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

Libraries

How to use grimulkan/Xwin-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/Xwin-longLORA-70b-rope8-32k-fp16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimulkan/Xwin-longLORA-70b-rope8-32k-fp16")
model = AutoModelForCausalLM.from_pretrained("grimulkan/Xwin-longLORA-70b-rope8-32k-fp16", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

Docker Model Runner
How to use grimulkan/Xwin-longLORA-70b-rope8-32k-fp16 with Docker Model Runner:
```
docker model run hf.co/grimulkan/Xwin-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 Xwin-LM's Xwin-LM-70B-V0.1, replacing the embed and norm layers as described in the LongLoRA repo, 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).

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

See this discussion for how to create merges like these.

Downloads last month: 19

Safetensors

Model size

69B params

Tensor type

F16

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

Quantizations

2 models