Instructions to use bartowski/codegemma-1.1-7b-it-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/codegemma-1.1-7b-it-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="bartowski/codegemma-1.1-7b-it-exl2")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/codegemma-1.1-7b-it-exl2", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bartowski/codegemma-1.1-7b-it-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/codegemma-1.1-7b-it-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/codegemma-1.1-7b-it-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/codegemma-1.1-7b-it-exl2

SGLang

How to use bartowski/codegemma-1.1-7b-it-exl2 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 "bartowski/codegemma-1.1-7b-it-exl2" \
    --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": "bartowski/codegemma-1.1-7b-it-exl2",
		"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 "bartowski/codegemma-1.1-7b-it-exl2" \
        --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": "bartowski/codegemma-1.1-7b-it-exl2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bartowski/codegemma-1.1-7b-it-exl2 with Docker Model Runner:
```
docker model run hf.co/bartowski/codegemma-1.1-7b-it-exl2
```

bartowski commited on May 11, 2024

Commit

82970c5

verified ·

1 Parent(s): 7cfa693

measurement.json

Browse files

Files changed (2) hide show

README.md +7 -7
measurement.json +0 -0

README.md CHANGED Viewed

@@ -32,17 +32,17 @@ Original model: https://huggingface.co/google/codegemma-1.1-7b-it
 ## Prompt format
-No chat template specified so default is used. This may be incorrect, check original model card for details.
 ```
-<|im_start|>system
-{system_prompt}<|im_end|>
-<|im_start|>user
-{prompt}<|im_end|>
-<|im_start|>assistant
 ```
 ## Available sizes
 No GQA - VRAM requirements will be higher

 ## Prompt format
 ```
+<bos><start_of_turn>user
+{prompt}<end_of_turn>
+<start_of_turn>model
+<end_of_turn>
+<start_of_turn>model
 ```
+Note that this model does not support a System prompt.
 ## Available sizes
 No GQA - VRAM requirements will be higher

measurement.json CHANGED Viewed

The diff for this file is too large to render. See raw diff