Instructions to use MaziyarPanahi/calme-2.8-qwen2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaziyarPanahi/calme-2.8-qwen2-7b with Transformers:

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

pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.8-qwen2-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
model = AutoModelForMultimodalLM.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MaziyarPanahi/calme-2.8-qwen2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaziyarPanahi/calme-2.8-qwen2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaziyarPanahi/calme-2.8-qwen2-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaziyarPanahi/calme-2.8-qwen2-7b

SGLang

How to use MaziyarPanahi/calme-2.8-qwen2-7b 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 "MaziyarPanahi/calme-2.8-qwen2-7b" \
    --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": "MaziyarPanahi/calme-2.8-qwen2-7b",
		"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 "MaziyarPanahi/calme-2.8-qwen2-7b" \
        --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": "MaziyarPanahi/calme-2.8-qwen2-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MaziyarPanahi/calme-2.8-qwen2-7b with Docker Model Runner:
```
docker model run hf.co/MaziyarPanahi/calme-2.8-qwen2-7b
```

MaziyarPanahi commited on Jul 21, 2024

Commit

06d159d

verified ·

1 Parent(s): aade7b0

Update README.md (#10)

Browse files

- Update README.md (b08fbd263a8720f7c66492c18b03b3e22b23e5ae)

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ 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
@@ -28,13 +28,13 @@ datasets:
 <img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
-# 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](https://huggingface.co/MaziyarPanahi/Qwen2-7B-Instruct-v0.8-GGUF)
 # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
@@ -68,7 +68,7 @@ from transformers import pipeline
 messages = [
     {"role": "user", "content": "Who are you?"},
 ]
-pipe = pipeline("text-generation", model="MaziyarPanahi/Qwen2-7B-Instruct-v0.8")
 pipe(messages)
@@ -76,6 +76,6 @@ pipe(messages)
 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")
 ```

 model_creator: MaziyarPanahi
 quantized_by: MaziyarPanahi
 base_model: Qwen/Qwen2-7B
+model_name: calme-2.8-qwen2-7b
 datasets:
 - nvidia/HelpSteer2
 - teknium/OpenHermes-2.5
 <img src="./qwen2-fine-tunes-maziyar-panahi.webp" alt="Qwen2 fine-tune" width="500" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+# MaziyarPanahi/calme-2.8-qwen2-7b
 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/calme-2.8-qwen2-7b-GGUF](https://huggingface.co/MaziyarPanahi/calme-2.8-qwen2-7b-GGUF)
 # 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
 messages = [
     {"role": "user", "content": "Who are you?"},
 ]
+pipe = pipeline("text-generation", model="MaziyarPanahi/calme-2.8-qwen2-7b")
 pipe(messages)
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
+model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-2.8-qwen2-7b")
 ```