Instructions to use Crystalcareai/gemma-codefeedback with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Crystalcareai/gemma-codefeedback with Transformers:

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

pipe = pipeline("text-generation", model="Crystalcareai/gemma-codefeedback")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Crystalcareai/gemma-codefeedback")
model = AutoModelForCausalLM.from_pretrained("Crystalcareai/gemma-codefeedback")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Crystalcareai/gemma-codefeedback with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Crystalcareai/gemma-codefeedback

SGLang

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

Docker Model Runner
How to use Crystalcareai/gemma-codefeedback with Docker Model Runner:
```
docker model run hf.co/Crystalcareai/gemma-codefeedback
```

Crystalcareai commited on Mar 13, 2024

Commit

c3c3add

verified ·

1 Parent(s): 8f751fb

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -1

README.md CHANGED Viewed

@@ -1,3 +1,20 @@
 ---
-license: apache-2.0
 ---

 ---
 ---
+## Gemma Fine-Tuned Model
+This repository contains a fine-tuned version of the Gemma model, which is part of the GemMoE (Gemma Mixture of Experts) family of models. For more information about GemMoE, please refer to the official documentation [https://huggingface.co/Crystalcareai/GemMoE-Beta-1].
+## Model Details
+- **Dataset**: This model was fine-tuned on 3 epochs of the Crystalcareai/CodeFeedback-Alpaca dataset.
+- **Architecture**: The fine-tuned model inherits the lean and efficient architecture of the base Gemma model, making it suitable for a wide range of applications with limited computational resources.
+## Usage
+You can use this fine-tuned model like any other HuggingFace model. Simply load it using the `from_pretrained` method:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("huggingface-username/gemma-fine-tuned")
+tokenizer = AutoTokenizer.from_pretrained("huggingface-username/gemma-fine-tuned")%%