Pradeep-Corethink
/

gemma4-v3-4epoch-quantized-fp8

compressed-tensors

Model card Files Files and versions

gemma4-v3-4epoch-quantized-fp8

28.7 GB

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

Pradeep-Corethink's picture

Pradeep-Corethink

FP8 quantization (router excluded), sanity-checked, pending BFCL eval

3f90a6b verified 3 months ago

.gitattributes

1.57 kB
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
chat_template.jinja

12 kB
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
config.json

216 kB
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
generation_config.json

204 Bytes
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
model.safetensors

28.6 GB
xet

FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
processor_config.json

1.69 kB
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
recipe.yaml

248 Bytes
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
tokenizer.json

32.2 MB
xet

FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago
tokenizer_config.json

2.71 kB
FP8 quantization (router excluded), sanity-checked, pending BFCL eval 3 months ago