MiMo-V2.5-ASR-8B-NOESIS-BF16

BF16 dtype-repack of XiaomiMiMo/MiMo-V2.5-ASR-8B — original FP32 floating-point weights losslessly cast to bfloat16 for LoRA / DoRA / PEFT compatibility and reduced disk footprint. The model architecture, parameter values, tokenizer, and configuration are identical to upstream — only the IEEE-754 storage dtype was changed.

License preserved end-to-end — see LICENSE in this repo for the full text and attribution chain.

Released as part of the NOESIS Professional Multilingual Dubbing Automation Platform (framework: DHCF-FNO — Deterministic Hybrid Control Framework for Frozen Neural Operators).

• Founder: Ilia Bolotnikov
• Organization: AMAImedia.com
• X (Twitter): @AMAImediacom
• LinkedIn: Ilia Bolotnikov
• Telegram: @AMAImediacom
• NOESIS version: v15.8
• Repack date: 2026-05-19

---

Summary

Robust speech recognition built on a Qwen2-derived causal LM backbone with an 8-channel audio token path (n_rvq=20, group_size=4). Multilingual coverage: Mandarin, English, Cantonese.

Use case inside NOESIS

Multilingual ASR / transcription. Inside NOESIS this is considered for the M1-ASR teacher pool of the cinema-dubbing pipeline as a Tier-1 zh/en/yue specialist.

What changed vs upstream

Aspect	Upstream	This bundle
Floating-point storage dtype	FP32	bfloat16
config.json torch_dtype	as-is	bfloat16
model.safetensors.index.json total_size	as-is	recomputed
Tokenizer / chat template / modeling code	as-is	unchanged
Number of parameters	as-is	unchanged
Value-level transformation beyond dtype cast	—	none
Disk size	30 GB	15 GB

Architecture

Property	Value
Immediate parent	XiaomiMiMo/MiMo-V2.5-ASR-8B
Architecture	MiMoV2ASRForCausalLM
Architecture base / lineage	Qwen2-derived (model_type=qwen2)
Parameters	~8B
Hidden size	4096
Num hidden layers	36
Attention heads / KV heads	32 / 8 (GQA)
Vocab size	151680
Max position embeddings	8192
Format	bfloat16
Bundle size on disk	15 GB
License	MIT License
Project page	https://github.com/XiaomiMiMo/MiMo-V2.5-ASR

Repack tooling

CPU-only sharded repack via repack_fp32_to_bf16.py — reads each shard with safetensors.safe_open, casts floating-point tensors to torch.bfloat16, rewrites the shard, updates the index manifest. No GPU involvement, no value-level transformation beyond the IEEE-754 dtype cast.

Performance reference (RTX 3060 laptop, NVMe SSD):

• Single 5 GB FP32 shard cast → ~28-40 sec
• Full 30 GB → 15 GB in 1 pass, sharded

Use cases (for the BF16 bundle)

• ✅ LoRA / DoRA / IA³ fine-tuning that requires a dtype=torch.bfloat16 base
• ✅ Bitsandbytes NF4 / AWQ-INT4 / GPTQ quantization (these tools prefer BF16 input)
• ✅ Inference on Ampere+ / MI200+ hardware with native BF16 support
• ✅ KD-teacher (forward-only) where BF16 storage saves bandwidth
• ❌ Full-parameter fine-tuning of weights — use FP32/BF16 master weights pattern; storage dtype alone is insufficient

Quick start

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

repo = "AMAImedia/MiMo-V2.5-ASR-8B-NOESIS-BF16"

tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
).eval()

Sealed rules (NOESIS DHCF-FNO)

• R-DTYPE-REPACK-BF16 — pure IEEE-754 dtype cast from FP32 to bfloat16. No value-level transformation, no LoRA merge, no architectural change. Equivalent to loading upstream with dtype=torch.bfloat16 and saving, but materialised on disk.
• R-MIT-CLEAN — upstream MIT License preserved end-to-end via the LICENSE file in this repo. AMAImedia adds only a derivative-work notice for the repack step.
• R-NO-VALUE-TRANSFORM — no fine-tuning, no distillation, no merge has been applied between upstream and this repo. Outputs are bit-for-bit equivalent up to the precision difference of the dtype cast.

License & attribution

This bundle inherits MIT License from XiaomiMiMo/MiMo-V2.5-ASR-8B. Original model card, citation, and attribution from upstream apply without modification. See LICENSE in this repo for the complete text plus the NOESIS derivative-work NOTICE.

Citation

@misc{noesis2026mimov25asr8bnoesisbf16bf16,
  title  = {NOESIS DHCF-FNO :: MiMo-V2.5-ASR-8B-NOESIS-BF16 — BF16 dtype-repack derivative},
  author = {Bolotnikov, Ilia and AMAImedia},
  year   = {2026},
  note   = {BF16 dtype-repack of XiaomiMiMo/MiMo-V2.5-ASR-8B for LoRA / PEFT
            compatibility. 15 GB on disk, MIT License
            preserved end-to-end.},
  url    = {https://huggingface.co/AMAImedia/MiMo-V2.5-ASR-8B-NOESIS-BF16}
}

Please also cite the upstream model when using this bundle. See the upstream README and LICENSE in this repo for citation requirements.

Author

• Founder: Ilia Bolotnikov
• Organization: AMAImedia.com
• X (Twitter): @AMAImediacom
• LinkedIn: Ilia Bolotnikov
• Telegram: @AMAImediacom
• NOESIS version: v15.8
• Repack date: 2026-05-19
• HF repo: AMAImedia/MiMo-V2.5-ASR-8B-NOESIS-BF16
• Upstream: XiaomiMiMo/MiMo-V2.5-ASR-8B

---

Produced 2026-05-19 by NOESIS DHCF-FNO v15.8 — AMAImedia.com