Instructions to use Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 with Transformers:

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

pipe = pipeline("text-generation", model="Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4")
model = AutoModelForMultimodalLM.from_pretrained("Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4

SGLang

How to use Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 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 "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4" \
    --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": "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4",
		"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 "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4" \
        --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": "Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 with Docker Model Runner:
```
docker model run hf.co/Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4
```

KAT-Coder-V2.5_JKL-Luau-NVFP4

Roblox Luau–specialized fine-tune of Kwaipilot/KAT-Coder-V2.5-Dev, released as NVFP4 (W4A4 compressed-tensors) for efficient inference on NVIDIA Blackwell GPUs.


Base model	Kwaipilot/KAT-Coder-V2.5-Dev (~35B-A3B Qwen3.5-MoE, text/language release)
Fine-tune	Supervised LoRA SFT on a Roblox / Luau mix (1 epoch)
This artifact	Merged bf16 weights → NVFP4 post-training quantization
Trained by	@dylanjkl at Comulative Limited (UK)
Hardware	1× NVIDIA RTX PRO 6000 Blackwell 96GB (sm_120)

This is not an official Kwaipilot release. It is an independent specialty fine-tune and quant by Comulative Limited.

Intended uses

Primary: local / self-hosted Roblox Luau coding assistant and task executor:

Idiomatic Luau modules (--!strict, services, remotes, DataStore patterns)
Roblox client/server split, RemoteEvents / RemoteFunctions, replication-aware snippets
Code completion / continuation on existing Luau scripts
Roblox engine Q&A grounded in specialty SFT data

Recommended deployment pattern: use a stronger planning / review model for architecture and security, and this model as a fast local executor for Luau implementation (low latency, private weights, Blackwell-friendly NVFP4).

Not intended for: unsupervised production game economy / anti-cheat design without human review; non-Roblox general agenting as a drop-in frontier replacement; vision/multimodal tasks (language-only lineage).

What we did (training pipeline)

1. Base

Started from KAT-Coder-V2.5-Dev (Qwen3.5 MoE coding model, language-only open weights; vision tower declared in config but not shipped upstream).

2. Domain SFT data mix

Built a chat-formatted SFT mix (42,302 train rows after filtering/dedup; ~57M tokens) from public Hugging Face datasets (local mirror under data/).

Hugging Face datasets used in training

Hub dataset	Role in mix	Approx. SFT rows (source tag)
TorpedoSoftware/Roblox-Luau-Reasoning-v1.0	Prompt → CoT + Luau code + explanation (`train`)	14,840 `luau-reasoning`
Pinkstack/luaucoder-instructions-v3-SFT	Instruction SFT (filtered; cap ~8k quality rows)	7,927 `pinkstack-sft`
khtsly/luau-stack-hq	Curated Luau corpus → fill-in / continuation tasks	5,944 `stackhq-completion`
TorpedoSoftware/RobloxQA-v2.0	Engine/API knowledge from `train` (MCQ + direct QA variants)	4,573 `robloxqa2-mcq` + 2,290 `robloxqa2-direct`
TorpedoSoftware/LuauLeetcode	Algorithmic Luau problems (`train`)	2,336 `luau-leetcode`
TorpedoSoftware/RobloxQA-v1.0	Older QA; deduped against RobloxQA-v2 test	2,281 `robloxqa1-mcq`
Roblox/luau_corpus	Official Luau Data Sharing fragments → continuation (`train`)	2,111 `luaucorpus-completion`

Total train examples: 42,302 (plus 400 held-out mix rows for training-time val).

Evaluation dataset (not used for gradient updates)

Hub dataset	Use
TorpedoSoftware/RobloxQA-v2.0 `test` (3,000 MCQ)	Held out for baseline / future eval only

Downloaded but not used in this SFT mix

Hub dataset	Notes
TorpedoSoftware/roblox-info-dump	Roblox/Luau docs scrape present under `data/`; not mixed into the epoch-1 SFT JSONL

Formatting used the base model chat template, with prompt tokens masked (train on completions). Optional system prompts mixed in (~30% Roblox-assistant style). Decompiled-looking completion snippets filtered out. Pinkstack rows required code fences + minimum reasoning length.

3. LoRA fine-tune (1 epoch)

Hyperparameter	Value
Method	LoRA (PEFT), bf16 base
Rank / alpha	r=64, α=128, dropout 0.05
Targets	Attention (q/k/v/o), linear-attn projections, shared-expert MLP; not per-routed experts
Context	4096
Effective batch	16 (microbatch 2 × grad accum 8)
Epochs shipped here	1 (stopped at step 2642 / 5284 of a 2-epoch schedule)
Optim	AdamW fused, LR 1e-4 cosine, warmup 40
Hardware	1× RTX PRO 6000 96GB, Windows 11 + WSL2 Ubuntu

A full Trainer checkpoint (adapter + optimizer) was frozen at epoch 1 so a second epoch can be resumed later if desired. This Hub repo is the merged + NVFP4 product of that epoch-1 adapter, not the raw LoRA.

