nm-testing
/

Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test

8-bit precision

compressed-tensors

Model card Files Files and versions

Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test

9.09 GB

2 contributors

History: 3 commits

mgoin's picture

Updated compression_config to quantization_config

789cc2a verified about 1 year ago

.gitattributes

1.52 kB

initial commit about 1 year ago
config.json

1.98 kB

Updated compression_config to quantization_config about 1 year ago
generation_config.json

194 Bytes

Upload folder using huggingface_hub about 1 year ago
model-00001-of-00002.safetensors

5 GB
xet

Upload folder using huggingface_hub about 1 year ago
model-00002-of-00002.safetensors

4.08 GB
xet

Upload folder using huggingface_hub about 1 year ago
model.safetensors.index.json

43.5 kB

Upload folder using huggingface_hub about 1 year ago
special_tokens_map.json

296 Bytes

Upload folder using huggingface_hub about 1 year ago
tokenizer.json

9.09 MB

Upload folder using huggingface_hub about 1 year ago
tokenizer_config.json

51 kB

Upload folder using huggingface_hub about 1 year ago