Sehyo
/

Qwen3.5-35B-A3B-NVFP4

compressed-tensors

Mixture of Experts

Model card Files Files and versions

Qwen3.5-35B-A3B-NVFP4

25.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 6 commits

Sehyo's picture

fix: add MTP ignore patterns to quantization config for speculative decoding

1393d72 verified 3 months ago

.gitattributes

1.64 kB
Re-quantize with MTP weights preserved for speculative decoding 3 months ago
README.md

1.38 kB
Re-quantize with MTP weights preserved for speculative decoding 3 months ago
chat_template.jinja

7.76 kB
Upload folder using huggingface_hub 3 months ago
config.json

36.2 kB
fix: add MTP ignore patterns to quantization config for speculative decoding 3 months ago
extra_weights.safetensors

1.69 GB
xet

Re-quantize with MTP weights preserved for speculative decoding 3 months ago
generation_config.json

213 Bytes
Re-quantize with MTP weights preserved for speculative decoding 3 months ago
model.safetensors

23.4 GB
xet

Upload folder using huggingface_hub 3 months ago
model.safetensors.index.json

12.5 MB
xet

Re-quantize with MTP weights preserved for speculative decoding 3 months ago
preprocessor_config.json

390 Bytes
Upload folder using huggingface_hub 3 months ago
recipe.yaml

274 Bytes
Re-quantize with MTP weights preserved for speculative decoding 3 months ago
tokenizer.json

20 MB
xet

Re-quantize with MTP weights preserved for speculative decoding 3 months ago
tokenizer_config.json

1.1 kB
Upload tokenizer_config.json with huggingface_hub 3 months ago
video_preprocessor_config.json

385 Bytes
Upload folder using huggingface_hub 3 months ago
vocab.json

6.72 MB
Upload folder using huggingface_hub 3 months ago