Instructions to use konkani/konkani-llama3.1-8b-instruct-256R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use konkani/konkani-llama3.1-8b-instruct-256R with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "konkani/konkani-llama3.1-8b-instruct-256R")

Transformers

How to use konkani/konkani-llama3.1-8b-instruct-256R with Transformers:

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

pipe = pipeline("text-generation", model="konkani/konkani-llama3.1-8b-instruct-256R")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("konkani/konkani-llama3.1-8b-instruct-256R", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use konkani/konkani-llama3.1-8b-instruct-256R with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "konkani/konkani-llama3.1-8b-instruct-256R"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konkani/konkani-llama3.1-8b-instruct-256R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/konkani/konkani-llama3.1-8b-instruct-256R

SGLang

How to use konkani/konkani-llama3.1-8b-instruct-256R 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 "konkani/konkani-llama3.1-8b-instruct-256R" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konkani/konkani-llama3.1-8b-instruct-256R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "konkani/konkani-llama3.1-8b-instruct-256R" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "konkani/konkani-llama3.1-8b-instruct-256R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use konkani/konkani-llama3.1-8b-instruct-256R with Docker Model Runner:
```
docker model run hf.co/konkani/konkani-llama3.1-8b-instruct-256R
```

Model Card for konkani-llama3.1-8b-instruct-Romionly-256r

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct. It has been trained using TRL.

Quick start

Do not use this model for inference as the quality of performance is quiet bad

This model was trained on Lora Rank 256

Framework versions

PEFT 0.18.0
TRL: 0.26.2
Transformers: 4.57.3
Pytorch: 2.8.0+cu129
Datasets: 4.4.2
Tokenizers: 0.22.0

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 4

Model tree for konkani/konkani-llama3.1-8b-instruct-256R

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Adapter

(2380)

this model