Instructions to use FinchResearch/SiLM-3b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FinchResearch/SiLM-3b-v2 with Transformers:

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

pipe = pipeline("text-generation", model="FinchResearch/SiLM-3b-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("FinchResearch/SiLM-3b-v2")
model = AutoModelForMultimodalLM.from_pretrained("FinchResearch/SiLM-3b-v2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FinchResearch/SiLM-3b-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FinchResearch/SiLM-3b-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FinchResearch/SiLM-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FinchResearch/SiLM-3b-v2

SGLang

How to use FinchResearch/SiLM-3b-v2 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 "FinchResearch/SiLM-3b-v2" \
    --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": "FinchResearch/SiLM-3b-v2",
		"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 "FinchResearch/SiLM-3b-v2" \
        --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": "FinchResearch/SiLM-3b-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FinchResearch/SiLM-3b-v2 with Docker Model Runner:
```
docker model run hf.co/FinchResearch/SiLM-3b-v2
```

SiLM Model Card

1. Model Details

Model Name: SiLM (Semantic Inference Language Model)
Version: 1.0
Model Type: Language Model

2. Overview

SiLM (Semantic Inference Language Model) is a state-of-the-art language model developed by [Your Organization/Research Team Name] to perform semantic inference tasks. It is designed to generate responses to prompts with a focus on understanding and inferring the underlying meaning of the input. SiLM has been fine-tuned on a diverse and extensive dataset known as the "AboveTheClouds" dataset, which provides a wide range of linguistic patterns and domains.

3. Dataset Information

3.1. AboveTheClouds Dataset

Dataset Source: FinchResearch
Description: The AboveTheClouds dataset is a comprehensive and diverse collection of text data from various sources, including books, articles, websites, and more. This dataset serves as the foundation for fine-tuning SiLM, ensuring that the model is exposed to a broad range of linguistic patterns and domains. It includes a vast amount of text data to train SiLM effectively in understanding semantic relationships and making accurate inferences.

4. Model Capabilities

SiLM is designed to excel in semantic inference tasks. It understands and generates responses based on the input prompts using the following template:

### Human: {prompt}
### Assistant:

Some of the key capabilities and use cases of SiLM include:

Semantic Understanding: SiLM can comprehend the semantic context of input prompts and generate coherent and contextually relevant responses.
Natural Language Generation: It is capable of generating human-like text responses that are contextually appropriate and grammatically correct.
Inference and Reasoning: SiLM can make inferences based on the information provided in the prompt, making it suitable for tasks involving reasoning and deduction.
Question Answering: SiLM can answer questions, provide explanations, and generate informative responses to queries.
Content Generation: It can be used to generate content for a wide range of applications, including chatbots, virtual assistants, and content creation tools.

Downloads last month: 2

Safetensors

Model size

3B params

Tensor type

F32

F16

FinchResearch
/

SiLM-3b-v2