Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Meta-Llama-3-70B-Instruct-FP8-v2 – AI Model by comaniac | AlphaNeural AI
You can deploy this model and start earning money today!
comaniac
/
Meta-Llama-3-70B-Instruct-FP8-v2
like
0
transformers
safetensors
llama
text-generation
conversational
autotrain_compatible
text-generation-inference
endpoints_compatible
fp8
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Llama-3-70B-Instruct-FP8-v2
Weights and activations are per-tensor quantized to float8_e4m3.
Quantization with AutoFP8 with the updated activation scaling factor names.
Calibration dataset: Ultrachat (mgoin/ultrachat_2k)
Samples: 1024
Sequence length: 4096
Evaluation
TBA
