Downloads · 30 days
3
14% of all-time downloads
Azure99_-_blossom-v4-qwen1_5-4b-4bits
RichardErkhov/Azure99_-_blossom-v4-qwen1_5-4b-4bits
Azure99_-_blossom-v4-qwen1_5-4b-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
22
Public
Parameters
4B
3.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 100%
Parameter types
How the weights are stored.
U83.2B · 79%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
blossom-v4-qwen1_5-4b - bnb 4bits
- Model creator: https://huggingface.co/Azure99/
- Original model: https://huggingface.co/Azure99/blossom-v4-qwen1_5-4b/
Original model description:
license: apache-2.0 datasets:
- Azure99/blossom-chat-v2
- Azure99/blossom-math-v3
- Azure99/blossom-wizard-v2
- Azure99/blossom-orca-v2 language:
- zh
- en pipeline_tag: text-generation
BLOSSOM-v4-qwen1_5-4b
介绍
Blossom是一个对话式语言模型，基于Qwen1.5-4B预训练模型，在Blossom Orca/Wizard/Chat/Math混合数据集上进行指令精调得来。Blossom拥有强大的通用能力及上下文理解能力，此外，训练使用的高质量中英文数据集也进行了开源。
训练分为两阶段，第一阶段使用100K Wizard、100K Orca、20K Math单轮指令数据集，训练1个epoch；第二阶段使用50K Blossom chat多轮对话数据集、以及上一阶段中随机采样2%的数据，训练3个epoch。
推理
推理采用对话续写的形式。
单轮对话
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: 你好
|Bot|:
多轮对话
A chat between a human and an artificial intelligence bot. The bot gives helpful, detailed, and polite answers to the human's questions.
|Human|: 你好
|Bot|: 你好，有什么我能帮助你的？<|endoftext|>
|Human|: 介绍下中国的首都吧
|Bot|:
注意：在历史对话的Bot输出结尾，拼接一个<|endoftext|>
- Type
- qwen2
- Created
- Oct 26, 2024
- Updated
- Oct 26, 2024