初始化项目，由ModelHub XC社区提供模型
Model: saarvajanik/facebook-opt-6.7b-gqa-ub-16-best-for-KV-cache Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
8
README.md
Normal file
8
README.md
Normal file
@@ -0,0 +1,8 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
This is a QCQA version of the original model facebook/opt-125m. In this version, the original MHA architecture is preserved but instead of having a single K/V head, different K/V heads corresponding to the same group have the same mean-pooled K or V values. It has 16 groups of KV heads per layer instead of original 32 KV heads in the MHA implementation.
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "facebook/opt-6.7b",
|
||||
"_remove_final_layer_norm": false,
|
||||
"activation_dropout": 0.0,
|
||||
"activation_function": "relu",
|
||||
"architectures": [
|
||||
"OPTForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 2,
|
||||
"do_layer_norm_before": true,
|
||||
"dropout": 0.1,
|
||||
"eos_token_id": 2,
|
||||
"ffn_dim": 16384,
|
||||
"hidden_size": 4096,
|
||||
"init_std": 0.02,
|
||||
"layerdrop": 0.0,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "opt",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 1,
|
||||
"prefix": "</s>",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.23.1",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50272,
|
||||
"word_embed_proj_dim": 4096
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00003.bin
Normal file
3
pytorch_model-00001-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a51afb59a3f43734a4eaecdf27df1b2b3c649da60bd6ae5a1da0e9a3a9e8e64
|
||||
size 9986589484
|
||||
3
pytorch_model-00002-of-00003.bin
Normal file
3
pytorch_model-00002-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:59366733c283b7adfc83e2f2b9c2c348f7ef887eed033e43e07961b738c19918
|
||||
size 9934800976
|
||||
3
pytorch_model-00003-of-00003.bin
Normal file
3
pytorch_model-00003-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ddbc2ba97f30888b430da48d8ef595c8969741d52bf651162bb4fac2516fb514
|
||||
size 7536342289
|
||||
524
pytorch_model.bin.index.json
Normal file
524
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,524 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 27457552384
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.embed_positions.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.12.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.20.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.23.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"model.decoder.layers.24.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.30.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin"
|
||||
}
|
||||
}
|
||||
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": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
40
tokenizer_config.json
Normal file
40
tokenizer_config.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_prefix_space": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"errors": "replace",
|
||||
"name_or_path": "facebook/opt-6.7b",
|
||||
"pad_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"special_tokens_map_file": null,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
50267
vocab.json
Normal file
50267
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user