Instructions to use baulab/elm-Meta-Llama-3-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use baulab/elm-Meta-Llama-3-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="baulab/elm-Meta-Llama-3-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("baulab/elm-Meta-Llama-3-8B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use baulab/elm-Meta-Llama-3-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "baulab/elm-Meta-Llama-3-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "baulab/elm-Meta-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/baulab/elm-Meta-Llama-3-8B-Instruct

SGLang

How to use baulab/elm-Meta-Llama-3-8B-Instruct 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 "baulab/elm-Meta-Llama-3-8B-Instruct" \
    --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": "baulab/elm-Meta-Llama-3-8B-Instruct",
		"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 "baulab/elm-Meta-Llama-3-8B-Instruct" \
        --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": "baulab/elm-Meta-Llama-3-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use baulab/elm-Meta-Llama-3-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/baulab/elm-Meta-Llama-3-8B-Instruct
```

ELM Llama3-8B-Instruct Model Card

Erasing Conceptual Knoweldge from Language Models,
Rohit Gandikota, Sheridan Feucht, Samuel Marks, David Bau

How to use

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "baulab/elm-Meta-Llama-3-8B-Instruct"
device = 'cuda:0'
dtype = torch.float32

model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=dtype)
model = model.to(device)
model.requires_grad_(False)
tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=False)

# generate text
inputs = tokenizer(prompt, return_tensors='pt', padding=True)
inputs = inputs.to(device).to(dtype)

outputs = model.generate(**inputs,
                         max_new_tokens=300,
                         do_sample=True,
                         top_p=.95,
                         temperature=1.2)

outputs = tokenizer.batch_decode(outputs, skip_special_tokens = True)
print(outputs[0])

Model Sources [optional]

Repository: https://github.com/rohitgandikota/erasing-llm
Paper [optional]: https://arxiv.org/pdf/2410.02760
Project [optional]: https://elm.baulab.info

Citation [optional]

BibTeX:

@article{gandikota2024elm,
  title={Erasing Conceptual Knowledge from Language Models},
  author={Rohit Gandikota and Sheridan Feucht and Samuel Marks and David Bau},
  journal={arXiv preprint arXiv:2410.02760},
  year={2024}
}

Downloads last month: -; Downloads are not tracked for this model. How to track

Collection including baulab/elm-Meta-Llama-3-8B-Instruct

ELM

Collection

Collection of various ELM models from "Erasing Conceptual Knowledge from Language Models" • 4 items • Updated Oct 21, 2024 • 3

Paper for baulab/elm-Meta-Llama-3-8B-Instruct

Erasing Conceptual Knowledge from Language Models

Paper • 2410.02760 • Published Oct 3, 2024 • 14