amd
/

Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

Model card Files Files and versions

Mixtral-8x7B-Instruct-v0.1-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8

38.2 GB

2 contributors

History: 13 commits

XuebinWang's picture

remove unused weight file model-00007-of-00007.safetensors

72bb4a6 verified 10 days ago

.gitattributes

1.52 kB

initial commit 3 months ago
README.md

3.18 kB

update model with several fixings (#5) 11 days ago
chat_template.jinja

1.06 kB

upload model (#1) 3 months ago
config.json

1.13 MB

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
generation_config.json

111 Bytes

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00001-of-00008.safetensors

4.98 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00002-of-00008.safetensors

4.98 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00003-of-00008.safetensors

4.99 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00004-of-00008.safetensors

4.97 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00005-of-00008.safetensors

5 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00006-of-00008.safetensors

4.95 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00007-of-00008.safetensors

4.94 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model-00008-of-00008.safetensors

3.44 GB
xet

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
model.safetensors.index.json

243 kB

update Quark quantized Mixtral-8x7B-Instruct-v0.1 AMP model with better accuracies (#3) about 2 months ago
special_tokens_map.json

437 Bytes

upload model (#1) 3 months ago
tokenizer.json

3.51 MB

update the AMP model with better accuracy numbers and lower effective bitwidth (5.6) (#2) about 2 months ago
tokenizer.model

493 kB
xet

upload model (#1) 3 months ago
tokenizer_config.json

1.05 kB

update the AMP model with better accuracy numbers and lower effective bitwidth (5.6) (#2) about 2 months ago