Instructions to use Azure99/blossom-v3-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azure99/blossom-v3-mistral-7b with Transformers:

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

pipe = pipeline("text-generation", model="Azure99/blossom-v3-mistral-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azure99/blossom-v3-mistral-7b")
model = AutoModelForCausalLM.from_pretrained("Azure99/blossom-v3-mistral-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Azure99/blossom-v3-mistral-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azure99/blossom-v3-mistral-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-v3-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Azure99/blossom-v3-mistral-7b

SGLang

How to use Azure99/blossom-v3-mistral-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-v3-mistral-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-v3-mistral-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-v3-mistral-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-v3-mistral-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Azure99/blossom-v3-mistral-7b with Docker Model Runner:
```
docker model run hf.co/Azure99/blossom-v3-mistral-7b
```

Azure99 commited on Nov 20, 2023

Commit

fc2ecf4

1 Parent(s): 029e6f2

Update README.md

Browse files

Files changed (1) hide show

README.md +41 -0

README.md CHANGED Viewed

@@ -1,3 +1,44 @@
 ---
 license: apache-2.0
 ---

 ---
 license: apache-2.0
+datasets:
+- Azure99/blossom-chat-v1
+- Azure99/blossom-math-v2
+- Azure99/blossom-wizard-v1
+- Azure99/blossom-orca-v1
+language:
+- zh
+- en
 ---
+# **BLOSSOM-v3-mistral-7b**
+### 介绍
+Blossom是一个对话式语言模型，基于Mistral-7B-v0.1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单轮指令数据集，训练1个epoch；第二阶段使用2K Blossom math数学推理数据集、50K Blossom chat多轮对话数据集、以及上一阶段中随机采样1%的数据，训练3个epoch。
+注意：Mistral-7B-v0.1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-v3-baichuan2-7b](https://huggingface.co/Azure99/blossom-v3-baichuan2-7b)
+### 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&lt;/s&gt;