Ruixiang Wang 7a20b417f4 model: add MTP support for Nemotron model (#26725) ...

* model: add MTP support for Nemotron Nano model

* model: add mtp_flags for nemotron model

* address review comments

2026-08-10 11:25:24 +03:00

..

__init__.py

model : Granite-Switch Architecture (#25107)

2026-08-10 09:53:46 +02:00

afmoe.py

…

arctic.py

…

baichuan.py

…

bailingmoe.py

…

base.py

model: Add MiniMax-M3 (MSA: MiniMax Sparse Attention) support (#24908)

2026-07-26 19:43:45 +02:00

bert.py

conversion: fix non-MoE NomicBert GGUF conversion error (#25996)

2026-07-23 11:01:35 +08:00

bitnet.py

conversion: accept BitNetForCausalLM architecture name (#25769)

2026-07-16 16:24:47 +03:00

bloom.py

…

chameleon.py

…

chatglm.py

convert : import bytes_to_unicode from convert_slow_tokenizer (#26217)

2026-08-04 10:34:30 +03:00

codeshell.py

…

cogvlm.py

…

command_r.py

…

dbrx.py

…

deci.py

…

deepseek.py

convert : fix DeepseekV4 rope parameters with transformers 5.x (#26673)

2026-08-06 16:06:52 +03:00

dots1.py

…

dotsocr.py

…

dream.py

…

ernie.py

…

exaone.py

convert : accept "ExaoneMoeForCausalLM" arch spelling (#26660)

2026-08-06 18:56:04 +08:00

falcon_h1.py

…

falcon.py

…

gemma.py

…

glm.py

model : support MTP in GLM-4.7-Flash (#24868)

2026-08-03 20:27:52 +02:00

gpt2.py

…

gpt_oss.py

…

gptneox.py

…

granite.py

model : Granite-Switch Architecture (#25107)

2026-08-10 09:53:46 +02:00

grok.py

…

grovemoe.py

…

hunyuan.py

convert: fix handle HunyuanVL XD-RoPE config (#25514)

2026-07-22 00:42:35 +02:00

internlm.py

…

internvl.py

…

jais.py

…

jamba.py

…

januspro.py

…

kimi_linear.py

…

kimivl.py

mtmd: add GLM-5.2-Vision (#26126)

2026-07-26 20:43:51 +02:00

laguna.py

Add support for Laguna XS.2 & M.1 (#25165)

2026-07-22 09:54:08 +08:00

lfm2.py

…

lighton_ocr.py

…

llada.py

…

llama4.py

…

llama.py

convert : add missing return after setting tekken vocab (#25947)

2026-08-04 11:41:18 +03:00

llava.py

…

maincoder.py

…

mamba.py

…

mellum.py

…

mimo.py

mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190)

2026-07-27 23:17:09 +02:00

minicpm.py

mtmd: add minicpmv46 downsample (#25993)

2026-08-01 13:38:36 +02:00

minimax.py

mtmd: Add Vision Support for Minimax-M3 (#25113)

2026-07-27 01:44:41 +02:00

mistral3.py

…

mistral.py

…

mpt.py

…

nanbeige.py

model: Add support for Nanbeige4.2 (#25994)

2026-07-27 17:04:18 +02:00

nemotron.py

model: add MTP support for Nemotron model (#26725)

2026-08-10 11:25:24 +03:00

olmo.py

…

openelm.py

…

orion.py

…

pangu.py

…

phi.py

…

pixtral.py

…

plamo.py

…

plm.py

…

qwen3tts.py

mtmd: support Qwen3-TTS (note: breaking change to llama-tts binary) (#26254)

2026-08-04 17:26:15 +02:00

qwen3vl.py

…

qwen.py

convert : import bytes_to_unicode from convert_slow_tokenizer (#26217)

2026-08-04 10:34:30 +03:00

qwenvl.py

conversion: fix Qwen2.5-Omni mmproj conversion regression (#26262)

2026-07-29 12:53:44 +02:00

refact.py

…

rwkv.py

…

sarashina2.py

…

smallthinker.py

…

smolvlm.py

…

stablelm.py

…

starcoder.py

…

step3.py

convert_hf_to_gguf: support split MTP export for HY V3 (#25641)

2026-07-14 11:43:15 +02:00

t5.py

…

talkie.py

…

ultravox.py

…

wavtokenizer.py

…

xverse.py

…

youtuvl.py

…