Instructions to use FinchResearch/Sherman-copilot-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FinchResearch/Sherman-copilot-1b with Transformers:

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

pipe = pipeline("text-generation", model="FinchResearch/Sherman-copilot-1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FinchResearch/Sherman-copilot-1b")
model = AutoModelForCausalLM.from_pretrained("FinchResearch/Sherman-copilot-1b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use FinchResearch/Sherman-copilot-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FinchResearch/Sherman-copilot-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FinchResearch/Sherman-copilot-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FinchResearch/Sherman-copilot-1b

SGLang

How to use FinchResearch/Sherman-copilot-1b 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/Sherman-copilot-1b" \
    --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/Sherman-copilot-1b",
		"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/Sherman-copilot-1b" \
        --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/Sherman-copilot-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FinchResearch/Sherman-copilot-1b with Docker Model Runner:
```
docker model run hf.co/FinchResearch/Sherman-copilot-1b
```

Model Card: Sherman Coding Assistant

Overview

Name: Sherman Coding Assistant
Model Type: Text Generation
Model Size: 1 billion parameters
Functionality: Code generation, code completion, text generation

Description

Sherman is a versatile coding assistant powered by a lightweight architecture. With 1 billion parameters and built on top of a versatile base model, Sherman excels in generating and completing code. It's designed to be adaptable and proficient, offering assistance in various coding tasks. Whether you're in need of code snippets, code completions, or general text generation, Sherman is here to help.

Use Cases

Code generation for various programming languages
Code completion to speed up development workflows
Generating documentation and comments
Creating examples and code samples
Exploring coding concepts through interactive code generation

Strengths

Lightweight architecture for efficient performance
Versatile in handling different coding tasks
Proficient in generating code
Adaptable to various coding styles and languages

Limitations

Primarily focused on code-related tasks
May require specific instructions for complex code scenarios
Limited understanding of context outside coding domain

Ethical Considerations

Sherman's code generation is designed to be helpful, respectful, and unbiased. It does not produce harmful, unethical, or discriminatory content. However, users should review generated code to ensure compliance with industry standards and best practices.

Downloads last month: 4