Instructions to use geshijoker/HealthCareMagic_sft_llama3_instruct_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use geshijoker/HealthCareMagic_sft_llama3_instruct_full with Transformers:

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

pipe = pipeline("text-generation", model="geshijoker/HealthCareMagic_sft_llama3_instruct_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("geshijoker/HealthCareMagic_sft_llama3_instruct_full")
model = AutoModelForCausalLM.from_pretrained("geshijoker/HealthCareMagic_sft_llama3_instruct_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use geshijoker/HealthCareMagic_sft_llama3_instruct_full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "geshijoker/HealthCareMagic_sft_llama3_instruct_full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "geshijoker/HealthCareMagic_sft_llama3_instruct_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/geshijoker/HealthCareMagic_sft_llama3_instruct_full

SGLang

How to use geshijoker/HealthCareMagic_sft_llama3_instruct_full 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 "geshijoker/HealthCareMagic_sft_llama3_instruct_full" \
    --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": "geshijoker/HealthCareMagic_sft_llama3_instruct_full",
		"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 "geshijoker/HealthCareMagic_sft_llama3_instruct_full" \
        --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": "geshijoker/HealthCareMagic_sft_llama3_instruct_full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use geshijoker/HealthCareMagic_sft_llama3_instruct_full with Docker Model Runner:
```
docker model run hf.co/geshijoker/HealthCareMagic_sft_llama3_instruct_full
```

sft_full

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the healthcaremagic dataset. It achieves the following results on the evaluation set:

Loss: 1.7460

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 8
total_train_batch_size: 512
total_eval_batch_size: 64
optimizer: Use adamw_torch 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: 0.05
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.2093	2.8429	500	1.7462

Evaluation results

Name	Checkpoint	Rouge1	RougeL	Meteor	Bert Score
baseline instruct model	Meta-Llama-3-8B-Instruct	0.254	0.128	0.222	0.747
full fientune from inst	sft_llama3_instruct_full	0.315	0.189	0.238	0.782
lora sft from inst	sft_llama3_instruct_lora_all	0.271	0.143	0.194	0.774
lora sft from base	sft_llama3_lora_all	0.239	0.113	0.211	0.735
qlora sft from inst	sft_llama3_instruct_qlora_all	0.137	0.071	0.102	0.679
qlora sft from base	sft_llama3_qlora_all	0.192	0.090	0.159	0.718