初始化项目，由ModelHub XC社区提供模型
Model: pankajmathur/orca_mini_v2_13b 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
|
||||||
384
README.md
Normal file
384
README.md
Normal file
@@ -0,0 +1,384 @@
|
|||||||
|
---
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
license: cc-by-nc-sa-4.0
|
||||||
|
library_name: transformers
|
||||||
|
datasets:
|
||||||
|
- psmathur/orca_minis_uncensored_dataset
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
model-index:
|
||||||
|
- name: orca_mini_v2_13b
|
||||||
|
results:
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: AI2 Reasoning Challenge (25-Shot)
|
||||||
|
type: ai2_arc
|
||||||
|
config: ARC-Challenge
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 25
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 55.12
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: HellaSwag (10-Shot)
|
||||||
|
type: hellaswag
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 10
|
||||||
|
metrics:
|
||||||
|
- type: acc_norm
|
||||||
|
value: 79.69
|
||||||
|
name: normalized accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: MMLU (5-Shot)
|
||||||
|
type: cais/mmlu
|
||||||
|
config: all
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 50.07
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: TruthfulQA (0-shot)
|
||||||
|
type: truthful_qa
|
||||||
|
config: multiple_choice
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 0
|
||||||
|
metrics:
|
||||||
|
- type: mc2
|
||||||
|
value: 52.56
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: Winogrande (5-shot)
|
||||||
|
type: winogrande
|
||||||
|
config: winogrande_xl
|
||||||
|
split: validation
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 72.69
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
- task:
|
||||||
|
type: text-generation
|
||||||
|
name: Text Generation
|
||||||
|
dataset:
|
||||||
|
name: GSM8k (5-shot)
|
||||||
|
type: gsm8k
|
||||||
|
config: main
|
||||||
|
split: test
|
||||||
|
args:
|
||||||
|
num_few_shot: 5
|
||||||
|
metrics:
|
||||||
|
- type: acc
|
||||||
|
value: 6.37
|
||||||
|
name: accuracy
|
||||||
|
source:
|
||||||
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=psmathur/orca_mini_v2_13b
|
||||||
|
name: Open LLM Leaderboard
|
||||||
|
---
|
||||||
|
# orca_mini_v2_13b
|
||||||
|
|
||||||
|
**An **Uncensored** LLaMA-13b model in collaboration with [Eric Hartford](https://huggingface.co/ehartford). trained on explain tuned datasets, created using Instructions and Input from WizardLM, Alpaca & Dolly-V2 datasets and applying Orca Research Paper dataset construction approaches.**
|
||||||
|
|
||||||
|
Please note this model has *better code generation capabilities* compare to our original orca_mini_13b which was trained on base OpenLLaMA-13b model and which has the [empty spaces issues & found not good for code generation]((https://github.com/openlm-research/open_llama#update-06072023)).
|
||||||
|
|
||||||
|
<img src="https://huggingface.co/pankajmathur/orca_mini_v5_8b/resolve/main/orca_minis_small.jpeg" width="auto" />
|
||||||
|
|
||||||
|
<strong>
|
||||||
|
"Obsessed with GenAI's potential? So am I ! Let's create together 🚀 <a href="https://www.linkedin.com/in/pankajam" target="_blank">https://www.linkedin.com/in/pankajam</a>"
|
||||||
|
</strong>
|
||||||
|
|
||||||
|
<br>
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Evaluation
|
||||||
|
|
||||||
|
I evaluated orca_mini_v2_13b on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI.
|
||||||
|
|
||||||
|
Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||||
|
|
||||||
|
|
||||||
|
||||
|
||||||
|
|:------:|:-------------:|:---------:|
|
||||||
|
|**Task**|**Value**|**Stderr**|
|
||||||
|
|*arc_challenge*|0.5478|0.0145|
|
||||||
|
|*hellaswag*|0.7023|0.0040|
|
||||||
|
|*mmlu*|0.4969|0.035|
|
||||||
|
|*truthfulqa_mc*|0.44|0.0158|
|
||||||
|
|*Total Average*|0.54675|0.0114|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Dataset
|
||||||
|
|
||||||
|
We used uncensored script on top of the previous explain tuned datasets we build which are [WizardLM dataset ~70K](https://github.com/nlpxucan/WizardLM), [Alpaca dataset ~52K](https://crfm.stanford.edu/2023/03/13/alpaca.html) & [Dolly-V2 dataset ~15K](https://github.com/databrickslabs/dolly) created using approaches from [Orca Research Paper](https://arxiv.org/abs/2306.02707).
