Instructions to use c-bone/CrystaLLM-pi_SLME with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use c-bone/CrystaLLM-pi_SLME with Transformers:

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

pipe = pipeline("text-generation", model="c-bone/CrystaLLM-pi_SLME")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, PKVGPT

tokenizer = AutoTokenizer.from_pretrained("c-bone/CrystaLLM-pi_SLME")
model = PKVGPT.from_pretrained("c-bone/CrystaLLM-pi_SLME", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use c-bone/CrystaLLM-pi_SLME with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/c-bone/CrystaLLM-pi_SLME

SGLang

How to use c-bone/CrystaLLM-pi_SLME 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 "c-bone/CrystaLLM-pi_SLME" \
    --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": "c-bone/CrystaLLM-pi_SLME",
		"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 "c-bone/CrystaLLM-pi_SLME" \
        --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": "c-bone/CrystaLLM-pi_SLME",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use c-bone/CrystaLLM-pi_SLME with Docker Model Runner:
```
docker model run hf.co/c-bone/CrystaLLM-pi_SLME
```

c-bone commited on 10 days ago

Commit

5da7f9f

verified ·

1 Parent(s): 96ac8e1

Point the study link at T4_SLME.ipynb

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ The model is intended for the exploration of chemical space for new photovoltaic
 ## Getting started
-Generation: [`T2_load_and_generate.ipynb`](https://github.com/C-Bone-UCL/CrystaLLM-pi/blob/main/notebooks/T2_load_and_generate.ipynb). The study: [`T5_SLME.ipynb`](https://github.com/C-Bone-UCL/CrystaLLM-pi/blob/main/notebooks/T5_SLME.ipynb).
 ## Citation

 ## Getting started
+Generation: [`T2_load_and_generate.ipynb`](https://github.com/C-Bone-UCL/CrystaLLM-pi/blob/main/notebooks/T2_load_and_generate.ipynb). The study: [`T4_SLME.ipynb`](https://github.com/C-Bone-UCL/CrystaLLM-pi/blob/main/notebooks/T4_SLME.ipynb).
 ## Citation