Instructions to use altomek/CodeRosa-70B-AB1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use altomek/CodeRosa-70B-AB1 with Transformers:

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

pipe = pipeline("text-generation", model="altomek/CodeRosa-70B-AB1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("altomek/CodeRosa-70B-AB1")
model = AutoModelForCausalLM.from_pretrained("altomek/CodeRosa-70B-AB1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use altomek/CodeRosa-70B-AB1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "altomek/CodeRosa-70B-AB1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "altomek/CodeRosa-70B-AB1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/altomek/CodeRosa-70B-AB1

SGLang

How to use altomek/CodeRosa-70B-AB1 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 "altomek/CodeRosa-70B-AB1" \
    --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": "altomek/CodeRosa-70B-AB1",
		"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 "altomek/CodeRosa-70B-AB1" \
        --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": "altomek/CodeRosa-70B-AB1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use altomek/CodeRosa-70B-AB1 with Docker Model Runner:
```
docker model run hf.co/altomek/CodeRosa-70B-AB1
```

altomek commited on Mar 21, 2024

Commit

23abe88

verified ·

1 Parent(s): 21bb0de

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -57,6 +57,7 @@ I use max_seq_len 8K with alpha_value 2.65.
 - [3bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-3bpw-EXL2)
 - [2.4bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-2.4bpw-EXL2) --> 24GB VRAM
 - [measurements](https://huggingface.co/altomek/measurements/resolve/main/CodeRosa-AB1_measurement.json) --> ExLlamav2 measurments
 ### PS
 I welcome your comments about this model.

 - [3bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-3bpw-EXL2)
 - [2.4bpw](https://huggingface.co/altomek/CodeRosa-70B-AB1-2.4bpw-EXL2) --> 24GB VRAM
 - [measurements](https://huggingface.co/altomek/measurements/resolve/main/CodeRosa-AB1_measurement.json) --> ExLlamav2 measurments
+- [GGUF](https://huggingface.co/mradermacher/CodeRosa-70B-AB1-GGUF)
 ### PS
 I welcome your comments about this model.