Instructions to use rhyliieee/LLAMA3-MED-v1.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rhyliieee/LLAMA3-MED-v1.2 with Transformers:

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

pipe = pipeline("text-generation", model="rhyliieee/LLAMA3-MED-v1.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rhyliieee/LLAMA3-MED-v1.2")
model = AutoModelForCausalLM.from_pretrained("rhyliieee/LLAMA3-MED-v1.2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rhyliieee/LLAMA3-MED-v1.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rhyliieee/LLAMA3-MED-v1.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rhyliieee/LLAMA3-MED-v1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rhyliieee/LLAMA3-MED-v1.2

SGLang

How to use rhyliieee/LLAMA3-MED-v1.2 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 "rhyliieee/LLAMA3-MED-v1.2" \
    --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": "rhyliieee/LLAMA3-MED-v1.2",
		"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 "rhyliieee/LLAMA3-MED-v1.2" \
        --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": "rhyliieee/LLAMA3-MED-v1.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rhyliieee/LLAMA3-MED-v1.2 with Docker Model Runner:
```
docker model run hf.co/rhyliieee/LLAMA3-MED-v1.2
```

Finetuned a pretrained Model with Lora, resize the base model's embeddings, then load Peft Model with the resized base model.

"""

add special tokens to the tokenizer and base model before merging peft with base

open_tokenizer.add_special_tokens({ "additional_special_tokens": ["<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>"] }) base_model.resize_token_embeddings(len(open_tokenizer))

reload the peft model with resized token embedding of base model

peft_model = PeftModel.from_pretrained(base_model, "rhyliieee/LLaMA3-8Bit-Lora-Med-v1",)

perform merging

merged_peft_base_with_special_tokens = peft_model.merge_and_unload() """

Downloads last month: 3

Safetensors

Model size

5B params

Tensor type

F16

F32

Model tree for rhyliieee/LLAMA3-MED-v1.2

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

aaditya/Llama3-OpenBioLLM-8B

Quantized

(16)

this model

rhyliieee
/

LLAMA3-MED-v1.2

add special tokens to the tokenizer and base model before merging peft with base

reload the peft model with resized token embedding of base model

perform merging

Model tree for rhyliieee/LLAMA3-MED-v1.2

Dataset used to train rhyliieee/LLAMA3-MED-v1.2