Models
Datasets
Spaces
Docs
Enterprise
SoraWatermarkRemover
Log In
Sign Up

study-hjt
/

Meta-Llama-3-70B-Instruct-GPTQ-Int8

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

Meta-Llama-3-70B-Instruct-GPTQ-Int8

74.3 GB

2 contributors

History: 2 commits

Jintao Huang

first commit

cab4783 over 1 year ago

.gitattributes

1.52 kB

initial commit over 1 year ago
.mdl

70 Bytes

first commit over 1 year ago
.msc

1.37 kB

first commit over 1 year ago
.mv

36 Bytes

first commit over 1 year ago
README.md

38.1 kB

first commit over 1 year ago
config.json

1.03 kB

first commit over 1 year ago
configuration.json

61 Bytes

first commit over 1 year ago
generation_config.json

126 Bytes

first commit over 1 year ago
model-00001-of-00008.safetensors

10 GB
xet

first commit over 1 year ago
model-00002-of-00008.safetensors

9.78 GB
xet

first commit over 1 year ago
model-00003-of-00008.safetensors

9.88 GB
xet

first commit over 1 year ago
model-00004-of-00008.safetensors

9.88 GB
xet

first commit over 1 year ago
model-00005-of-00008.safetensors

9.96 GB
xet

first commit over 1 year ago
model-00006-of-00008.safetensors

9.96 GB
xet

first commit over 1 year ago
model-00007-of-00008.safetensors

9.88 GB
xet

first commit over 1 year ago
model-00008-of-00008.safetensors

4.97 GB
xet

first commit over 1 year ago
model.safetensors.index.json

241 kB

first commit over 1 year ago
quantize_config.json

223 Bytes

first commit over 1 year ago
special_tokens_map.json

359 Bytes

first commit over 1 year ago
tokenizer.json

9.09 MB

first commit over 1 year ago
tokenizer_config.json

50.8 kB

first commit over 1 year ago