Edit model card

repo_clone_081124

name: mistral-7b-instruct-v0.3-chinese-chat-4bit
license: apache-2.0
tags:
- Mistral
- text-generation
- text2text-generation
- natural-language
- multilingual
- orpo
- llama-factory
- shenzhi_wang
- hiyouga
type:
- 4GB
- llm
- chat
- role-playing
- writing
- code
- math
- mistral
config:
- ctx=32768
- 4bit
resolutions: 
datasets: huggingface
language:
- en
- zh
size: 4113289024
use: 
shortcomings: 
sources: 
- https://arxiv.org/abs/2301.13688
- https://arxiv.org/abs/2306.02707
- https://arxiv.org/abs/2310.06825
- https://arxiv.org/abs/2403.07691
funded_by: 
train_hardware: 
pipeline_tag: text-generation
examples: 
- "You are a helpful assistant."
- "简要地介绍一下什么是机器学习"
Downloads last month
67
GGUF
Model size
7.25B params
Architecture
llama

4-bit

Inference Examples
Inference API (serverless) is not available, repository is disabled.