Instructions to use Minbyul/meditron-7b-wo-live_qa-iter-sft-step1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minbyul/meditron-7b-wo-live_qa-iter-sft-step1 with Transformers:

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

pipe = pipeline("text-generation", model="Minbyul/meditron-7b-wo-live_qa-iter-sft-step1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Minbyul/meditron-7b-wo-live_qa-iter-sft-step1")
model = AutoModelForMultimodalLM.from_pretrained("Minbyul/meditron-7b-wo-live_qa-iter-sft-step1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Minbyul/meditron-7b-wo-live_qa-iter-sft-step1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Minbyul/meditron-7b-wo-live_qa-iter-sft-step1

SGLang

How to use Minbyul/meditron-7b-wo-live_qa-iter-sft-step1 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 "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1" \
    --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": "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1",
		"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 "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1" \
        --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": "Minbyul/meditron-7b-wo-live_qa-iter-sft-step1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Minbyul/meditron-7b-wo-live_qa-iter-sft-step1 with Docker Model Runner:
```
docker model run hf.co/Minbyul/meditron-7b-wo-live_qa-iter-sft-step1
```

meditron-7b-wo-live_qa-iter-sft-step1

This model is a fine-tuned version of epfl-llm/meditron-7b on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:

Loss: 1.5597

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: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.4036	0.96	19	1.4487
2.0418	1.97	39	1.4852
1.8471	2.89	57	1.5597

Framework versions

Transformers 4.39.0.dev0
Pytorch 2.1.2
Datasets 2.14.6
Tokenizers 0.15.2

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Minbyul/meditron-7b-wo-live_qa-iter-sft-step1

Base model

meta-llama/Llama-2-7b

Finetuned

epfl-llm/meditron-7b

Finetuned

(41)

this model

Minbyul
/

meditron-7b-wo-live_qa-iter-sft-step1

meditron-7b-wo-live_qa-iter-sft-step1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for Minbyul/meditron-7b-wo-live_qa-iter-sft-step1

Dataset used to train Minbyul/meditron-7b-wo-live_qa-iter-sft-step1