19.5 GB

Ctrl+K

1 contributor

History: 7 commits

kannappans

Attribution: Kannappan Sirchabesan (@kannappans )

b823e8a verified 4 months ago

eval
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
results
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
rl-floor
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
scripts
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
.gitattributes

1.58 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
HF_README.md

3.26 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
LICENSE.md

11.3 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
README.md

4.26 kB
Attribution: Kannappan Sirchabesan (@kannappans) 4 months ago
SUBMISSION.md

3.62 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
attn_precision_microbench.py

4.94 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
chat_template.jinja

6.23 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
config.json

5.21 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
configuration_laguna.py

9.73 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
fix_and_requant.sh

1.72 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
generation_config.json

184 Bytes
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model-00001-of-00005.safetensors

3.07 GB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model-00002-of-00005.safetensors

5.12 GB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model-00003-of-00005.safetensors

5.12 GB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model-00004-of-00005.safetensors

5.12 GB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model-00005-of-00005.safetensors

1.01 GB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
model.safetensors.index.json

12.1 MB
xet

Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
modeling_laguna.py

34.1 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
quality_eval.sh

1.74 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
quant_attn_manual.py

5.09 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
quant_attn_nvfp4.py

5.57 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
quant_frontier.py

3.78 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
quant_only.sh

777 Bytes
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
quantize_attention.py

6.61 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
run_all_unattended.sh

4.55 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
serve_and_bench.sh

1.55 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
setup_and_quant.sh

1.92 kB
Hackathon submission: Laguna NVFP4-attention + quantization study 4 months ago
special_tokens_map.json

214 Bytes
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
tokenizer.json

7.29 MB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago
tokenizer_config.json

13 kB
Add fully-NVFP4-attention Laguna weights (19GB) 4 months ago