Instructions to use FreedomIntelligence/HuatuoGPT2-34B-4bits with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FreedomIntelligence/HuatuoGPT2-34B-4bits with Transformers:

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

pipe = pipeline("text-generation", model="FreedomIntelligence/HuatuoGPT2-34B-4bits", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT2-34B-4bits", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FreedomIntelligence/HuatuoGPT2-34B-4bits with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomIntelligence/HuatuoGPT2-34B-4bits"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FreedomIntelligence/HuatuoGPT2-34B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FreedomIntelligence/HuatuoGPT2-34B-4bits

SGLang

How to use FreedomIntelligence/HuatuoGPT2-34B-4bits 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 "FreedomIntelligence/HuatuoGPT2-34B-4bits" \
    --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": "FreedomIntelligence/HuatuoGPT2-34B-4bits",
		"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 "FreedomIntelligence/HuatuoGPT2-34B-4bits" \
        --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": "FreedomIntelligence/HuatuoGPT2-34B-4bits",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FreedomIntelligence/HuatuoGPT2-34B-4bits with Docker Model Runner:
```
docker model run hf.co/FreedomIntelligence/HuatuoGPT2-34B-4bits
```

HuatuoGPT2-34B-4bits / README.md

jymcc

Update README.md

b8712fa over 2 years ago

preview code

Raw

History Blame Contribute Delete

1.12 kB

	---
	language:
	- zh
	license: apache-2.0
	tasks:
	- text-generation
	---

	<!-- markdownlint-disable first-line-h1 -->
	<!-- markdownlint-disable html -->
	<div align="center">
	<h1>
	HuatuoGPT2-34B-4bits
	</h1>
	</div>

	<div align="center">
	<a href="https://github.com/FreedomIntelligence/HuatuoGPT-II" target="_blank">GitHub</a> \| <a href="https://arxiv.org/pdf/2311.09774.pdf" target="_blank">Our Paper</a>
	</div>

	# <span id="Start">Quick Start</span>

	```Python
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer
	from transformers.generation.utils import GenerationConfig
	tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/HuatuoGPT2-34B-4bits", use_fast=True, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT2-34B-4bits", device_map="auto", torch_dtype="auto", trust_remote_code=True)
	model.generation_config = GenerationConfig.from_pretrained("FreedomIntelligence/HuatuoGPT2-34B-4bits")
	messages = []
	messages.append({"role": "user", "content": "肚子疼怎么办？"})
	response = model.HuatuoChat(tokenizer, messages)
	print(response)
	```