Instructions to use karths/coder_commit_base_32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use karths/coder_commit_base_32B with Transformers:

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

pipe = pipeline("text-generation", model="karths/coder_commit_base_32B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("karths/coder_commit_base_32B")
model = AutoModelForCausalLM.from_pretrained("karths/coder_commit_base_32B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use karths/coder_commit_base_32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "karths/coder_commit_base_32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "karths/coder_commit_base_32B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/karths/coder_commit_base_32B

SGLang

How to use karths/coder_commit_base_32B 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 "karths/coder_commit_base_32B" \
    --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": "karths/coder_commit_base_32B",
		"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 "karths/coder_commit_base_32B" \
        --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": "karths/coder_commit_base_32B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use karths/coder_commit_base_32B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for karths/coder_commit_base_32B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for karths/coder_commit_base_32B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for karths/coder_commit_base_32B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="karths/coder_commit_base_32B",
    max_seq_length=2048,
)

Docker Model Runner
How to use karths/coder_commit_base_32B with Docker Model Runner:
```
docker model run hf.co/karths/coder_commit_base_32B
```

coder_commit_base_32B

File size: 826 Bytes

100052d

{
  "_name_or_path": "unsloth/qwen2.5-coder-32b-bnb-4bit",
  "architectures": [
    "Qwen2ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151643,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 27648,
  "max_position_embeddings": 32768,
  "max_window_layers": 64,
  "model_type": "qwen2",
  "num_attention_heads": 40,
  "num_hidden_layers": 64,
  "num_key_value_heads": 8,
  "pad_token_id": 151665,
  "rms_norm_eps": 1e-05,
  "rope_scaling": null,
  "rope_theta": 1000000.0,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.49.0",
  "unsloth_fixed": true,
  "unsloth_version": "2025.3.5",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 152064
}