Instructions to use natankatz/chan_model_class with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use natankatz/chan_model_class with Transformers:

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

pipe = pipeline("text-generation", model="natankatz/chan_model_class")

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

tokenizer = AutoTokenizer.from_pretrained("natankatz/chan_model_class")
model = AutoModelForCausalLM.from_pretrained("natankatz/chan_model_class", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use natankatz/chan_model_class with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/natankatz/chan_model_class

SGLang

How to use natankatz/chan_model_class 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 "natankatz/chan_model_class" \
    --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": "natankatz/chan_model_class",
		"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 "natankatz/chan_model_class" \
        --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": "natankatz/chan_model_class",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use natankatz/chan_model_class with Docker Model Runner:
```
docker model run hf.co/natankatz/chan_model_class
```

chan_model_class

Commit History

Feb 23, 2025

05:23
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
bdd4fc9

Oct 13, 2023

09:10
Upload tokenizer

natankatz

542bac3
09:10
Upload model

natankatz

50bdd35
08:54
Upload tokenizer

natankatz

54f8506
08:54
Upload model

natankatz

7e578e3
08:32
Upload tokenizer

natankatz

2365e7b
08:32
Upload model

natankatz

8eb6448

Oct 12, 2023

22:02
Upload tokenizer

natankatz

979c6cc
22:02
Upload model

natankatz

d5667e5
21:40
Upload tokenizer

natankatz

c253453
21:40
Upload model

natankatz

e0e8e1d
21:18
Upload tokenizer

natankatz

d5e3c7f
21:18
Upload model

natankatz

c666106
21:05
Upload tokenizer

natankatz

61a3afa
21:05
Upload model

natankatz

c17d1eb
20:52
Upload tokenizer

natankatz

e9acd2e
20:52
Upload model

natankatz

4c62dc7
19:02
Upload tokenizer

natankatz

17db08e
19:02
Upload model

natankatz

eb7ca58
19:02
initial commit

natankatz

4f36094

Commit History

Feb 23, 2025

Adding `safetensors` variant of this model⁠

Oct 13, 2023

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Oct 12, 2023

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Upload tokenizer

Upload model

Upload tokenizer

Upload model

initial commit