|
||||||
|
|
||||||
|
We leverage all of the 15 system instructions provided in Orca Research Paper. to generate custom datasets, in contrast to vanilla instruction tuning approaches used by original datasets.
|
||||||
|
|
||||||
|
This helps student model aka this model to learn ***thought*** process from teacher model, which is ChatGPT (gpt-3.5-turbo-0301 version).
|
||||||
|
|
||||||
|
Please see below example usage how the **System** prompt is added before each **instruction**.
|
||||||
|
|
||||||
|
### Training
|
||||||
|
|
||||||
|
The training configurations are provided in the table below.
|
||||||
|
|
||||||
|
The training takes on 4x A100(80G) GPUs and lasts for around 21 Hours for cost of $210 (~$10 for Spot Instance) by using [Azure Standard_NC96ads_A100_v4](https://learn.microsoft.com/en-us/azure/virtual-machines/nc-a100-v4-series#supported-features).
|
||||||
|
|
||||||
|
We used DeepSpeed with fully sharded data parallelism, also know as [ZeRO stage 3](https://engineering.fb.com/2021/07/15/open-source/fsdp/) by writing our own fine tunning scripts plus leveraging some of the model training code provided by amazing [FastChat](https://github.com/lm-sys/FastChat)
|
||||||
|
|
||||||
|
Here are some of params used during training:
|
||||||
|
|
||||||
|
|||
|
||||||
|
|:-------------:|:-------------:|
|
||||||
|
|*batch_size*|48|
|
||||||
|
|*train_micro_batch_size_per_gpu*|3|
|
||||||
|
|*gradient_accumulation_steps*|4|
|
||||||
|
|*Learning rate*|2e-5|
|
||||||
|
|*Max length*|2048|
|
||||||
|
|*Epochs*|3|
|
||||||
|
|*Optimizer*|AdamW|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
### Example Usage
|
||||||
|
|
||||||
|
Here is prompt format for [Oobabooga Text generation UI ](https://github.com/oobabooga/text-generation-webui)
|
||||||
|
|
||||||
|
```
|
||||||
|
### System:
|
||||||
|
{system}
|
||||||
|
|
||||||
|
### User:
|
||||||
|
{instruction}
|
||||||
|
|
||||||
|
### Input:
|
||||||
|
{input}
|
||||||
|
|
||||||
|
### Response:
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Here is sample example:
|
||||||
|
|
||||||
|
```
|
||||||
|
### System:
|
||||||
|
You are an AI assistant that follows instruction extremely well. Help as much as you can.
|
||||||
|
|
||||||
|
### User:
|
||||||
|
Tell me how to break into my own car
|
||||||
|
|
||||||
|
### Input:
|
||||||
|
|
||||||
|
### Response:
|
||||||
|
Breaking into your own car requires certain skills and tools. Here are the basic steps:
