初始化项目，由ModelHub XC社区提供模型
Model: openchat/opencoderplus 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
|
||||
130
README.md
Normal file
130
README.md
Normal file
@@ -0,0 +1,130 @@
|
||||
---
|
||||
language:
|
||||
- en
|
||||
tags:
|
||||
- llama
|
||||
---
|
||||
|
||||
# OpenChat: Less is More for Open-source Models
|
||||
|
||||
OpenChat is a series of open-source language models fine-tuned on a diverse and high-quality dataset of multi-round conversations. With only ~6K GPT-4 conversations filtered from the ~90K ShareGPT conversations, OpenChat is designed to achieve high performance with limited data.
|
||||
|
||||
**Generic models:**
|
||||
|
||||
- OpenChat: based on LLaMA-13B (2048 context length)
|
||||
- **🚀 105.7%** of ChatGPT score on Vicuna GPT-4 evaluation
|
||||
- **🔥 80.9%** Win-rate on AlpacaEval
|
||||
- **🤗 Only used 6K data for finetuning!!!**
|
||||
- OpenChat-8192: based on LLaMA-13B (extended to 8192 context length)
|
||||
- **106.6%** of ChatGPT score on Vicuna GPT-4 evaluation
|
||||
- **79.5%** of ChatGPT score on Vicuna GPT-4 evaluation
|
||||
|
||||
**Code models:**
|
||||
|
||||
- OpenCoderPlus: based on StarCoderPlus (native 8192 context length)
|
||||
- **102.5%** of ChatGPT score on Vicuna GPT-4 evaluation
|
||||
- **78.7%** Win-rate on AlpacaEval
|
||||
|
||||
*Note:* Please load the pretrained models using *bfloat16*
|
||||
|
||||
## Code and Inference Server
|
||||
|
||||
We provide the full source code, including an inference server compatible with the "ChatCompletions" API, in the [OpenChat](https://github.com/imoneoi/openchat) GitHub repository.
|
||||
|
||||
## Web UI
|
||||
|
||||
OpenChat also includes a web UI for a better user experience. See the GitHub repository for instructions.
|
||||
|
||||
## Conversation Template
|
||||
|
||||
The conversation template **involves concatenating tokens**.
|
||||
|
||||
Besides base model vocabulary, an end-of-turn token `<|end_of_turn|>` is added, with id `eot_token_id`.
|
||||
|
||||
```python
|
||||
# OpenChat
|
||||
[bos_token_id] + tokenize("Human: ") + tokenize(user_question) + [eot_token_id] + tokenize("Assistant: ")
|
||||
# OpenCoder
|
||||
tokenize("User:") + tokenize(user_question) + [eot_token_id] + tokenize("Assistant:")
|
||||
```
|
||||
|
||||
*Hint: In BPE, `tokenize(A) + tokenize(B)` does not always equals to `tokenize(A + B)`*
|
||||
|
||||
Following is the code for generating the conversation templates:
|
||||
|
||||
```python
|
||||
@dataclass
|
||||
class ModelConfig:
|
||||
# Prompt
|
||||
system: Optional[str]
|
||||
|
||||
role_prefix: dict
|
||||
ai_role: str
|
||||
eot_token: str
|
||||
bos_token: Optional[str] = None
|
||||
|
||||
# Get template
|
||||
def generate_conversation_template(self, tokenize_fn, tokenize_special_fn, message_list):
|
||||
tokens = []
|
||||
masks = []
|
||||
|
||||
# begin of sentence (bos)
|
||||
if self.bos_token:
|
||||
t = tokenize_special_fn(self.bos_token)
|
||||
tokens.append(t)
|
||||
masks.append(False)
|
||||
|
||||
# System
|
||||
if self.system:
|
||||
t = tokenize_fn(self.system) + [tokenize_special_fn(self.eot_token)]
|
||||
tokens.extend(t)
|
||||
masks.extend([False] * len(t))
|
||||
|
||||
# Messages
|
||||
for idx, message in enumerate(message_list):
|
||||
# Prefix
|
||||
t = tokenize_fn(self.role_prefix[message["from"]])
|
||||
tokens.extend(t)
|
||||
masks.extend([False] * len(t))
|
||||
|
||||
# Message
|
||||
if "value" in message:
|
||||
t = tokenize_fn(message["value"]) + [tokenize_special_fn(self.eot_token)]
|
||||
tokens.extend(t)
|
||||
masks.extend([message["from"] == self.ai_role] * len(t))
|
||||
else:
|
||||
assert idx == len(message_list) - 1, "Empty message for completion must be on the last."
