初始化项目,由ModelHub XC社区提供模型
Model: TabbyML/StarCoder-7B Source: Original Platform
This commit is contained in:
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
|
||||||
|
ggml/*.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
14
README.md
Normal file
14
README.md
Normal file
@@ -0,0 +1,14 @@
|
|||||||
|
---
|
||||||
|
license: other
|
||||||
|
tasks:
|
||||||
|
- text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# TabbyML/StarCoder-7B
|
||||||
|
|
||||||
|
This is an mirror of [TabbyML/StarCoder-7B](https://huggingface.co/TabbyML/StarCoder-7B).
|
||||||
|
|
||||||
|
[Tabby](https://github.com/TabbyML/tabby) is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features:
|
||||||
|
* Self-contained, with no need for a DBMS or cloud service.
|
||||||
|
* OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE).
|
||||||
|
* Supports consumer-grade GPUs.
|
||||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoder-7b",
|
||||||
|
"activation_function": "gelu",
|
||||||
|
"architectures": [
|
||||||
|
"GPTBigCodeForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_softmax_in_fp32": true,
|
||||||
|
"multi_query": true,
|
||||||
|
"attn_pdrop": 0.1,
|
||||||
|
"bos_token_id": 0,
|
||||||
|
"embd_pdrop": 0.1,
|
||||||
|
"eos_token_id": 0,
|
||||||
|
"inference_runner": 0,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"layer_norm_epsilon": 1e-05,
|
||||||
|
"max_batch_size": null,
|
||||||
|
"max_sequence_length": null,
|
||||||
|
"model_type": "gpt_bigcode",
|
||||||
|
"n_embd": 4096,
|
||||||
|
"n_head": 32,
|
||||||
|
"n_inner": 16384,
|
||||||
|
"n_layer": 42,
|
||||||
|
"n_positions": 8192,
|
||||||
|
"pad_key_length": true,
|
||||||
|
"pre_allocate_kv_cache": false,
|
||||||
|
"resid_pdrop": 0.1,
|
||||||
|
"scale_attention_softmax_in_fp32": true,
|
||||||
|
"scale_attn_weights": true,
|
||||||
|
"summary_activation": null,
|
||||||
|
"summary_first_dropout": 0.1,
|
||||||
|
"summary_proj_to_labels": true,
|
||||||
|
"summary_type": "cls_index",
|
||||||
|
"summary_use_proj": true,
|
||||||
|
"torch_dtype": "float32",
|
||||||
|
"transformers_version": "4.28.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"validate_runner_input": true,
|
||||||
|
"vocab_size": 49152
|
||||||
|
}
|
||||||
7
configuration.json
Normal file
7
configuration.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"framework": "pytorch",
|
||||||
|
"task": "text-generation",
|
||||||
|
"pipeline": {
|
||||||
|
"type": "text-generation-pipeline"
|
||||||
|
}
|
||||||
|
}
|
||||||
6
ctranslate2/config.json
Normal file
6
ctranslate2/config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"layer_norm_epsilon": null,
|
||||||
|
"unk_token": "<|endoftext|>"
|
||||||
|
}
|
||||||
3
ctranslate2/model.bin
Normal file
3
ctranslate2/model.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:bb6c8fb5581390fae1ae9ae071ff06716e70ada17f6425cb9268047080b511d2
|
||||||
|
size 14654557177
|
||||||
49154
ctranslate2/vocabulary.json
Normal file
49154
ctranslate2/vocabulary.json
Normal file
File diff suppressed because it is too large
Load Diff
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 0,
|
||||||
|
"eos_token_id": 0,
|
||||||
|
"transformers_version": "4.28.1"
|
||||||
|
}
|
||||||
3
ggml/f16.gguf
Normal file
3
ggml/f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:65458a1ccb23680a2f065202dc93e264b7f2d1f80931a526138cc82663ed0c8a
|
||||||
|
size 15062898176
|
||||||
3
ggml/f16.v2.gguf
Normal file
3
ggml/f16.v2.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f80be31b194a6a5bbaa42b72ae1f51b02871b2fba6b13774e41d286115aba31b
|
||||||
|
size 15062749920
|
||||||
3
ggml/q8_0.gguf
Normal file
3
