tokenlabsdotrun
/

Llama-3.1-8B-ModelOpt-FP8

nvidia-modeloptimizer

Model card Files Files and versions

Llama-3.1-8B-ModelOpt-FP8

9.1 GB

Ctrl+K

Ctrl+K

1 contributor

History: 3 commits

genai2eliza's picture

Upload Llama-3.1-8B quantized with ModelOpt FP8

cda4bbd verified 4 months ago

.gitattributes

1.57 kB
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
README.md

1.37 kB
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
chat_template.jinja

4.61 kB
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
config.json

868 Bytes
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
generation_config.json

184 Bytes
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
hf_quant_config.json

239 Bytes
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
model-00001-of-00002.safetensors

5 GB
xet

Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
model-00002-of-00002.safetensors

4.08 GB
xet

Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
model.safetensors.index.json

62.8 kB
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
special_tokens_map.json

325 Bytes
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
tokenizer.json

17.2 MB
xet

Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago
tokenizer_config.json

50.6 kB
Upload Llama-3.1-8B quantized with ModelOpt FP8 4 months ago