Instructions to use emozilla/landmark-llama-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emozilla/landmark-llama-7b with Transformers:

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

pipe = pipeline("text-generation", model="emozilla/landmark-llama-7b", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("emozilla/landmark-llama-7b", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("emozilla/landmark-llama-7b", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use emozilla/landmark-llama-7b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/emozilla/landmark-llama-7b

SGLang

How to use emozilla/landmark-llama-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 "emozilla/landmark-llama-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": "emozilla/landmark-llama-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 "emozilla/landmark-llama-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": "emozilla/landmark-llama-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use emozilla/landmark-llama-7b with Docker Model Runner:
```
docker model run hf.co/emozilla/landmark-llama-7b
```

emozilla/landmark-llama-7b

This model is an out-of-the-box ready version of the LLaMA-7B variant of Landmark Attention. The original code is modified from the Landmark GitHub and the weights from here.

As a LLaMA variant, this model may be subject to the LLaMA license.

To use

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch

tokenizer = AutoTokenizer.from_pretrained("emozilla/landmark-llama-7b", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("emozilla/landmark-llama-7b", \
  torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

print(pipe("Somebody once told me the world is gonna roll me", \
           max_new_tokens=256, temperature=0.8, do_sample=True))

You can configure the Landmark parameters by editing mem_freq, mem_top_k, mem_max_seq_len, and mem_max_cache_size.

config = AutoConfig.from_pretrained("emozilla/landmark-llama-7b", trust_remote_code=True)
config.mem_top_k = 6
model = AutoModelForCausalLM.from_pretrained("emozilla/landmark-llama-7b", \
  torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", config=config)

Downloads last month: 224

Paper for emozilla/landmark-llama-7b

Landmark Attention: Random-Access Infinite Context Length for Transformers

Paper • 2305.16300 • Published May 25, 2023