"transformer.h.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
"transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"transformer.h.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"transformer.h.10.self_attention.dense.weight": "model-00003-of-00008.safetensors",
"transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
"transformer.h.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
"transformer.h.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
"transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"transformer.h.11.self_attention.dense.weight": "model-00003-of-00008.safetensors",
"transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
"transformer.h.12.input_layernorm.bias": "model-00003-of-00008.safetensors",
"transformer.h.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
"transformer.h.12.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"transformer.h.12.self_attention.dense.weight": "model-00003-of-00008.safetensors",
"transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
"transformer.h.13.input_layernorm.bias": "model-00004-of-00008.safetensors",
"transformer.h.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
"transformer.h.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"transformer.h.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"transformer.h.13.self_attention.dense.weight": "model-00004-of-00008.safetensors",
"transformer.h.13.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
"transformer.h.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
"transformer.h.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
"transformer.h.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"transformer.h.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"transformer.h.14.self_attention.dense.weight": "model-00004-of-00008.safetensors",
"transformer.h.14.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
"transformer.h.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
"transformer.h.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
"transformer.h.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"transformer.h.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"transformer.h.15.self_attention.dense.weight": "model-00004-of-00008.safetensors",
"transformer.h.15.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
"transformer.h.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
"transformer.h.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
"transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
"transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
"transformer.h.16.self_attention.dense.weight": "model-00004-of-00008.safetensors",
"transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
"transformer.h.17.input_layernorm.bias": "model-00004-of-00008.safetensors",
"transformer.h.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
"transformer.h.17.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"transformer.h.17.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"transformer.h.17.self_attention.dense.weight": "model-00004-of-00008.safetensors",
"transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
"transformer.h.18.input_layernorm.bias": "model-00005-of-00008.safetensors",
"transformer.h.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
"transformer.h.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"transformer.h.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"transformer.h.18.self_attention.dense.weight": "model-00005-of-00008.safetensors",
"transformer.h.18.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
"transformer.h.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
"transformer.h.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
"transformer.h.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"transformer.h.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"transformer.h.19.self_attention.dense.weight": "model-00005-of-00008.safetensors",
"transformer.h.19.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
"transformer.h.2.input_layernorm.bias": "model-00001-of-00008.safetensors",
"transformer.h.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
"transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
"transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
"transformer.h.2.self_attention.dense.weight": "model-00001-of-00008.safetensors",
"transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
"transformer.h.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
"transformer.h.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
"transformer.h.20.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"transformer.h.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"transformer.h.20.self_attention.dense.weight": "model-00005-of-00008.safetensors",
"transformer.h.20.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
"transformer.h.21.input_layernorm.bias": "model-00005-of-00008.safetensors",
"transformer.h.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
"transformer.h.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
"transformer.h.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
"transformer.h.21.self_attention.dense.weight": "model-00005-of-00008.safetensors",
"transformer.h.21.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
"transformer.h.22.input_layernorm.bias": "model-00005-of-00008.safetensors",
"transformer.h.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
"transformer.h.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"transformer.h.22.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"transformer.h.22.self_attention.dense.weight": "model-00006-of-00008.safetensors",
"transformer.h.22.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
"transformer.h.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
"transformer.h.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
"transformer.h.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"transformer.h.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"transformer.h.23.self_attention.dense.weight": "model-00006-of-00008.safetensors",
"transformer.h.23.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
"transformer.h.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
"transformer.h.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
"transformer.h.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"transformer.h.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"transformer.h.24.self_attention.dense.weight": "model-00006-of-00008.safetensors",
"transformer.h.24.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
"transformer.h.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
"transformer.h.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
"transformer.h.25.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
"transformer.h.25.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"transformer.h.25.self_attention.dense.weight": "model-00006-of-00008.safetensors",
"transformer.h.25.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
"transformer.h.26.input_layernorm.bias": "model-00006-of-00008.safetensors",
"transformer.h.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
"transformer.h.26.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"transformer.h.26.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
"transformer.h.26.self_attention.dense.weight": "model-00006-of-00008.safetensors",
"transformer.h.26.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
"transformer.h.27.input_layernorm.bias": "model-00007-of-00008.safetensors",
"transformer.h.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
"transformer.h.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"transformer.h.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"transformer.h.27.self_attention.dense.weight": "model-00007-of-00008.safetensors",
"transformer.h.27.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
"transformer.h.28.input_layernorm.bias": "model-00007-of-00008.safetensors",
"transformer.h.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
"transformer.h.28.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"transformer.h.28.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"transformer.h.28.self_attention.dense.weight": "model-00007-of-00008.safetensors",
"transformer.h.28.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
"transformer.h.29.input_layernorm.bias": "model-00007-of-00008.safetensors",
"transformer.h.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
"transformer.h.29.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"transformer.h.29.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"transformer.h.29.self_attention.dense.weight": "model-00007-of-00008.safetensors",
"transformer.h.29.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
"transformer.h.3.input_layernorm.bias": "model-00001-of-00008.safetensors",
"transformer.h.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
"transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"transformer.h.3.self_attention.dense.weight": "model-00001-of-00008.safetensors",
"transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
"transformer.h.30.input_layernorm.bias": "model-00007-of-00008.safetensors",
"transformer.h.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
"transformer.h.30.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
"transformer.h.30.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
"transformer.h.30.self_attention.dense.weight": "model-00007-of-00008.safetensors",
"transformer.h.30.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
"transformer.h.31.input_layernorm.bias": "model-00007-of-00008.safetensors",
"transformer.h.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
"transformer.h.31.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
"transformer.h.31.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
"transformer.h.31.self_attention.dense.weight": "model-00007-of-00008.safetensors",
"transformer.h.31.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
"transformer.h.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
"transformer.h.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
"transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"transformer.h.4.self_attention.dense.weight": "model-00002-of-00008.safetensors",
"transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
"transformer.h.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
"transformer.h.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
"transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"transformer.h.5.self_attention.dense.weight": "model-00002-of-00008.safetensors",
"transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
"transformer.h.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
"transformer.h.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
"transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"transformer.h.6.self_attention.dense.weight": "model-00002-of-00008.safetensors",
"transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
"transformer.h.7.input_layernorm.bias": "model-00002-of-00008.safetensors",
"transformer.h.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
"transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
"transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
"transformer.h.7.self_attention.dense.weight": "model-00002-of-00008.safetensors",
"transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
"transformer.h.8.input_layernorm.bias": "model-00002-of-00008.safetensors",
"transformer.h.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
"transformer.h.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"transformer.h.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"transformer.h.8.self_attention.dense.weight": "model-00003-of-00008.safetensors",
"transformer.h.8.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
"transformer.h.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
"transformer.h.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
"transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
"transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
"transformer.h.9.self_attention.dense.weight": "model-00003-of-00008.safetensors",
"transformer.h.9.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
"transformer.ln_f.bias": "model-00008-of-00008.safetensors",
"transformer.ln_f.weight": "model-00008-of-00008.safetensors",
"transformer.word_embeddings.weight": "model-00001-of-00008.safetensors"
}
}

