Instructions to use Azure99/blossom-v2-llama2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azure99/blossom-v2-llama2-7b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Azure99/blossom-v2-llama2-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azure99/blossom-v2-llama2-7b")
model = AutoModelForCausalLM.from_pretrained("Azure99/blossom-v2-llama2-7b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azure99/blossom-v2-llama2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azure99/blossom-v2-llama2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azure99/blossom-v2-llama2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Azure99/blossom-v2-llama2-7b

SGLang

How to use Azure99/blossom-v2-llama2-7b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Azure99/blossom-v2-llama2-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azure99/blossom-v2-llama2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Azure99/blossom-v2-llama2-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azure99/blossom-v2-llama2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Azure99/blossom-v2-llama2-7b with Docker Model Runner:
```
docker model run hf.co/Azure99/blossom-v2-llama2-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BLOSSOM-v2-llama2-7b

💻Github • 🚀Blossom Chat Demo

介绍

Blossom是一个对话式语言模型，基于Llama-2-7b预训练模型，在Blossom、Wizard、Dolphin混合数据集上进行指令精调得来。

训练分为两阶段，第一阶段使用120K Wizard、180K Dolphin单轮指令数据集，训练1个epoch；第二阶段使用60K Blossom chat、2K Blossom math多轮对话数据集，训练3个epoch。

注意：Llama-2-7b预训练模型的中文知识较为欠缺，因此对于中文场景，更推荐使用blossom-v2-baichuan-7b

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？</s>
|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</s>

Downloads last month: 781

Model tree for Azure99/blossom-v2-llama2-7b

Quantizations

3 models

Azure99
/

blossom-v2-llama2-7b

BLOSSOM-v2-llama2-7b

介绍

推理

Model tree for Azure99/blossom-v2-llama2-7b

Datasets used to train Azure99/blossom-v2-llama2-7b