ennerd/Laguna-S-2.1-NVFP4 at main

Laguna-S-2.1-NVFP4

68.9 GB

Ctrl+K

Ctrl+K

1 contributor

History: 26 commits

frodeborli's picture

docker: add patches_lo loader patch

33ffcef verified 14 days ago

dflash
Add bundled 4-bit (NVFP4 weight-only) DFlash drafter 14 days ago
patches_lo
docker: add patches_lo loader patch 14 days ago
.gitattributes
1.58 kB
Add files using upload-large-folder tool 17 days ago
DOCKER.md
3.66 kB
docker: add DOCKER.md 14 days ago
Dockerfile
2.9 kB
docker: add Dockerfile 14 days ago
LICENSE.md
2.62 kB
Add files using upload-large-folder tool 17 days ago
README.md
17.2 kB
Card: step-by-step run instructions — Standard (vLLM/BF16) + Maximum (Docker/4-bit) 14 days ago
chart_accuracy.svg
12.1 kB
Add performance charts (decode/accuracy/context/DFlash-tuning SVGs) + quantization script 16 days ago
chart_concurrency.svg
22.6 kB
Add concurrency chart: pure DP+EP overtakes TP=2 at scale (790 vs 505 tok/s @ 128-way) 16 days ago
chart_context.svg
28.6 kB
Refresh perf charts from clean 12-config benchmark sweep (single+dual GB10 decode, context, prefill) 16 days ago
chart_decode.svg
11.9 kB
Refresh perf charts from clean 12-config benchmark sweep (single+dual GB10 decode, context, prefill) 16 days ago
chart_decode_dual.svg
11.9 kB
Refresh perf charts from clean 12-config benchmark sweep (single+dual GB10 decode, context, prefill) 16 days ago
chart_ksweep.svg
13.3 kB
Add performance charts (decode/accuracy/context/DFlash-tuning SVGs) + quantization script 16 days ago
chart_prefill.svg
26.9 kB
Refresh perf charts from clean 12-config benchmark sweep (single+dual GB10 decode, context, prefill) 16 days ago
chat_template.jinja
3.96 kB
Add files using upload-large-folder tool 17 days ago
config.json
7.38 kB
Add files using upload-large-folder tool 17 days ago
configuration_laguna.py
13.4 kB
Add files using upload-large-folder tool 17 days ago
entrypoint.sh
1.88 kB
docker: add entrypoint.sh 14 days ago
generation_config.json
485 Bytes
Add files using upload-large-folder tool 17 days ago
model-00001-of-00015.safetensors
2.13 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00002-of-00015.safetensors
4.09 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00003-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00004-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00005-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00006-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00007-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00008-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00009-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00010-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00011-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00012-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00013-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00014-of-00015.safetensors
5.12 GB
xet

Add files using upload-large-folder tool 17 days ago
model-00015-of-00015.safetensors
234 MB
xet

Add files using upload-large-folder tool 17 days ago
model.safetensors.index.json
14 MB
xet

Add files using upload-large-folder tool 17 days ago
modeling_laguna.py
40.9 kB
Add files using upload-large-folder tool 17 days ago
quantize_attention.py
6.56 kB
Add performance charts (decode/accuracy/context/DFlash-tuning SVGs) + quantization script 16 days ago
special_tokens_map.json
214 Bytes
Add files using upload-large-folder tool 17 days ago
tokenizer.json
7.29 MB
Add files using upload-large-folder tool 17 days ago
tokenizer_config.json
13 kB
Add files using upload-large-folder tool 17 days ago