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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FinchResearch/Gurkha-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/Gurkha-copilot-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

Model Card: Gurkha Coding Assistant

Overview

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

Description

Gurkha is a versatile coding assistant designed to excel in generating and completing code tasks. With a robust architecture comprising 1 billion parameters, Gurkha offers efficiency and proficiency in various coding scenarios. Whether you need code snippets, code completions, or general text generation, Gurkha is here to provide reliable assistance.

Use Cases

Efficient code generation for multiple programming languages
Accelerated code completion to streamline development workflows
Automated generation of documentation and comments
Creation of illustrative code samples and examples
Exploring coding concepts through interactive code generation

Strengths

Strong parameter base for robust performance
Versatility in addressing diverse coding challenges
Proficient generation of high-quality code
Adaptability to different coding styles and languages

Limitations

Focus is primarily on code-related tasks
Complexity might require specific instructions for precise code generation
Limited contextual understanding outside of coding domain

Ethical Considerations

Gurkha's code generation adheres to ethical guidelines, producing content that is unbiased, respectful, and non-discriminatory. Users are encouraged to review generated code to ensure alignment with industry standards and coding best practices.

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

F16