Instructions to use TryMore/TryMoreGPT-delta-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TryMore/TryMoreGPT-delta-7b with Transformers:

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

pipe = pipeline("text-generation", model="TryMore/TryMoreGPT-delta-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TryMore/TryMoreGPT-delta-7b")
model = AutoModelForMultimodalLM.from_pretrained("TryMore/TryMoreGPT-delta-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TryMore/TryMoreGPT-delta-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TryMore/TryMoreGPT-delta-7b

SGLang

How to use TryMore/TryMoreGPT-delta-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 "TryMore/TryMoreGPT-delta-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": "TryMore/TryMoreGPT-delta-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 "TryMore/TryMoreGPT-delta-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": "TryMore/TryMoreGPT-delta-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TryMore/TryMoreGPT-delta-7b with Docker Model Runner:
```
docker model run hf.co/TryMore/TryMoreGPT-delta-7b
```

注意：这个 "delta model"不能直接使用。用户必须将其应用于原始的 LLaMA 权重之上，以获得的TryMoreGPT权重。详情请见https://github.com/TrustedLLM/TryMoreGPT

介绍

TryMoreGPT-7B，是由揣摩研习社开源的聊天机器人，本项目以LLaMA作为基座模型，使用Vicuna训练框架，在shareGPT，Alpaca中英数据集，COIG中通用价值观，代码编写数据集完成指令微调。在中文表现上相较于原始Vicuna以及一众中文聊天机器人有具有非常有竞争力的表现。

TryMoreGPT-7B is an open-source chat robot developed by Chuanmo Research Institute. This project uses LLaMA as the base model, uses the Vicuna training framework to complete instruction fine-tuning with shareGPT and Alpaca Chinese-English dataset, universal values and code writing dataset in COIG. In terms of Chinese performance, it has a very competitive performance compared to the original Vicuna and other Chinese chatbots.

Downloads last month: 4