Instructions to use tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot with Transformers:

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

pipe = pipeline("text-generation", model="tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot")
model = AutoModelForMultimodalLM.from_pretrained("tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot

SGLang

How to use tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot 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 "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot" \
    --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": "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot",
		"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 "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot" \
        --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": "tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot with Docker Model Runner:
```
docker model run hf.co/tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot
```

300STEPS_5e7rate_Meditron_7B_SFT

This model is a fine-tuned version of epfl-llm/meditron-7b on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3127

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-07
train_batch_size: 4
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss
1.2096	0.1	50	1.1770
0.7177	0.2	100	0.6260
0.3357	0.29	150	0.3221
0.3191	0.39	200	0.3142
0.3195	0.49	250	0.3128
0.3195	0.59	300	0.3127

Framework versions

Transformers 4.37.2
Pytorch 2.0.0+cu117
Datasets 2.17.0
Tokenizers 0.15.1

Downloads last month: 7

Safetensors

Model size

7B params

Tensor type

F16

Model tree for tsavage68/300STEPS_5e7rate_Meditron_7B_SFT_zeroshot

Base model

meta-llama/Llama-2-7b

Finetuned

epfl-llm/meditron-7b

Finetuned

(41)

this model