4. Merge & cleanup

Merged LoRA into base bf16 weights
Stripped randomly initialized visual.* keys so the checkpoint matches the language-only upstream release

5. NVFP4 quantization

Tooling: llm-compressor oneshot PTQ
Scheme: NVFP4 (W4A4, nvfp4-pack-quantized)
Calibration: 256 samples @ 4096 from the Luau SFT mix
moe_calibrate_all_experts=True
Ignores: lm_head, visual towers, router gates, embeddings, linear-attn (see recipe.yaml)

Why NVFP4: native-friendly 4-bit float path for Blackwell inference stacks (e.g. vLLM on modern NVIDIA data-center / pro GPUs). Smaller footprint (~~22GB weights here) vs full bf16 (~~70GB class).

Base model evaluation note

Unmodified base KAT-Coder-V2.5-Dev on RobloxQA-v2.0 test (3000 questions), MMLU-style log-prob forced choice, bf16, HF Transformers:

Baseline: 87.60% (2628 / 3000) — measured 2026-08-01.

Post–fine-tune / post-NVFP4 RobloxQA numbers for this checkpoint may be published later; treat the above as the starting point the specialty run was designed to preserve or beat on knowledge while improving Luau generation.

How to use

Transformers / llm-compressor compressed load

Follow current llm-compressor / Transformers docs for NVFP4 compressed-tensors checkpoints. Ensure a stack that understands quantization_config with format nvfp4-pack-quantized.

vLLM (Blackwell)

Prefer a recent vLLM build with NVFP4 + Qwen3.5 MoE support. Language-only serving flags may still apply (upstream was language-only; config may still mention vision). Example pattern (versions change quickly—check your vLLM release notes):

vllm serve Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4 \
  --quantization modelopt_fp4 \
  # plus whatever your vLLM build requires for NVFP4 / Qwen3.5 MoE

Use the model’s chat template (chat_template.jinja / tokenizer config). For agentic coding UIs, Qwen-style reasoning / tool parsers may apply depending on runtime.

Prompting tips

Prefer narrow tasks: one module, one bugfix, one remote contract
State client vs server, remote names, and data shapes
Ask for --!strict Luau when you want typed modules
Review security (RemoteEvent trust, DataStore races) with a stronger planner model before shipping

Training summary card

Base:     Kwaipilot/KAT-Coder-V2.5-Dev (Qwen3.5-MoE ~35B-A3B)
SFT:      LoRA r=64, 1 epoch, Luau/Roblox mix ~42k examples
Merge:    bf16 merge + strip visual.*
Quant:    NVFP4 (llm-compressor), 256 calib samples, all MoE experts
Trainer:  @dylanjkl / Comulative Limited (UK)
GPU:      1× NVIDIA RTX PRO 6000 Blackwell 96GB

Limitations & risks

Domain SFT can narrow style; may be weaker than base on non-Roblox agentic coding
1 epoch only in this release; second epoch optional, not included
NVFP4 is a lossy quant vs bf16 merge—validate on your tasks
No Studio execution loop in training—always test Luau in Roblox
May produce insecure remote/DataStore patterns; do not deploy unreviewed
MoE + hybrid linear attention runtimes are still evolving—pin tested engine versions

License

Weights are a derivative of Kwaipilot/KAT-Coder-V2.5-Dev. Unless otherwise required by the base model license, this distribution is provided under Apache-2.0. Review the base model card and license for any additional terms.

Citation / attribution

Base model: Kwaipilot/KAT-Coder-V2.5-Dev
Fine-tune & NVFP4 release: Comulative Limited (UK) / @dylanjkl
Hub: Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4
Hardware: 1× NVIDIA RTX PRO 6000 Blackwell 96GB

Maintainers

@dylanjkl — Comulative Limited (United Kingdom)
Organization: Comulative

For issues with this fine-tune/quant, contact the Comulative maintainers—not Kwaipilot—unless the bug is reproducible on the unmodified base.

Downloads last month: -

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for Comulative/KAT-Coder-V2.5_JKL-Luau-NVFP4

Base model

Kwaipilot/KAT-Coder-V2.5-Dev

Finetuned

(4)

this model

Comulative
/

KAT-Coder-V2.5_JKL-Luau-NVFP4