Instructions to use fierysurf/Kan-LLaMA-7B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fierysurf/Kan-LLaMA-7B-base with Transformers:

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

pipe = pipeline("text-generation", model="fierysurf/Kan-LLaMA-7B-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fierysurf/Kan-LLaMA-7B-base")
model = AutoModelForCausalLM.from_pretrained("fierysurf/Kan-LLaMA-7B-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use fierysurf/Kan-LLaMA-7B-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fierysurf/Kan-LLaMA-7B-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fierysurf/Kan-LLaMA-7B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fierysurf/Kan-LLaMA-7B-base

SGLang

How to use fierysurf/Kan-LLaMA-7B-base 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 "fierysurf/Kan-LLaMA-7B-base" \
    --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": "fierysurf/Kan-LLaMA-7B-base",
		"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 "fierysurf/Kan-LLaMA-7B-base" \
        --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": "fierysurf/Kan-LLaMA-7B-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fierysurf/Kan-LLaMA-7B-base with Docker Model Runner:
```
docker model run hf.co/fierysurf/Kan-LLaMA-7B-base
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Kannada LLaMA 7B

Welcome to the repository dedicated to the Kannada LLaMA 7B model. This repository is specifically tailored to offer users a sharded version of the original Kannada LLaMA 7B model, which was initially developed and released by Tensoic. The model in question is a significant development in the field of language processing and machine learning, specifically tailored for the Kannada language.

The original model, titled "Kan-LLaMA-7B-base", is available on Hugging Face, a popular platform for hosting machine learning models. You can access and explore the original model by visiting the Hugging Face website at this link: Tensoic/Kan-LLaMA-7B-base. This link will direct you to the model's page where you can find detailed information about its architecture, usage, and capabilities.

For those who are interested in a deeper understanding of the Kannada LLaMA 7B model, including its development process, applications, and technical specifications, Tensoic has published an extensive blog post. This blog post provides valuable insights into the model's creation and its potential impact on natural language processing tasks involving the Kannada language. To read this informative and detailed blog post, please follow this link: Tensoic's Kannada LLaMA blog post.

The blog is an excellent resource for anyone looking to gain a comprehensive understanding of the model, whether you are a student, researcher, or a professional in the field of machine learning and language processing.

In summary, this repository serves as a gateway to accessing the sharded version of the Kannada LLaMA 7B model and provides links to the original model and an informative blog post for a more in-depth exploration. We encourage all interested parties to explore these resources to fully appreciate the capabilities and advancements represented by the Kannada LLaMA 7B model.

Downloads last month: 83

Safetensors

Model size

7B params

Tensor type

F16

Model tree for fierysurf/Kan-LLaMA-7B-base

Quantizations

1 model

fierysurf
/

Kan-LLaMA-7B-base

Kannada LLaMA 7B

Model tree for fierysurf/Kan-LLaMA-7B-base

Space using fierysurf/Kan-LLaMA-7B-base 1