初始化项目，由ModelHub XC社区提供模型
Model: medicalai/MedFound-7B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
*.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
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
20
README.md
Normal file
20
README.md
Normal file
@@ -0,0 +1,20 @@
|
||||
---
|
||||
license: afl-3.0
|
||||
library_name: transformers
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- medical
|
||||
---
|
||||
|
||||
## Introduction
|
||||
For more information, visit our GitHub repository:
|
||||
https://github.com/medfound/medfound
|
||||
|
||||
## Limitations
|
||||
|
||||
The project is intended for research purposes only and restricted from commercial or clinical use. The generated content by the model is subject to factors such as model computations, randomness, misinterpretation, and biases, and this project cannot guarantee its accuracy. This project assumes no legal liability for any content produced by the model. Users are advised to exercise caution and independently verify the generated results.
|
||||
|
||||
## Citation
|
||||
|
||||
Please cite this article:
|
||||
Wang, G., Liu, X., Liu, H., Yang, G. et al. A Generalist Medical Language Model for Disease Diagnosis Assistance. Nat Med (2025). https://doi.org/10.1038/s41591-024-03416-6
|
||||
31
config.json
Normal file
31
config.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"apply_residual_connection_post_layernorm": false,
|
||||
"architectures": [
|
||||
"BloomForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"attention_softmax_in_fp32": true,
|
||||
"bias_dropout_fusion": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_dropout": 0.0,
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"masked_softmax_fusion": true,
|
||||
"model_type": "bloom",
|
||||
"n_head": 32,
|
||||
"n_inner": null,
|
||||
"n_layer": 30,
|
||||
"offset_alibi": 100,
|
||||
"pad_token_id": 3,
|
||||
"pretraining_tp": 1,
|
||||
"skip_bias_add": true,
|
||||
"skip_bias_add_qkv": false,
|
||||
"slow_but_exact": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.42.4",
|
||||
"unk_token_id": 0,
|
||||
"use_cache": true,
|
||||
"vocab_size": 250880
|
||||
}
|
||||
5
generation_config.json
Normal file
5
generation_config.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"temperature": null,
|
||||
"top_p": null,
|
||||
"transformers_version": "4.42.4"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a084718288028752c7bbf42129f8e0ad8ba15e88fe541172d1b4ac30f14bdd3b
|
||||
size 4975258008
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44f57b3cf496b18e08c7495858d34fd9ed2d193584bac7e9145651f44e52560d
|
||||
size 4866712640
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9f824123fdf5adb05cd28e2e8c28e336dfb549b652860445c1919d580ae13ddc
|
||||
size 4296104456
|
||||
372
model.safetensors.index.json
Normal file
372
model.safetensors.index.json
Normal file
@@ -0,0 +1,372 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14138032128
|
||||
},
|
||||
"weight_map": {
|
||||
"transformer.h.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.10.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.10.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.11.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.12.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.19.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.20.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.20.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.21.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.22.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.23.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.24.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.25.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.26.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.self_attention.dense.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.self_attention.dense.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.self_attention.query_key_value.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.h.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.self_attention.dense.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.self_attention.dense.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.h.8.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.8.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.input_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.self_attention.dense.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.self_attention.dense.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.self_attention.query_key_value.bias": "model-00002-of-00003.safetensors",
|
||||
"transformer.h.9.self_attention.query_key_value.weight": "model-00002-of-00003.safetensors",
|
||||
"transformer.ln_f.bias": "model-00003-of-00003.safetensors",
|
||||
"transformer.ln_f.weight": "model-00003-of-00003.safetensors",
|
||||
"transformer.word_embeddings.weight": "model-00001-of-00003.safetensors",
|
||||
"transformer.word_embeddings_layernorm.bias": "model-00001-of-00003.safetensors",
|
||||
"transformer.word_embeddings_layernorm.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c15972849c91c78dfab27e2ef0eb53b17f95c4fe81be6664f7e85c6a7fffde0e
|
||||
size 14500499
|
||||
45
tokenizer_config.json
Normal file
45
tokenizer_config.json
Normal file
@@ -0,0 +1,45 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<pad>",
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "BloomTokenizer",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user