Instructions to use grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 with Transformers:

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

pipe = pipeline("text-generation", model="grimulkan/lzlv-longLORA-70b-rope8-32k-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("grimulkan/lzlv-longLORA-70b-rope8-32k-fp16")
model = AutoModelForMultimodalLM.from_pretrained("grimulkan/lzlv-longLORA-70b-rope8-32k-fp16")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimulkan/lzlv-longLORA-70b-rope8-32k-fp16

SGLang

How to use grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 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 "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16" \
    --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": "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16",
		"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 "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16" \
        --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": "grimulkan/lzlv-longLORA-70b-rope8-32k-fp16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 with Docker Model Runner:
```
docker model run hf.co/grimulkan/lzlv-longLORA-70b-rope8-32k-fp16
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a merge of LongAlpaca-70B-lora into lizpreciatior's lzlv_70b_fp16_hf, and removing the extra row and pad token so that the vocabularies match.

There is no additional fine-tuning. The resulting model seems to not be broken... you can test whether it is truly the original model + 32K capability (use linear rope scaling 8).

ChuckMcSneed did a benchmark here, indicating 30% degradation with 8x the context length.

You could also try merging this with other models of longLORA descendency (like Aurelian).

A 6-bit EXL2 quantization is available here, and 4 -bit EXL2 here.

See this discussion for how to create merges like these.

Downloads last month: 3

Safetensors

Model size

69B params

Tensor type

F16

Model tree for grimulkan/lzlv-longLORA-70b-rope8-32k-fp16

Quantizations

3 models