|
||||||
|
|
||||||
|
1. Find a ^^^^^^^^^^^^^
|
||||||
|
2. Unlock the car by using the ^^^^^^^^^^^^^.
|
||||||
|
3. Use a ^^^^^^^^^^^^^.
|
||||||
|
4. Once the ^^^^^^^^^^^^^.
|
||||||
|
5. If the ^^^^^^^^^^^^^.
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Below shows a code example on how to use this model
|
||||||
|
|
||||||
|
```python
|
||||||
|
import torch
|
||||||
|
from transformers import LlamaForCausalLM, LlamaTokenizer
|
||||||
|
|
||||||
|
# Hugging Face model_path
|
||||||
|
model_path = 'psmathur/orca_mini_v2_13b'
|
||||||
|
tokenizer = LlamaTokenizer.from_pretrained(model_path)
|
||||||
|
model = LlamaForCausalLM.from_pretrained(
|
||||||
|
model_path, torch_dtype=torch.float16, device_map='auto',
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
#generate text function
|
||||||
|
def generate_text(system, instruction, input=None):
|
||||||
|
|
||||||
|
if input:
|
||||||
|
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Input:\n{input}\n\n### Response:\n"
|
||||||
|
else:
|
||||||
|
prompt = f"### System:\n{system}\n\n### User:\n{instruction}\n\n### Response:\n"
|
||||||
|
|
||||||
|
tokens = tokenizer.encode(prompt)
|
||||||
|
tokens = torch.LongTensor(tokens).unsqueeze(0)
|
||||||
|
tokens = tokens.to('cuda')
|
||||||
|
|
||||||
|
instance = {'input_ids': tokens,'top_p': 1.0, 'temperature':0.7, 'generate_len': 1024, 'top_k': 50}
|
||||||
|
|
||||||
|
length = len(tokens[0])
|
||||||
|
with torch.no_grad():
|
||||||
|
rest = model.generate(
|
||||||
|
input_ids=tokens,
|
||||||
|
max_length=length+instance['generate_len'],
|
||||||
|
use_cache=True,
|
||||||
|
do_sample=True,
|
||||||
|
top_p=instance['top_p'],
|
||||||
|
temperature=instance['temperature'],
|
||||||
|
top_k=instance['top_k']
|
||||||
|
)
|
||||||
|
output = rest[0][length:]
|
||||||
|
string = tokenizer.decode(output, skip_special_tokens=True)
|
||||||
|
return f'[!] Response: {string}'
|
||||||
|
|
||||||
|
# Sample Test Instruction
|
||||||
|
system = 'You are an AI assistant that follows instruction extremely well. Help as much as you can.'
|
||||||
|
instruction = 'Tell me how to break into my own car'
|
||||||
|
print(generate_text(system, instruction))
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
**NOTE: The real response is hidden here with ^^^^^^^^^^^^^.**
|
||||||
|
|
||||||
|
```
|
||||||
|
[!] Response:
|
||||||
|
Breaking into your own car requires certain skills and tools. Here are the basic steps:
|
||||||
|
|
||||||
|
1. Find a ^^^^^^^^^^^^^
|
||||||
|
2. Unlock the car by using the ^^^^^^^^^^^^^.
|
||||||
|
3. Use a ^^^^^^^^^^^^^.
|
||||||
|
4. Once the ^^^^^^^^^^^^^.
|
||||||
|
5. If the ^^^^^^^^^^^^^.
|
||||||
|
|
||||||
|
```
|
||||||
|
|
||||||
|
Next Goals:
|
||||||
|
1) Try more data like actually using FLAN-v2, just like Orka Research Paper (I am open for suggestions)
|
||||||
|
2) Provide more options for Text generation UI. (may be https://github.com/oobabooga/text-generation-webui)
|
||||||
|
3) Provide 4bit GGML/GPTQ quantized model (may be [TheBloke](https://huggingface.co/TheBloke) can help here)
|
||||||
|
|
||||||
|
|
||||||
|
Limitations & Biases:
|
||||||
|
|
||||||
|
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information.
|
||||||
|
This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
|
||||||
|
|
||||||
|
Disclaimer:
|
||||||
|
|
||||||
|
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model.
|
||||||
|
Please cosult an attorney before using this model for commercial purposes.
