10.8 GB

1 contributor

History: 8 commits

canesin

Add vocab.json from Qwen2-7B

73b6a7a verified 20 days ago

.gitattributes

199 Bytes

Add FP8 quantized VibeVoice-ASR checkpoint 22 days ago
README.md

4.35 kB

Add FP8 quantized VibeVoice-ASR checkpoint 22 days ago
config.json

3.61 kB

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
fp8_report.json

154 Bytes

Add quantization report 22 days ago
merges.txt

1.67 MB

Add merges.txt from Qwen2-7B 20 days ago
model-00001-of-00008.safetensors

1.79 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00002-of-00008.safetensors

1.19 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00003-of-00008.safetensors

1.23 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00004-of-00008.safetensors

1.23 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00005-of-00008.safetensors

1.25 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00006-of-00008.safetensors

1.57 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00007-of-00008.safetensors

1.44 GB
xet

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
model-00008-of-00008.safetensors

1.09 GB
xet

Add FP8 quantized VibeVoice-ASR checkpoint 22 days ago
model.safetensors.index.json

141 kB

Convert to mistral.rs FP8 format (weight_scale_inv naming, quant_method=fp8) 20 days ago
tokenizer.json

7.03 MB

Add tokenizer.json from Qwen2-7B 20 days ago
tokenizer_config.json

1.29 kB

Add tokenizer_config.json from Qwen2-7B 20 days ago
vocab.json

2.78 MB

Add vocab.json from Qwen2-7B 20 days ago