Instructions to use PY007/EasyContext-1M-Llama-2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PY007/EasyContext-1M-Llama-2-7B with Transformers:

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

pipe = pipeline("text-generation", model="PY007/EasyContext-1M-Llama-2-7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PY007/EasyContext-1M-Llama-2-7B")
model = AutoModelForCausalLM.from_pretrained("PY007/EasyContext-1M-Llama-2-7B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PY007/EasyContext-1M-Llama-2-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PY007/EasyContext-1M-Llama-2-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PY007/EasyContext-1M-Llama-2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PY007/EasyContext-1M-Llama-2-7B

SGLang

How to use PY007/EasyContext-1M-Llama-2-7B 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 "PY007/EasyContext-1M-Llama-2-7B" \
    --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": "PY007/EasyContext-1M-Llama-2-7B",
		"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 "PY007/EasyContext-1M-Llama-2-7B" \
        --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": "PY007/EasyContext-1M-Llama-2-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PY007/EasyContext-1M-Llama-2-7B with Docker Model Runner:
```
docker model run hf.co/PY007/EasyContext-1M-Llama-2-7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

EasyContext

GitHub Repo

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

This is a context-extrapolated base model. It has not been instruct-finetuned.

This model is finetuned from Llama-2-7B-hf with EasyContext on context length 512K and generalized to 1M tokens. Note that I keep max_position_embeddings in config.json to 4096 because HF llama will create 2D causal mask during initialization. If it is set to 1M GPU will just OOM. You can surely use this model with context length longer than 4096.

Downloads last month: 10

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for PY007/EasyContext-1M-Llama-2-7B

Quantizations

2 models

Collection including PY007/EasyContext-1M-Llama-2-7B

EasyContext

Collection

https://github.com/jzhang38/EasyContext • 7 items • Updated Apr 19, 2024 • 6