openaccess-ai-collective/minotaur-15b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: openaccess-ai-collective/minotaur-15b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-09 10:19:18 +08:00
commit 0f2d96fdc0
16 changed files with 148137 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View 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
minotaur.png filter=lfs diff=lfs merge=lfs -text

204
README.md Normal file
View File

@@ -0,0 +1,204 @@
---
pipeline_tag: text-generation
inference: true
widget:
- text: 'def print_hello_world():'
example_title: Hello world
group: Python
- text: 'Gradient descent is'
example_title: Machine Learning
group: English
- license: bigcode-openrail-m
datasets:
- bigcode/the-stack-dedup
- tiiuae/falcon-refinedweb
- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
- QingyiSi/Alpaca-CoT
- teknium/GPTeacher-General-Instruct
- metaeval/ScienceQA_text_only
- hellaswag
- openai/summarize_from_feedback
- riddle_sense
- gsm8k
- camel-ai/math
- camel-ai/biology
- camel-ai/physics
- camel-ai/chemistry
- winglian/evals
metrics:
- code_eval
- mmlu
- arc
- hellaswag
- truthfulqa
library_name: transformers
tags:
- code
extra_gated_prompt: >-
## Model License Agreement
Please read the BigCode [OpenRAIL-M
license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)
agreement before accepting it.
extra_gated_fields:
I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
---
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!**
# Minotaur 15B 8K
Minotaur 15B is an instruct fine-tuned model on top of Starcoder Plus. Minotaur 15B is fine-tuned **on only completely open datasets** making this model reproducible by anyone.
Minotaur 15B has a context length of 8K tokens, allowing for strong recall at long contexts.
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/PugNNHAF5r) or email [wing@openaccessaicollective.org](mailto:wing@openaccessaicollective.org)
# Prompts
Chat only style prompts using `USER:`,`ASSISTANT:`.
<img src="https://huggingface.co/openaccess-ai-collective/minotaur-13b/resolve/main/minotaur.png" alt="minotaur" width="600" height="600"/>
# Training Datasets
Minotaur 15B model is fine-tuned on the following openly available datasets:
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
- [camel-ai/math](https://huggingface.co/datasets/camel-ai/math)
- [camel-ai/physics](https://huggingface.co/datasets/camel-ai/physics)
- [camel-ai/chemistry](https://huggingface.co/datasets/camel-ai/chemistry)
- [camel-ai/biology](https://huggingface.co/datasets/camel-ai/biology)
- [winglian/evals](https://huggingface.co/datasets/winglian/evals) - instruct augmented datasets
- custom sysnthetic datasets around misconceptions, in-context qa, jokes, N-tasks problems, and context-insensitivity
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses, derived from the `train` split
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 30K+ rows of instruct augmented for detailed explanations w 30K+ rows, derived from the `train` split
- [riddle_sense](https://huggingface.co/datasets/riddle_sense) - instruct augmented, derived from the `train` split
- [gsm8k](https://huggingface.co/datasets/gsm8k) - instruct augmented, derived from the `train` split
- prose generation
# Shoutouts
Special thanks to Nanobit for helping with Axolotl and TheBloke for quantizing these models are more accessible to all.
# Demo
HF Demo in Spaces available in the [Community ChatBot Arena](https://huggingface.co/spaces/openaccess-ai-collective/rlhf-arena) under the OAAIC Chatbots tab.
## Release Notes
- https://wandb.ai/wing-lian/minotaur-16b-8k/runs/tshgbl2k
## Build
Minotaur was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 4XA100 80GB
- 1 epochs taking approximately 30 hours
- Trained using QLoRA techniques
## Bias, Risks, and Limitations
Minotaur has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
Minotaur was fine-tuned from the base model StarCoder, please refer to its model card's Limitations Section for relevant information. (included below)
## Benchmarks
TBD
## Examples
TBD
# StarCoderPlus
Play with the instruction-tuned StarCoderPlus at [StarChat-Beta](https://huggingface.co/spaces/HuggingFaceH4/starchat-playground).
## Table of Contents
1. [Model Summary](##model-summary)
2. [Use](##use)
3. [Limitations](##limitations)
4. [Training](##training)
5. [License](##license)
6. [Citation](##citation)
## Model Summary
StarCoderPlus is a fine-tuned version of [StarCoderBase](https://huggingface.co/bigcode/starcoderbase) on 600B tokens from the English web dataset [RedefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)
combined with [StarCoderData](https://huggingface.co/datasets/bigcode/starcoderdata) from [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack) and a Wikipedia dataset.
