Instructions to use YeungNLP/firefly-bloom-1b4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YeungNLP/firefly-bloom-1b4 with Transformers:

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

pipe = pipeline("text-generation", model="YeungNLP/firefly-bloom-1b4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YeungNLP/firefly-bloom-1b4")
model = AutoModelForCausalLM.from_pretrained("YeungNLP/firefly-bloom-1b4")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YeungNLP/firefly-bloom-1b4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YeungNLP/firefly-bloom-1b4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YeungNLP/firefly-bloom-1b4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/YeungNLP/firefly-bloom-1b4

SGLang

How to use YeungNLP/firefly-bloom-1b4 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 "YeungNLP/firefly-bloom-1b4" \
    --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": "YeungNLP/firefly-bloom-1b4",
		"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 "YeungNLP/firefly-bloom-1b4" \
        --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": "YeungNLP/firefly-bloom-1b4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use YeungNLP/firefly-bloom-1b4 with Docker Model Runner:
```
docker model run hf.co/YeungNLP/firefly-bloom-1b4
```

YeungNLP commited on Apr 5, 2023

Commit

8aac2ae

1 Parent(s): 5c2c405

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 # Firefly(流萤): 中文对话式大语言模型
 ## 项目简介
-项目地址：[Firefly（流萤）:中文对话式大语言模型](https://github.com/yangjianxin1/Firefly)
 ![firefly_logo](firefly_logo.png)
 **Firefly（流萤）** 是一个开源的中文对话式大语言模型，使用指令微调（Instruction Tuning）在中文数据集上进行调优。同时使用了词表裁剪、ZeRO、张量并行等技术，有效降低显存消耗和提高训练效率。
@@ -79,6 +79,7 @@ Bloom是个多语言模型，由于需要兼容多语言，所以词表有25w之
 ## 训练细节
 在训练时，对于每条样本，我们将input与target处理成如下格式，然后输出模型中。
 ```
 <s>input</s></s>target</s>
@@ -162,7 +163,8 @@ Bloom是个多语言模型，由于需要兼容多语言，所以词表有25w之
 ## 关注我们
-![gongzhonghao](gongzhonghao.jpeg)

 # Firefly(流萤): 中文对话式大语言模型
 ## 项目简介
+项目地址：[Firefly（流萤）: 中文对话式大语言模型](https://github.com/yangjianxin1/Firefly)， 如果您觉得此模型对您有帮助，请like此模型并在Github项目中star我们。
 ![firefly_logo](firefly_logo.png)
 **Firefly（流萤）** 是一个开源的中文对话式大语言模型，使用指令微调（Instruction Tuning）在中文数据集上进行调优。同时使用了词表裁剪、ZeRO、张量并行等技术，有效降低显存消耗和提高训练效率。
 ## 训练细节
 在训练时，对于每条样本，我们将input与target处理成如下格式，然后输出模型中。
 ```
 <s>input</s></s>target</s>
 ## 关注我们
+![gongzhonghao](
+gongzhonghao.jpeg)