Instructions to use ethicalabs/xLSTM-7b-Polymath-PEFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ethicalabs/xLSTM-7b-Polymath-PEFT with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("ethicalabs/xLSTM-7b-Instruct")
model = PeftModel.from_pretrained(base_model, "ethicalabs/xLSTM-7b-Polymath-PEFT")

Transformers

How to use ethicalabs/xLSTM-7b-Polymath-PEFT with Transformers:

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

pipe = pipeline("text-generation", model="ethicalabs/xLSTM-7b-Polymath-PEFT")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ethicalabs/xLSTM-7b-Polymath-PEFT", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ethicalabs/xLSTM-7b-Polymath-PEFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ethicalabs/xLSTM-7b-Polymath-PEFT

SGLang

How to use ethicalabs/xLSTM-7b-Polymath-PEFT 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 "ethicalabs/xLSTM-7b-Polymath-PEFT" \
    --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": "ethicalabs/xLSTM-7b-Polymath-PEFT",
		"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 "ethicalabs/xLSTM-7b-Polymath-PEFT" \
        --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": "ethicalabs/xLSTM-7b-Polymath-PEFT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ethicalabs/xLSTM-7b-Polymath-PEFT with Docker Model Runner:
```
docker model run hf.co/ethicalabs/xLSTM-7b-Polymath-PEFT
```

Model Card for xlstm-7b-instruct-phase-2

This model is a fine-tuned version of ethicalabs/xLSTM-7b-Instruct for task alignment.

It has been trained using TRL using SFT on assistant-only tokens.

The k_proj and v_proj matrices have been frozen to isolate and preserve the model's pre-trained knowledge base.

This fine-tuning focused only on the q_proj (query) and FFN matrices, adapting the model's reasoning and query-retrieval mechanisms without overwriting its core, frozen knowledge.

This experiment was designed to test the hypothesis that the model's reasoning capabilities (q_proj) could be specialized for math/code while its knowledge (k_proj, v_proj) remained intact.

Quick start

Work in Progress!

Training procedure

This model was trained with SFT.

Framework versions

PEFT 0.17.1
TRL: 0.24.0
Transformers: 4.57.1
Pytorch: 2.8.0+cu126
Datasets: 4.2.0
Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}

Downloads last month: 1

Model tree for ethicalabs/xLSTM-7b-Polymath-PEFT

Base model

NX-AI/xLSTM-7b

Finetuned

ethicalabs/xLSTM-7b-Instruct

Adapter

(1)

this model

ethicalabs
/

xLSTM-7b-Polymath-PEFT