Instructions to use AscendKernelGen/KernelGen-LM-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AscendKernelGen/KernelGen-LM-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="AscendKernelGen/KernelGen-LM-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AscendKernelGen/KernelGen-LM-1.7B")
model = AutoModelForCausalLM.from_pretrained("AscendKernelGen/KernelGen-LM-1.7B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AscendKernelGen/KernelGen-LM-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AscendKernelGen/KernelGen-LM-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AscendKernelGen/KernelGen-LM-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AscendKernelGen/KernelGen-LM-1.7B

SGLang

How to use AscendKernelGen/KernelGen-LM-1.7B 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 "AscendKernelGen/KernelGen-LM-1.7B" \
    --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": "AscendKernelGen/KernelGen-LM-1.7B",
		"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 "AscendKernelGen/KernelGen-LM-1.7B" \
        --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": "AscendKernelGen/KernelGen-LM-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AscendKernelGen/KernelGen-LM-1.7B with Docker Model Runner:
```
docker model run hf.co/AscendKernelGen/KernelGen-LM-1.7B
```

KernelGen-LM-1.7B

Commit History

Update README.md

58dd498
verified

AscendKernelGen commited on 10 days ago

Update README.md

1dd5d28
verified

AscendKernelGen commited on 10 days ago

Upload 2 files

0403965
verified

AscendKernelGen commited on 10 days ago

Update README.md

ec9b133
verified

AscendKernelGen commited on 11 days ago

Update README.md

819572b
verified

AscendKernelGen commited on 11 days ago

Update README.md

e1e73c0
verified

AscendKernelGen commited on 14 days ago

Update README.md

0f7e292
verified

AscendKernelGen commited on 15 days ago

Add metadata and improve model card (#1)

0bfb08c

AscendKernelGen

nielsr HF Staff commited on 17 days ago

Update README.md

009d33b
verified

AscendKernelGen commited on Mar 13

Update README.md

97bb180
verified

AscendKernelGen commited on Mar 13

Update README.md

158d0c6
verified

AscendKernelGen commited on Mar 13

Create README.md

c4ce8ed
verified

AscendKernelGen commited on Jan 26

Upload folder using huggingface_hub

c19f399
verified

AscendKernelGen commited on Jan 23

initial commit

d901659
verified

AscendKernelGen commited on Jan 23

Commit History

Update README.md 58dd498 verified

Update README.md 1dd5d28 verified

Upload 2 files 0403965 verified

Update README.md ec9b133 verified

Update README.md 819572b verified

Update README.md e1e73c0 verified

Update README.md 0f7e292 verified

Add metadata and improve model card (#1) 0bfb08c

Update README.md 009d33b verified

Update README.md 97bb180 verified

Update README.md 158d0c6 verified

Create README.md c4ce8ed verified

Upload folder using huggingface_hub c19f399 verified

initial commit d901659 verified

Update README.md

58dd498
verified

Update README.md

1dd5d28
verified

Upload 2 files

0403965
verified

Update README.md

ec9b133
verified

Update README.md

819572b
verified

Update README.md

e1e73c0
verified

Update README.md

0f7e292
verified

Add metadata and improve model card (#1)

0bfb08c

Update README.md

009d33b
verified

Update README.md

97bb180
verified

Update README.md

158d0c6
verified

Create README.md

c4ce8ed
verified

Upload folder using huggingface_hub

c19f399
verified

initial commit

d901659
verified