Instructions to use solintellegence/Sol-Lite-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solintellegence/Sol-Lite-2 with Transformers:

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

pipe = pipeline("text-generation", model="solintellegence/Sol-Lite-2", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("solintellegence/Sol-Lite-2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solintellegence/Sol-Lite-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solintellegence/Sol-Lite-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "solintellegence/Sol-Lite-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/solintellegence/Sol-Lite-2

SGLang

How to use solintellegence/Sol-Lite-2 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 "solintellegence/Sol-Lite-2" \
    --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": "solintellegence/Sol-Lite-2",
		"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 "solintellegence/Sol-Lite-2" \
        --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": "solintellegence/Sol-Lite-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use solintellegence/Sol-Lite-2 with Docker Model Runner:
```
docker model run hf.co/solintellegence/Sol-Lite-2
```

Sol-Lite-2

File size: 620 Bytes

53d1439

{
  "vocab_size": 4096,
  "width": 256,
  "heads": 8,
  "kv_heads": 4,
  "blocks": 10,
  "ffn_width": 1552,
  "recurrent_start": 1,
  "recurrent_blocks": 4,
  "passes": 2,
  "loop_conditioning": true,
  "rope_theta": 20000.0,
  "max_context": 2048,
  "model_type": "sol2",
  "architectures": [
    "Sol2ForCausalLM"
  ],
  "backend": "sdpa",
  "torch_dtype": "float32",
  "tie_word_embeddings": true,
  "is_decoder": true,
  "use_cache": false,
  "eos_token_id": 3,
  "pad_token_id": 3,
  "auto_map": {
    "AutoConfig": "configuration_sol2.Sol2Config",
    "AutoModelForCausalLM": "modeling_sol2.Sol2ForCausalLM"
  }
}