ggml/q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4e99e76ed0ee91cc74aeb3385da1f36699f32cf3c15891353e4cddac4aae29e9
|
||||||
|
size 8006637120
|
||||||
3
ggml/q8_0.v2.gguf
Normal file
3
ggml/q8_0.v2.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:33dfcc7e216f1a072b4e16cd3bb19a0e55f5874ed319416435c8fc99216b8bfa
|
||||||
|
size 8006488832
|
||||||
48892
merges.txt
Normal file
48892
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00004.bin
Normal file
3
pytorch_model-00001-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1bc158094d8042472ffb102358edc404e01fca915f750f6583bd0a04493ba327
|
||||||
|
size 9859125333
|
||||||
3
pytorch_model-00002-of-00004.bin
Normal file
3
pytorch_model-00002-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:93bdbf4a261a3bdb9470cedf66bacbd998751418a807e78f1bfea9df6b6365b5
|
||||||
|
size 9993542361
|
||||||
3
pytorch_model-00003-of-00004.bin
Normal file
3
pytorch_model-00003-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:397636f10cc990cd9abb94960d71200b89ff2cb78e27900bdb21d5f25b376a4a
|
||||||
|
size 9456554659
|
||||||
3
pytorch_model-00004-of-00004.bin
Normal file
3
pytorch_model-00004-of-00004.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:72bb6594879519b299cae04e8c433078eae2de78291511f1e4976a904f71bdc6
|
||||||
|
size 805307306
|
||||||
516
pytorch_model.bin.index.json
Normal file
516
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,516 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 30114359296
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00004-of-00004.bin",
|
||||||
|
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.13.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.13.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.13.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.28.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||||
|
"transformer.h.28.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.40.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.40.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.41.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.ln_f.bias": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.ln_f.weight": "pytorch_model-00003-of-00004.bin",
|
||||||
|
"transformer.wpe.weight": "pytorch_model-00001-of-00004.bin",
|
||||||
|
"transformer.wte.weight": "pytorch_model-00001-of-00004.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
4
tabby.json
Normal file
4
tabby.json
Normal file
@@ -0,0 +1,4 @@
|
|||||||
|
{
|
||||||
|
"auto_model": "AutoModelForCausalLM",
|
||||||
|
"prompt_template": "<fim_prefix>{prefix}<fim_suffix>{suffix}<fim_middle>"
|
||||||
|
}
|
||||||
98256
tokenizer.json
Normal file
98256
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
30
tokenizer_config.json
Normal file
30
tokenizer_config.json
Normal file
@@ -0,0 +1,30 @@
|
|||||||
|
{
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|endoftext|>",
|
||||||
|
"<fim_prefix>",
|
||||||
|
"<fim_middle>",
|
||||||
|
"<fim_suffix>",
|
||||||
|
"<fim_pad>",
|
||||||
|
"<filename>",
|
||||||
|
"<gh_stars>",
|
||||||
|
"<issue_start>",
|
||||||
|
"<issue_comment>",
|
||||||
|
"<issue_closed>",
|
||||||
|
"<jupyter_start>",
|
||||||
|
"<jupyter_text>",
|
||||||
|
"<jupyter_code>",
|
||||||
|
"<jupyter_output>",
|
||||||
|
"<empty_output>",
|
||||||
|
"<commit_before>",
|
||||||
|
"<commit_msg>",
|
||||||
|
"<commit_after>",
|
||||||
|
"<reponame>"
|
||||||
|
],
|
||||||
|
"bos_token": "<|endoftext|>",
|
||||||
|
"eos_token": "<|endoftext|>",
|
||||||
|
"model_max_length": 1000000000000000019884624838656,
|
||||||
|
"tokenizer_class": "GPT2Tokenizer",
|
||||||
|
"unk_token": "<|endoftext|>",
|
||||||
|
"vocab_size": 49152
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user