Instructions to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq with Transformers:

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

pipe = pipeline("text-generation", model="EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq

SGLang

How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq 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 "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq with Docker Model Runner:
```
docker model run hf.co/EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq
```

Laguna-XS.2 → Dense (K=8) · CUDA-SFT · HQQ 4-bit

Quantized variant of EvanOLeary/laguna-xs2-dense-k8-cuda-sft. 4-bit weight quantization via HQQ (Half-Quadratic Quantization). Pure-PyTorch, data-free, no calibration set required.

Size & quality

	bf16 (base)	HQQ 4-bit
Weight file	5.99 GB	2.28 GB (38% of bf16)
VRAM (loaded)	6.00 GB	2.28 GB
Bits/param (effective)	16	~4.5 (incl. group scales + zeros)

ReLU CUDA kernel smoke test (greedy decode, 400 max_new_tokens)

302 tokens generated in 51.7s = 5.8 tok/s.

Prompt: "Write a CUDA kernel that computes ReLU (max(x, 0)) on a float array in-place. Include the kernel and a host-side launcher."

The model produced a complete torch::extension-style CUDA kernel with templated relu_kernel, AT_DISPATCH_FLOATING_TYPES dispatch, a relu_forward host launcher, and a PYBIND11_MODULE entrypoint suitable for torch.utils.cpp_extension.load_inline.

How to load

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
from hqq.models.hf.base import AutoHQQHFModel
model = AutoHQQHFModel.from_quantized(repo, compute_dtype=torch.bfloat16, device="cuda")

msgs = [{"role":"user","content":"Write a CUDA kernel for elementwise sigmoid on a float array."}]
text = tok.apply_chat_template(msgs, add_generation_prompt=True, tokenize=False)
ids = tok(text, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
out = model.generate(ids, max_new_tokens=400, do_sample=False, pad_token_id=tok.pad_token_id)
print(tok.decode(out[0][ids.shape[-1]:], skip_special_tokens=True))

Provenance & roadmap

Stage	Repo
Teacher MoE	poolside/Laguna-XS.2
Dense recon (V1)	EvanOLeary/laguna-xs2-dense-k8-recon
CUDA-SFT (bf16 base for this quant)	EvanOLeary/laguna-xs2-dense-k8-cuda-sft
This: HQQ 4-bit	EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq

Quantization details

Library: hqq 0.2.8 Half-Quadratic Quantization
Scheme: 4-bit weight-only, group_size=64, axis=1
Calibration: none (data-free; HQQ optimizes per-tensor quantization params analytically)
Verification: smoke test produces valid CUDA kernel code on the ReLU prompt (see snapshot in this card)

Downloads last month: 10

Model tree for EvanOLeary/laguna-xs2-dense-k8-cuda-sft-int4-hqq

Base model

poolside/Laguna-XS.2

Finetuned

EvanOLeary/laguna-xs2-dense-k8-cuda-sft

Finetuned

(3)

this model