Instructions to use Johnny1201/llama3.2_1b_med_QA_2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Johnny1201/llama3.2_1b_med_QA_2 with Transformers:

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

pipe = pipeline("text-generation", model="Johnny1201/llama3.2_1b_med_QA_2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Johnny1201/llama3.2_1b_med_QA_2")
model = AutoModelForCausalLM.from_pretrained("Johnny1201/llama3.2_1b_med_QA_2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Johnny1201/llama3.2_1b_med_QA_2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Johnny1201/llama3.2_1b_med_QA_2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Johnny1201/llama3.2_1b_med_QA_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Johnny1201/llama3.2_1b_med_QA_2

SGLang

How to use Johnny1201/llama3.2_1b_med_QA_2 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 "Johnny1201/llama3.2_1b_med_QA_2" \
    --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": "Johnny1201/llama3.2_1b_med_QA_2",
		"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 "Johnny1201/llama3.2_1b_med_QA_2" \
        --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": "Johnny1201/llama3.2_1b_med_QA_2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Johnny1201/llama3.2_1b_med_QA_2 with Docker Model Runner:
```
docker model run hf.co/Johnny1201/llama3.2_1b_med_QA_2
```

medicalQA_1b_2

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the MedQA2 and the Med_int_data datasets. It achieves the following results on the evaluation set:

Loss: 1.2446

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: 5e-05
train_batch_size: 4
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.3452	0.6254	500	1.5974
0.8293	1.2508	1000	1.3727
0.7086	1.8762	1500	1.2465

Framework versions

Transformers 4.45.2
Pytorch 2.5.1+cu124
Datasets 2.21.0
Tokenizers 0.20.3

Downloads last month: 8

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for Johnny1201/llama3.2_1b_med_QA_2

Base model

meta-llama/Llama-3.2-1B

Finetuned

(915)

this model