Instructions to use Sathvik265/llama4-medical-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sathvik265/llama4-medical-qlora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-4-Scout-17B-16E-Instruct")
model = PeftModel.from_pretrained(base_model, "Sathvik265/llama4-medical-qlora")

Transformers

How to use Sathvik265/llama4-medical-qlora with Transformers:

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

pipe = pipeline("text-generation", model="Sathvik265/llama4-medical-qlora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Sathvik265/llama4-medical-qlora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sathvik265/llama4-medical-qlora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sathvik265/llama4-medical-qlora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sathvik265/llama4-medical-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sathvik265/llama4-medical-qlora

SGLang

How to use Sathvik265/llama4-medical-qlora 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 "Sathvik265/llama4-medical-qlora" \
    --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": "Sathvik265/llama4-medical-qlora",
		"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 "Sathvik265/llama4-medical-qlora" \
        --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": "Sathvik265/llama4-medical-qlora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sathvik265/llama4-medical-qlora with Docker Model Runner:
```
docker model run hf.co/Sathvik265/llama4-medical-qlora
```

llama4-medical-qlora

This model is a fine-tuned version of meta-llama/Llama-4-Scout-17B-16E-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 7.3007

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
7.3185	1.0	150	7.3091
7.3092	2.0	300	7.3508
7.3075	3.0	450	7.3007

Framework versions

PEFT 0.18.0
Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.4.1
Tokenizers 0.22.1

Downloads last month: 3

Model tree for Sathvik265/llama4-medical-qlora

Base model

meta-llama/Llama-4-Scout-17B-16E

Finetuned

meta-llama/Llama-4-Scout-17B-16E-Instruct

Adapter

(27)

this model