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
```

j0no12 commited on 29 days ago

Commit

12bf225

verified ·

1 Parent(s): b209c37

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ datasets:
 # Sol Lite 2
-Sol Lite 2 is a 14,942,592-parameter base language model trained from scratch on exactly 20 billion tokens. We screened 50 architecture runs before choosing its configuration. The released checkpoint keeps recurrence and loop conditioning; TN-Gram, Engram, SPAB, and XSA are disabled.
 The final checkpoint scored 9.6120 on the Axiomic Open SLM Intelligence Index. It was the highest Index score measured during this production run. Sol Lite 2 completes text and has no instruction tuning.

 # Sol Lite 2
+Sol Lite 2 is a 14,942,592-parameter base language model trained from scratch on exactly 20 billion tokens. We screened 50 architecture runs before choosing its configuration. The released checkpoint keeps recurrence and loop conditioning.
 The final checkpoint scored 9.6120 on the Axiomic Open SLM Intelligence Index. It was the highest Index score measured during this production run. Sol Lite 2 completes text and has no instruction tuning.