Skip to content
Other

Malaysian-Qwen2.5-7B-Instruct

adapting the language model for Malaysian context and dialects

1 min readupdated

This model is a further fine-tune of the base Qwen2.5-7B-Instruct LLM (large language model) trained on a 1.5 billion token dataset. It uses LoRA (a small add-on adapter for the base model) and supports responses in Mandarin, Tamil, Jawi, Manglish, and various regional dialects across Malaysia. The model excels at multi-step tasks involving local legal, political, and religious material, making it a great tool for developers and researchers who need high-quality text processing tailored to the region.

Key features

  • Support for multiple regional Malaysian dialects and languages (including Jawi and Manglish).
  • Code writing in local languages and dialects.
  • Handling multi-step context, including Malaysian legislation and culture.

What you can do

  • Integrate it into chatbots and support services for users in Malaysia.
  • Use it to generate and analyze regional legal or political documentation.

Example

Using the model to generate responses and work with Malaysian context via standard Hugging Face libraries with attached LoRA weights.

Read moreDetails
Benchmarks: average MalayMMLU (0-shot) accuracy reaches 69.26% for the Rank 128 revision.
Training: LoRA on q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, embed_tokens, and lm_head projections with an 8192 context length.
Hardware: an 8x H100 node (supported by SNS and Nvidia).
Discuss Telegram 0 20

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 14 GB · ready files16 GB
  • FP8 / INT8recommendedweights 7.1 GB8.3 GB
  • 4-bitweights 4.0 GB4.9 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 3080 · BF16 — from RTX 4090

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # mdcreativeagent/Malaysian-Qwen2.5-7B-Instruct
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download mdcreativeagent/Malaysian-Qwen2.5-7B-Instruct --local-dir ~/models/Malaysian-Qwen2.5-7B-Instruct
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of Malaysian-Qwen2.5-7B-Instruct (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

mdcreativeagent/Malaysian-Qwen2.5-7B-Instruct
Author
mdcreativeagent
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

200

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Language models

Asmaa 2B

Asmaa 2B