It's a 15.5B parameter Language Model trained on English and 80+ programming languages. The model uses [Multi Query Attention](https://arxiv.org/abs/1911.02150),
[a context window of 8192 tokens](https://arxiv.org/abs/2205.14135), and was trained using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on 1.6 trillion tokens.
- **Repository:** [bigcode/Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Project Website:** [bigcode-project.org](https://www.bigcode-project.org)
- **Point of Contact:** [contact@bigcode-project.org](mailto:contact@bigcode-project.org)
- **Languages:** English & 80+ Programming languages
## Use
### Intended use
The model was trained on English and GitHub code. As such it is _not_ an instruction model and commands like "Write a function that computes the square root." do not work well. However, the instruction-tuned version in [StarChat](hhttps://huggingface.co/spaces/HuggingFaceH4/starchat-playground) makes a capable assistant.
**Feel free to share your generations in the Community tab!**
### Generation
```python
# pip install -q transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
checkpoint = "bigcode/starcoderplus"
device = "cuda" # for GPU usage or "cpu" for CPU usage
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
inputs = tokenizer.encode("def print_hello_world():", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
### Fill-in-the-middle
Fill-in-the-middle uses special tokens to identify the prefix/middle/suffix part of the input and output:
```python
input_text = "<fim_prefix>def print_hello_world():\n <fim_suffix>\n print('Hello world!')<fim_middle>"
inputs = tokenizer.encode(input_text, return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))
```
### Attribution & Other Requirements
The training code dataset of the model was filtered for permissive licenses only. Nevertheless, the model can generate source code verbatim from the dataset. The code's license might require attribution and/or other specific requirements that must be respected. We provide a [search index](https://huggingface.co/spaces/bigcode/starcoder-search) that let's you search through the pretraining data to identify where generated code came from and apply the proper attribution to your code.
# Limitations
The model has been trained on a mixture of English text from the web and GitHub code. Therefore it might encounter limitations when working with non-English text, and can carry the stereotypes and biases commonly encountered online.
Additionally, the generated code should be used with caution as it may contain errors, inefficiencies, or potential vulnerabilities. For a more comprehensive understanding of the base model's code limitations, please refer to See [StarCoder paper](hhttps://arxiv.org/abs/2305.06161).
# Training
StarCoderPlus is a fine-tuned version on 600B English and code tokens of StarCoderBase, which was pre-trained on 1T code tokens. Below are the fine-tuning details:
## Model
- **Architecture:** GPT-2 model with multi-query attention and Fill-in-the-Middle objective
- **Finetuning steps:** 150k
- **Finetuning tokens:** 600B
- **Precision:** bfloat16
## Hardware
- **GPUs:** 512 Tesla A100
- **Training time:** 14 days
## Software
- **Orchestration:** [Megatron-LM](https://github.com/bigcode-project/Megatron-LM)
- **Neural networks:** [PyTorch](https://github.com/pytorch/pytorch)
- **BP16 if applicable:** [apex](https://github.com/NVIDIA/apex)
# License
The model is licensed under the BigCode OpenRAIL-M v1 license agreement. You can find the full agreement [here](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement).