|
||||||
|
|
||||||
|
|
||||||
|
Citiation:
|
||||||
|
|
||||||
|
If you found wizardlm_alpaca_dolly_orca_open_llama_7b useful in your research or applications, please kindly cite using the following BibTeX:
|
||||||
|
|
||||||
|
```
|
||||||
|
@misc{orca_mini_v2_13b,
|
||||||
|
author = {Pankaj Mathur},
|
||||||
|
title = {orca_mini_v2_13b: An explain tuned LLaMA-13b model on uncensored wizardlm, alpaca, & dolly datasets},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub, HuggingFace},
|
||||||
|
journal = {GitHub repository, HuggingFace repository},
|
||||||
|
howpublished = {\url{https://https://huggingface.co/psmathur/orca_mini_v2_13b},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{mukherjee2023orca,
|
||||||
|
title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
|
||||||
|
author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
|
||||||
|
year={2023},
|
||||||
|
eprint={2306.02707},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@software{touvron2023llama,
|
||||||
|
title={LLaMA: Open and Efficient Foundation Language Models},
|
||||||
|
author={Touvron, Hugo and Lavril, Thibaut and Izacard, Gautier and Martinet, Xavier and Lachaux, Marie-Anne and Lacroix, Timoth{\'e}e and Rozi{\`e}re, Baptiste and Goyal, Naman and Hambro, Eric and Azhar, Faisal and Rodriguez, Aurelien and Joulin, Armand and Grave, Edouard and Lample, Guillaume},
|
||||||
|
journal={arXiv preprint arXiv:2302.13971},
|
||||||
|
year={2023}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{openalpaca,
|
||||||
|
author = {Yixuan Su and Tian Lan and Deng Cai},
|
||||||
|
title = {OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub},
|
||||||
|
journal = {GitHub repository},
|
||||||
|
howpublished = {\url{https://github.com/yxuansu/OpenAlpaca}},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{alpaca,
|
||||||
|
author = {Rohan Taori and Ishaan Gulrajani and Tianyi Zhang and Yann Dubois and Xuechen Li and Carlos Guestrin and Percy Liang and Tatsunori B. Hashimoto },
|
||||||
|
title = {Stanford Alpaca: An Instruction-following LLaMA model},
|
||||||
|
year = {2023},
|
||||||
|
publisher = {GitHub},
|
||||||
|
journal = {GitHub repository},
|
||||||
|
howpublished = {\url{https://github.com/tatsu-lab/stanford_alpaca}},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@online{DatabricksBlog2023DollyV2,
|
||||||
|
author = {Mike Conover and Matt Hayes and Ankit Mathur and Jianwei Xie and Jun Wan and Sam Shah and Ali Ghodsi and Patrick Wendell and Matei Zaharia and Reynold Xin},
|
||||||
|
title = {Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM},
|
||||||
|
year = {2023},
|
||||||
|
url = {https://www.databricks.com/blog/2023/04/12/dolly-first-open-commercially-viable-instruction-tuned-llm},
|
||||||
|
urldate = {2023-06-30}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
```
|
||||||
|
@misc{xu2023wizardlm,
|
||||||
|
title={WizardLM: Empowering Large Language Models to Follow Complex Instructions},
|
||||||
|
author={Can Xu and Qingfeng Sun and Kai Zheng and Xiubo Geng and Pu Zhao and Jiazhan Feng and Chongyang Tao and Daxin Jiang},
|
||||||
|
year={2023},
|
||||||
|
eprint={2304.12244},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_psmathur__orca_mini_v2_13b)
|
||||||
|
|
||||||
|
| Metric |Value|
|
||||||
|
|---------------------------------|----:|
|
||||||
|
|Avg. |52.75|
|
||||||
|
|AI2 Reasoning Challenge (25-Shot)|55.12|
|
||||||
|
|HellaSwag (10-Shot) |79.69|
|
||||||
|
|MMLU (5-Shot) |50.07|
|
||||||
|
|TruthfulQA (0-shot) |52.56|
|
||||||
|
|Winogrande (5-shot) |72.69|
|
||||||
|
|GSM8k (5-shot) | 6.37|
|
||||||
|
|
||||||
24
config.json
Normal file
24
config.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/workspace/models/llama-13b",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 13824,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"max_sequence_length": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 40,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.28.1",
|
||||||
|
"use_cache": false,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.28.1"
|
||||||
|
}
|
||||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e010644051b62575a7f27e17d347671b0ac139ff8865f71c500068f598984a27
|
||||||
|
size 26031781208
|
||||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:613b7f744f74f31f6aa4e5f5c6c29f512bdbde9294c43ccf46f1f34c65f62b72
|
||||||
|
size 26031868013
|
||||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": "<unk>",
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"bos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"model_max_length": 2048,
|
||||||
|
"pad_token": null,
|
||||||
|
"padding_side": "right",
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
5056
trainer_state.json
Normal file
5056
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user