Instructions to use screevoai/abbvie-llama2-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use screevoai/abbvie-llama2-7b with Transformers:

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

pipe = pipeline("text-generation", model="screevoai/abbvie-llama2-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("screevoai/abbvie-llama2-7b")
model = AutoModelForCausalLM.from_pretrained("screevoai/abbvie-llama2-7b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use screevoai/abbvie-llama2-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "screevoai/abbvie-llama2-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "screevoai/abbvie-llama2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/screevoai/abbvie-llama2-7b

SGLang

How to use screevoai/abbvie-llama2-7b 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 "screevoai/abbvie-llama2-7b" \
    --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": "screevoai/abbvie-llama2-7b",
		"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 "screevoai/abbvie-llama2-7b" \
        --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": "screevoai/abbvie-llama2-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use screevoai/abbvie-llama2-7b with Docker Model Runner:
```
docker model run hf.co/screevoai/abbvie-llama2-7b
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Details

This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on the screevoai/abbvie dataset.

Training results

Training Loss	Epoch	Step	Validation Loss
1.4318	7	1100	1.4409

Libraries to Install

pip install transformers datasets safetensors huggingface-hub accelerator
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu

Authentication needed before running the script

Run the following command in the terminal/jupyter_notebook:

Terminal: huggingface-cli login

Jupyter_notebook:

>>> from huggingface_hub import notebook_login
>>> notebook_login()

NOTE: Copy and Paste the token from your Huggingface Account Settings > Access Tokens > Create a new token / Copy the existing one.

Script

>>>from datasets import load_dataset
>>>from transformers import AutoModelForCausalLM, AutoTokenizer

>>> # Load model and Tokenizer
>>> model = AutoModelForCausalLM.from_pretrained("screevoai/abbvie-llama2-7b", device_map = "auto")
>>>  tokenizer = AutoTokenizer.from_pretrained("screevoai/abbvie-llama2-7b")
>>>  tokenizer.padding_side='right'
>>>  tokenizer.pad_token = tokenizer.eos_token

>>> # Load the dataset
>>> ds = load_dataset("screevoai/abbvie", split="test", use_auth_token=True)
>>> sample_prompt = ds["Prompt"][0]  # change the row number for testing different prompts

>>> # Generate answer to the prompt using the model
>>> encoded_input = tokenizer(sample_prompt,  return_tensors="pt", add_special_tokens=True)
>>> model_inputs = encoded_input.to('auto')
>>> generated_ids = model.generate(**model_inputs, max_new_tokens=500, do_sample=True, pad_token_id=tokenizer.eos_token_id)
>>> decoded_output = tokenizer.batch_decode(generated_ids)

>>> print(decoded_output[0].replace(prompt, ""))

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for screevoai/abbvie-llama2-7b

Base model

meta-llama/Llama-2-7b-hf

Finetuned

(989)

this model

Evaluation results

Training loss on Abbvie Dataset
self-reported