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoderplus/large-model",
"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": 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": "float32",
"transformers_version": "4.28.1",
"use_cache": true,
"validate_runner_input": true,
"vocab_size": 49152
}

140
configs/config.yml Normal file
View File

@@ -0,0 +1,140 @@
base_model: bigcode/starcoderplus
base_model_config: bigcode/starcoderplus
load_in_8bit: false
load_in_4bit: true
gptq: false
strict: false
push_dataset_to_hub: winglian
hf_use_auth_token: true
datasets:
- path: winglian/evals
data_files:
- hf/ARC-Challenge.jsonl
- hf/ARC-Easy.jsonl
- hf/riddle_sense.jsonl
- hf/piqa.jsonl
type: explainchoice:chat
- path: winglian/evals
data_files:
- hf/gsm8k.jsonl
- hf/winogrande.jsonl
type: alpaca_chat.load_qa
- path: winglian/evals
data_files:
- custom/n_task.jsonl
- custom/misconceptions.jsonl
- custom/context_insensitivity.jsonl
type: alpaca_chat
- path: camel-ai/math
type: alpaca_chat.load_camel_ai
- path: camel-ai/biology
type: alpaca_chat.load_camel_ai
- path: camel-ai/physics
type: alpaca_chat.load_camel_ai
- path: camel-ai/chemistry
type: alpaca_chat.load_camel_ai
- path: winglian/evals
data_files:
- custom/in_context_qa.jsonl
type: context_qa
- path: winglian/evals
data_files:
- custom/in_context_qa.jsonl
type: context_qa.load_404
- path: winglian/evals
data_files:
- custom/jokes_explained_500up.jsonl
type: sharegpt_jokes
- path: winglian/evals
data_files:
- custom/classify-self-chat.sharegpt.jsonl
- custom/coding-self-chat.sharegpt.jsonl
- custom/prose-gpt4.sharegpt.jsonl
- custom/prose-rewrite-gpt4.sharegpt.jsonl
type: sharegpt_simple.load_role
- path: winglian/evals
data_files:
- openai/tldr.jsonl
type: summarizetldr:chat
- path: winglian/evals
data_files:
- hellaswag/hellaswag.jsonl
type: explainchoice:chat
- path: metaeval/ScienceQA_text_only
type: concisechoice:chat
- path: teknium/GPT4-LLM-Cleaned
type: alpaca_chat
- path: teknium/GPTeacher-General-Instruct
data_files: gpt4-instruct-similarity-0.6-dataset.json
type: gpteacher:chat
- path: QingyiSi/Alpaca-CoT
data_files:
- Chain-of-Thought/formatted_cot_data/aqua_train.json
- Chain-of-Thought/formatted_cot_data/creak_train.json
- Chain-of-Thought/formatted_cot_data/ecqa_train.json
- Chain-of-Thought/formatted_cot_data/esnli_train.json
- Chain-of-Thought/formatted_cot_data/qasc_train.json
- Chain-of-Thought/formatted_cot_data/qed_train.json
- Chain-of-Thought/formatted_cot_data/sensemaking_train.json
- Chain-of-Thought/formatted_cot_data/strategyqa_train.json
- GPTeacher/Roleplay/formatted_roleplay-similarity_0.6-instruct-dataset.json
type: alpaca_chat
- path: ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
type: alpaca_chat
- path: ehartford/wizard_vicuna_70k_unfiltered
type: sharegpt:chat
dataset_prepared_path: last_run_prepared
val_set_size: 0.01
adapter: qlora
lora_model_dir:
sequence_len: 8192
max_packed_sequence_len: 8192
lora_r: 40
lora_alpha: 32
lora_dropout: 0.1
lora_target_modules:
- c_attn
- c_proj
- c_fc
lora_target_linear: true
lora_fan_in_fan_out:
wandb_project: minotaur-16b-8k
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./minotaur-16b-8k
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.00013
train_on_inputs: false
group_by_length: true
bf16: true
fp16: false
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention: false
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 100
eval_steps: 20
save_steps: 51
load_best_model_at_end: false
debug:
deepspeed:
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: "<|endoftext|>"
bos_token: "<|endoftext|>"
eos_token: "<|endoftext|>"
unk_token: "<|endoftext|>"

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 0,
"transformers_version": "4.27.0.dev0"
}

48892
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
minotaur.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de94bc7a7161471e5409baf7ef7bd5166467960a7322b8176694a0e9a3dc9b1a
size 1996083

3
pytorch_model-00001-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b63d1b39b0a4343cdcdf07b1268ab59afc751cda1ae77090276829999ab99a8d
size 9957983029

3
pytorch_model-00002-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33673fdbed848f5ccff4a38883de3fee5863e11c133dc3c928130fc3875762f4
size 9857381671

3
pytorch_model-00003-of-00004.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:867f349a3983025428fc04a5a4bd1bfcf3caef78dda1a719919cea02d1cbe874
size 9857381671

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f0197a8b4b763f67d7af791ebfe294aa5f58658c39b65036b1ea22a37b25e198
size 1362327955

492
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,492 @@
{
"metadata": {
"total_size": 31638990848
},
"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"
}
}

26
special_tokens_map.json Normal file
View File

@@ -0,0 +1,26 @@
{
"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|>",
"unk_token": "<|endoftext|>"
}

98256
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

30
tokenizer_config.json Normal file
View 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
View File

File diff suppressed because one or more lines are too long