Instructions to use JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat with Transformers:

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

pipe = pipeline("text-generation", model="JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat")
model = AutoModelForCausalLM.from_pretrained("JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat

SGLang

How to use JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat 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 "JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat" \
    --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": "JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat",
		"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 "JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat" \
        --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": "JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat with Docker Model Runner:
```
docker model run hf.co/JosephusCheung/Qwen-VL-LLaMAfied-7B-Chat
```

This is the LLaMAfied replica of Qwen/Qwen-VL-Chat (Original Version before 25.09.2023), recalibrated to fit the original LLaMA/LLaMA-2-like model structure.

You can use LlamaForCausalLM for model inference, which is the same as LLaMA/LLaMA-2 models (using GPT2Tokenizer converted from the original tiktoken, by vonjack).

The model has been edited to be white-labelled, meaning the model will no longer call itself a Qwen.

Up until now, the model has undergone numerical alignment of weights and preliminary reinforcement learning in order to align with the original model. Some errors and outdated knowledge have been addressed through model editing methods. This model remains completely equivalent to the original version, without having any dedicated supervised finetuning on downstream tasks or other extensive conversation datasets.

PROMPT FORMAT: chatml

Downloads last month: 1,019