| .. |
|
__init__.py
|
spec: add DSpark speculative decoding (#25173)
|
2026-07-28 14:43:27 +03:00 |
|
afmoe.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
arctic.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
baichuan.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
bailingmoe.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
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
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
chameleon.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
chatglm.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
codeshell.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
cogvlm.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
command_r.py
|
Add arch support for cohere2-MoE (#24260)
|
2026-06-13 19:49:00 +02:00 |
|
dbrx.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
deci.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
deepseek.py
|
DeepSeek V4 (#24162)
|
2026-06-29 16:58:51 +08:00 |
|
dots1.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
dotsocr.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
dream.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
ernie.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
exaone.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
falcon.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
falcon_h1.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
gemma.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
glm.py
|
model: add NextN/MTP speculative decoding support for GLM_DSA (GLM-5.2) (#25980)
|
2026-07-29 14:02:31 +08:00 |
|
gpt2.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
gpt_oss.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
gptneox.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
granite.py
|
model: Granite Speech Plus (#24818)
|
2026-06-23 12:03:31 +02:00 |
|
grok.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
grovemoe.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
hunyuan.py
|
convert: fix handle HunyuanVL XD-RoPE config (#25514)
|
2026-07-22 00:42:35 +02:00 |
|
internlm.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
internvl.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
jais.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
jamba.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
januspro.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
kimi_linear.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
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
|
model : Add LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M (#24913)
|
2026-06-24 09:49:46 +03:00 |
|
lighton_ocr.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
llada.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
llama.py
|
spec: add eagle3-v3 support for gpt-oss model (#25794)
|
2026-07-28 09:58:16 +03:00 |
|
llama4.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
llava.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
maincoder.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
mamba.py
|
mamba2: remove hardcoded 2x expansion factor and invalid d_inner % d_state check (#23082)
|
2026-06-26 08:50:54 +03:00 |
|
mellum.py
|
model: add Mellum architecture (#23966)
|
2026-06-02 22:11:12 +03:00 |
|
mimo.py
|
mtmd: support MiMo-V2.5 audio input (RVQ-based model) (#26190)
|
2026-07-27 23:17:09 +02:00 |
|
minicpm.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
minimax.py
|
mtmd: Add Vision Support for Minimax-M3 (#25113)
|
2026-07-27 01:44:41 +02:00 |
|
mistral.py
|
convert : fix conversion for Mistral-Medium-3.5-128B (#24268)
|
2026-06-07 21:41:39 +02:00 |
|
mistral3.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
mpt.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
nanbeige.py
|
model: Add support for Nanbeige4.2 (#25994)
|
2026-07-27 17:04:18 +02:00 |
|
nemotron.py
|
mtmd : add Nemotron 3 Nano Omni support (parakeet) (#22520)
|
2026-07-28 17:20:25 +02:00 |
|
olmo.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
openelm.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
orion.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
pangu.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
phi.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
pixtral.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
plamo.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
plm.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
qwen.py
|
spec: add DSpark speculative decoding (#25173)
|
2026-07-28 14:43:27 +03:00 |
|
qwen3vl.py
|
convert : fix Qwen3 ASR conversion (#23081)
|
2026-05-15 18:38:39 +02:00 |
|
qwenvl.py
|
conversion: fix Qwen2.5-Omni mmproj conversion regression (#26262)
|
2026-07-29 12:53:44 +02:00 |
|
refact.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
rwkv.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
sarashina2.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
smallthinker.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
smolvlm.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
stablelm.py
|
convert : more consistent handling of rope_parameters (#24833)
|
2026-06-20 13:42:36 +03:00 |
|
starcoder.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
step3.py
|
convert_hf_to_gguf: support split MTP export for HY V3 (#25641)
|
2026-07-14 11:43:15 +02:00 |
|
t5.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
talkie.py
|
model : add support for talkie-1930-13b (#22596)
|
2026-05-26 07:57:38 +03:00 |
|
ultravox.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
wavtokenizer.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
xverse.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
|
youtuvl.py
|
Refactor: convert_hf_to_gguf.py (#17114)
|
2026-05-15 15:18:12 +02:00 |
