Instructions to use c-bone/CrystaLLM-pi_Chili100K-XRD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use c-bone/CrystaLLM-pi_Chili100K-XRD with Transformers:

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

pipe = pipeline("text-generation", model="c-bone/CrystaLLM-pi_Chili100K-XRD")

# Load model directly
from transformers import AutoTokenizer, SliderGPT

tokenizer = AutoTokenizer.from_pretrained("c-bone/CrystaLLM-pi_Chili100K-XRD")
model = SliderGPT.from_pretrained("c-bone/CrystaLLM-pi_Chili100K-XRD")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use c-bone/CrystaLLM-pi_Chili100K-XRD 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_Chili100K-XRD"
# 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_Chili100K-XRD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/c-bone/CrystaLLM-pi_Chili100K-XRD

SGLang

How to use c-bone/CrystaLLM-pi_Chili100K-XRD 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_Chili100K-XRD" \
    --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_Chili100K-XRD",
		"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_Chili100K-XRD" \
        --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_Chili100K-XRD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use c-bone/CrystaLLM-pi_Chili100K-XRD with Docker Model Runner:
```
docker model run hf.co/c-bone/CrystaLLM-pi_Chili100K-XRD
```

CrystaLLM-pi_Chili100K-XRD

File size: 987 Bytes

e4df472

{
  "_name_or_path": "model_ckpts/mattergen_XRD/slider_ft/checkpoint-405000",
  "activation_function": "gelu_new",
  "architectures": [
    "SliderGPT"
  ],
  "attn_pdrop": 0.1,
  "bos_token_id": 372,
  "embd_pdrop": 0.1,
  "eos_token_id": 373,
  "initializer_range": 0.02,
  "layer_norm_epsilon": 1e-05,
  "model_type": "gpt2",
  "n_embd": 512,
  "n_head": 8,
  "n_inner": null,
  "n_layer": 8,
  "n_positions": 1536,
  "pad_token_id": 371,
  "reorder_and_upcast_attn": false,
  "resid_pdrop": 0.1,
  "scale_attn_by_inverse_layer_idx": false,
  "scale_attn_weights": true,
  "slider_dropout": 0.196393312280024,
  "slider_n_heads_sharing_slider": 2,
  "slider_n_hidden": 64,
  "slider_n_variables": 40,
  "slider_on": true,
  "summary_activation": null,
  "summary_first_dropout": 0.1,
  "summary_proj_to_labels": true,
  "summary_type": "cls_index",
  "summary_use_proj": true,
  "torch_dtype": "float32",
  "transformers_version": "4.48.0",
  "use_cache": true,
  "vocab_size": 377
}