Instructions to use Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw with Transformers:

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

pipe = pipeline("text-generation", model="Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw")
model = AutoModelForCausalLM.from_pretrained("Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw

SGLang

How to use Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw 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 "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw with Docker Model Runner:
```
docker model run hf.co/Suparious/Qwen2-7B-Instruct-v0.8-exl2-6.5bpw
```

Qwen2-7B-Instruct-v0.8-exl2-6.5bpw / README.md

Suparious

adding model

67a8301 about 2 years ago

preview code

Raw History Blame Contribute Delete

1.76 kB

metadata

license: apache-2.0
language:
  - en
pipeline_tag: text-generation
tags:
  - chat
  - qwen
  - qwen2
  - finetune
  - chatml
  - OpenHermes-2.5
  - HelpSteer2
  - Orca
  - SlimOrca
library_name: transformers
inference: false
model_creator: MaziyarPanahi
quantized_by: MaziyarPanahi
base_model: Qwen/Qwen2-7B
model_name: Qwen2-7B-Instruct-v0.8
datasets:
  - nvidia/HelpSteer2
  - teknium/OpenHermes-2.5
  - microsoft/orca-math-word-problems-200k
  - Open-Orca/SlimOrca

MaziyarPanahi/Qwen2-7B-Instruct-v0.8

This is a fine-tuned version of the Qwen/Qwen2-7B model. It aims to improve the base model across all benchmarks.

⚡ Quantized GGUF

All GGUF models are available here: MaziyarPanahi/Qwen2-7B-Instruct-v0.8-GGUF

🏆 Open LLM Leaderboard Evaluation Results

coming soon!

Prompt Template

This model uses ChatML prompt template:

<|im_start|>system
{System}
<|im_end|>
<|im_start|>user
{User}
<|im_end|>
<|im_start|>assistant
{Assistant}

How to use


# Use a pipeline as a high-level helper

from transformers import pipeline

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="MaziyarPanahi/Qwen2-7B-Instruct-v0.8")
pipe(messages)


# Load model directly

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Qwen2-7B-Instruct-v0.8")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Qwen2-7B-Instruct-v0.8")