Instructions to use sayhan/Qwen1.5-72B-Chat-LLaMAfied with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sayhan/Qwen1.5-72B-Chat-LLaMAfied with Transformers:

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

pipe = pipeline("text-generation", model="sayhan/Qwen1.5-72B-Chat-LLaMAfied")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sayhan/Qwen1.5-72B-Chat-LLaMAfied")
model = AutoModelForCausalLM.from_pretrained("sayhan/Qwen1.5-72B-Chat-LLaMAfied")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use sayhan/Qwen1.5-72B-Chat-LLaMAfied with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sayhan/Qwen1.5-72B-Chat-LLaMAfied"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sayhan/Qwen1.5-72B-Chat-LLaMAfied",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sayhan/Qwen1.5-72B-Chat-LLaMAfied

SGLang

How to use sayhan/Qwen1.5-72B-Chat-LLaMAfied 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 "sayhan/Qwen1.5-72B-Chat-LLaMAfied" \
    --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": "sayhan/Qwen1.5-72B-Chat-LLaMAfied",
		"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 "sayhan/Qwen1.5-72B-Chat-LLaMAfied" \
        --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": "sayhan/Qwen1.5-72B-Chat-LLaMAfied",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sayhan/Qwen1.5-72B-Chat-LLaMAfied with Docker Model Runner:
```
docker model run hf.co/sayhan/Qwen1.5-72B-Chat-LLaMAfied
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Description

This repo containst the "LLaMAfied" version of Qwen1.5-72B-Chat by Alibaba Cloud. I used the amazing script made by Minami-su to LLaMAfy the model.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
tokenizer = AutoTokenizer.from_pretrained("sayhan/Qwen1.5-72B-Chat-LLaMAfied")
model = AutoModelForCausalLM.from_pretrained("sayhan/Qwen1.5-72B-Chat-LLaMAfied", torch_dtype="auto", device_map="auto")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

messages = [
    {"role": "user", "content": "Who are you?"}
]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")
inputs = inputs.to("cuda")
generate_ids = model.generate(inputs,max_length=2048, streamer=streamer)

Other LLaMAfied Qwen1.5 Models

The two other sizes of the Qwen1.5 have been LLaMAfied by Minami-su

0.5B: Minami-su/Qwen1.5-0.5B-Chat_llamafy
7B: Minami-su/Qwen1.5-7B-Chat_llamafy

Downloads last month: 10

Model tree for sayhan/Qwen1.5-72B-Chat-LLaMAfied

Quantizations

1 model