3
pytorch_model-00001-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97615feb1a3a2b0d0fc484fb5d46cd1e89371d5e8d515777cc4db71a1515ff5e
size 1917139629

3
pytorch_model-00002-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4064a0ca0f7984370ca35b7197d2bf6e72d3ca21bd0a5f15c0ef048348bd67b
size 1986955207

3
pytorch_model-00003-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:978e5579c7d451931e725a6d67f8e69c954385929531afa41eb12ac61cb5c743
size 1905508341

3
pytorch_model-00004-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:513fcb1cdb725c9c3fe95336af7d51e833b585f95386e4a55571f9f56e6d0631
size 1905527129

3
pytorch_model-00005-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa8b59468f435ad2412b65490585d48af7484f33cad0811d88529ed361e28e4a
size 1986955271

3
pytorch_model-00006-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:72c3569869b27d728eb3f49b696df1c1c19ca9bf1011b969a08b8c09dc6288cf
size 1905508341

3
pytorch_model-00007-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e41896e45ae0931db01a5714d2aa694f0f94073b62c190c0194b73a41b02c78c
size 1905527129

3
pytorch_model-00008-of-00008.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5984b3da8abe84827d7e9828f8fdf5df15fcb74aabf2fe82b84fe103b7758348
size 921325422

203
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,203 @@
{
"metadata": {
"total_size": 14434379520
},
"weight_map": {
"lm_head.weight": "pytorch_model-00008-of-00008.bin",
"transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
"transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.10.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
"transformer.h.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.10.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.12.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
"transformer.h.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.12.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.13.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
"transformer.h.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.13.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.17.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
"transformer.h.17.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.17.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
"transformer.h.18.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
"transformer.h.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.18.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
"transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.20.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
"transformer.h.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.20.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.22.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
"transformer.h.22.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
"transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.22.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.26.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
"transformer.h.26.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.26.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
"transformer.h.27.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
"transformer.h.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.27.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
"transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
"transformer.h.30.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
"transformer.h.30.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.30.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.31.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
"transformer.h.31.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00008.bin",
"transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00008.bin",
"transformer.h.31.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
"transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
"transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.8.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
"transformer.h.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
"transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
"transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
"transformer.ln_f.bias": "pytorch_model-00008-of-00008.bin",
"transformer.ln_f.weight": "pytorch_model-00008-of-00008.bin",
"transformer.word_embeddings.weight": "pytorch_model-00001-of-00008.bin"
}
}

16
special_tokens_map.json Normal file
View File

@@ -0,0 +1,16 @@
{
"additional_special_tokens": [
">>TITLE<<",
">>ABSTRACT<<",
">>INTRODUCTION<<",
">>SUMMARY<<",
">>COMMENT<<",
">>ANSWER<<",
">>QUESTION<<",
">>DOMAIN<<",
">>PREFIX<<",
">>SUFFIX<<",
">>MIDDLE<<"
],
"eos_token": "<|endoftext|>"
}

129971
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

7
tokenizer_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"add_prefix_space": false,
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 2048,
"tokenizer_class": "PreTrainedTokenizerFast"
}