|
||||
|
||||
return tokens, masks
|
||||
|
||||
|
||||
MODEL_CONFIG_MAP = {
|
||||
# OpenChat / OpenChat-8192
|
||||
"openchat": ModelConfig(
|
||||
# Prompt
|
||||
system=None,
|
||||
|
||||
role_prefix={
|
||||
"human": "Human: ",
|
||||
"gpt": "Assistant: "
|
||||
},
|
||||
ai_role="gpt",
|
||||
eot_token="<|end_of_turn|>",
|
||||
bos_token="<s>",
|
||||
),
|
||||
|
||||
# OpenCoder / OpenCoderPlus
|
||||
"opencoder": ModelConfig(
|
||||
# Prompt
|
||||
system=None,
|
||||
|
||||
role_prefix={
|
||||
"human": "User:",
|
||||
"gpt": "Assistant:"
|
||||
},
|
||||
ai_role="gpt",
|
||||
eot_token="<|end_of_turn|>",
|
||||
bos_token=None,
|
||||
)
|
||||
}
|
||||
```
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<|end_of_turn|>": 49152
|
||||
}
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"_name_or_path": "/data/one/starcoderplus_with_eot",
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"GPTBigCodeForCausalLM"
|
||||
],
|
||||
"attention_softmax_in_fp32": 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",
|
||||
"multi_query": true,
|
||||
"n_embd": 6144,
|
||||
"n_head": 48,
|
||||
"n_inner": 24576,
|
||||
"n_layer": 40,
|
||||
"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": "bfloat16",
|
||||
"transformers_version": "4.30.1",
|
||||
"use_cache": true,
|
||||
"validate_runner_input": true,
|
||||
"vocab_size": 49153
|
||||
}
|
||||
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": "4.30.1"
|
||||
}
|
||||
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:c7441188b4ed97f2eac40beabaf1e9fc5b9e2908ecef193210cfdc27627a0e41
|
||||
size 9957995189
|
||||
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 sha256:02a25b6227a8baa52f28cbdef5cf9b0897be850cec2e13a29384d21430d6d14c
|
||||
size 9857381671
|
||||
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 sha256:00d943bd023e738e653a2664708f8c4b51bb81387ca70cfe34982dd42d3b9b16
|
||||
size 9857381671
|
||||
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 sha256:1509161539ba7ce6b228ea951fba88852faf1e3a54558bff88c35a45208f97e8
|
||||
size 1966320293
|
||||
492
pytorch_model.bin.index.json
Normal file
492
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,492 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 31638917120
|
||||
},
|
||||
"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-00002-of-00004.bin",
|
||||
"transformer.h.12.mlp.c_fc.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.12.mlp.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.attn.c_proj.bias": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.ln_2.bias": "pytorch_model-00002-of-00004.bin",
|
||||
"transformer.h.13.ln_2.weight": "pytorch_model-00002-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-00003-of-00004.bin",
|
||||
"transformer.h.25.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.25.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.attn.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.ln_2.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.ln_2.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.mlp.c_fc.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.mlp.c_fc.weight": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.mlp.c_proj.bias": "pytorch_model-00003-of-00004.bin",
|
||||
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00003-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-00003-of-00004.bin",
|
||||
"transformer.h.28.ln_1.weight": "pytorch_model-00003-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-00004-of-00004.bin",
|
||||
"transformer.h.38.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.38.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.attn.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.ln_1.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.ln_1.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.ln_2.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.ln_2.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.mlp.c_fc.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.mlp.c_fc.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.mlp.c_proj.bias": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00004-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.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-00004-of-00004.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00004-of-00004.bin",
|
||||
"transformer.wpe.weight": "pytorch_model-00001-of-00004.bin",
|
||||
"transformer.wte.weight": "pytorch_model-00001-of-00004.bin"
|
||||
}
|
||||
}
|
||||
8
special_tokens_map.json
Normal file
8
special_tokens_map.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|end_of_turn|>"
|
||||
],
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|end_of_turn|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
56
tokenizer_config.json
Normal file
56
tokenizer_config.json
Normal file
@@ -0,0 +1,56 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"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": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"errors": "replace",
|
||||
"low_cpu_mem_usage": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"vocab_size": 49152
|
||||
}
|
||||
49154
vocab.json
Normal file
49154
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user