Instructions to use 11-47/codegemma-2b-cot-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 11-47/codegemma-2b-cot-reasoning with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/codegemma-1.1-2b")
model = PeftModel.from_pretrained(base_model, "11-47/codegemma-2b-cot-reasoning")

Transformers

How to use 11-47/codegemma-2b-cot-reasoning with Transformers:

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

pipe = pipeline("text-generation", model="11-47/codegemma-2b-cot-reasoning")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("11-47/codegemma-2b-cot-reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 11-47/codegemma-2b-cot-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "11-47/codegemma-2b-cot-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "11-47/codegemma-2b-cot-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/11-47/codegemma-2b-cot-reasoning

SGLang

How to use 11-47/codegemma-2b-cot-reasoning 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 "11-47/codegemma-2b-cot-reasoning" \
    --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": "11-47/codegemma-2b-cot-reasoning",
		"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 "11-47/codegemma-2b-cot-reasoning" \
        --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": "11-47/codegemma-2b-cot-reasoning",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use 11-47/codegemma-2b-cot-reasoning with Docker Model Runner:
```
docker model run hf.co/11-47/codegemma-2b-cot-reasoning
```

11-47 commited on about 10 hours ago

Commit

8baf6e2

verified ·

1 Parent(s): 1f1dfa4

Training in progress, step 2163

Browse files

Files changed (1) hide show

adapter_model.safetensors +1 -1

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6c18ce4bc513cfe090b33f266e4b2ac506eceb391c0404be37178f38574d2ab
 size 39256456

 version https://git-lfs.github.com/spec/v1
+oid sha256:7210e002576b884a22c09c44a850cce5fd0c664f055fd80fb6be3e09cece6225
 size 39256456