Quantization made by Richard Erkhov.
ReflectionCoder-CL-34B - GGUF
- Model creator: https://huggingface.co/SenseLLM/
- Original model: https://huggingface.co/SenseLLM/ReflectionCoder-CL-34B/
| Name | Quant method | Size |
|---|---|---|
| ReflectionCoder-CL-34B.Q2_K.gguf | Q2_K | 11.65GB |
| ReflectionCoder-CL-34B.Q3_K_S.gguf | Q3_K_S | 13.6GB |
| ReflectionCoder-CL-34B.Q3_K.gguf | Q3_K | 15.19GB |
| ReflectionCoder-CL-34B.Q3_K_M.gguf | Q3_K_M | 15.19GB |
| ReflectionCoder-CL-34B.Q3_K_L.gguf | Q3_K_L | 16.55GB |
| ReflectionCoder-CL-34B.IQ4_XS.gguf | IQ4_XS | 16.99GB |
| ReflectionCoder-CL-34B.Q4_0.gguf | Q4_0 | 17.74GB |
| ReflectionCoder-CL-34B.IQ4_NL.gguf | IQ4_NL | 17.92GB |
| ReflectionCoder-CL-34B.Q4_K_S.gguf | Q4_K_S | 17.87GB |
| ReflectionCoder-CL-34B.Q4_K.gguf | Q4_K | 18.83GB |
| ReflectionCoder-CL-34B.Q4_K_M.gguf | Q4_K_M | 18.83GB |
| ReflectionCoder-CL-34B.Q4_1.gguf | Q4_1 | 19.69GB |
| ReflectionCoder-CL-34B.Q5_0.gguf | Q5_0 | 21.64GB |
| ReflectionCoder-CL-34B.Q5_K_S.gguf | Q5_K_S | 21.64GB |
| ReflectionCoder-CL-34B.Q5_K.gguf | Q5_K | 22.2GB |
| ReflectionCoder-CL-34B.Q5_K_M.gguf | Q5_K_M | 22.2GB |
| ReflectionCoder-CL-34B.Q5_1.gguf | Q5_1 | 23.59GB |
| ReflectionCoder-CL-34B.Q6_K.gguf | Q6_K | 25.78GB |
| ReflectionCoder-CL-34B.Q8_0.gguf | Q8_0 | 33.39GB |
Original model description:
license: apache-2.0 datasets: - SenseLLM/ReflectionSeq-GPT - SenseLLM/ReflectionSeq-DS language: - en
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
📄 Paper • 🏠 Repo • 🤖 Models • 📚 Datasets
Introduction
ReflectionCoder is a novel approach that effectively leverages reflection sequences constructed by integrating compiler feedback to improve one-off code generation performance. Please refer to our paper and repo for more details!
Models
| Model | Checkpoint | Size | HumanEval (+) | MBPP (+) | License |
|---|---|---|---|---|---|
| ReflectionCoder-CL-7B | 🤗 HF Link | 7B | 75.0 (68.9) | 72.2 (61.4) | Llama2 |
| ReflectionCoder-CL-34B | 🤗 HF Link | 34B | 70.7 (66.5) | 68.4 (56.6) | Llama2 |
| ReflectionCoder-DS-6.7B | 🤗 HF Link | 6.7B | 80.5 (74.4) | 81.5 (69.6) | DeepSeek |
| ReflectionCoder-DS-33B | 🤗 HF Link | 33B | 82.9 (76.8) | 84.1 (72.0) | DeepSeek |
Datasets
How to Use
Chat Format
Following chat templates of most models, we use two special tokens to wrap the message of user and assistant, i.e., <|user|>, <|assistant|>, and <|endofmessage|>. Furthermore, we use two special tokens to wrap the content of different blocks, i.e., <|text|> and <|endofblock|>. You can use the following template to prompt our ReflectionCoder.
import torch
from transformers import pipeline
chat = [
{"role": "user", "content": "<Your code instruction here>"}
]
generator = pipeline(
model="SenseLLM/ReflectionCoder-CL-34B",
task="text-generation",
torch_dtype=torch.bfloat16,
device_map="auto",
)
result = generator(chat, max_length=128, num_return_sequences=1)
print(result)
Please refer to our GitHub Repo for more technical details.
Citation
If you find this repo useful for your research, please kindly cite our paper:
@misc{ren2024reflectioncoder,
title={ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation},
author={Houxing Ren and Mingjie Zhan and Zhongyuan Wu and Aojun Zhou and Junting Pan and Hongsheng Li},
year={2024},
eprint={2405.17057},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
Acknowledgments
We thank the following amazing projects that truly inspired us:
- Downloads last month
- 11