Hugging Face's logo

Varadrajan
/
Foundation-Sec-8B-Reasoning-INT8-W8A16

Safetensors
llama
int8
w8a16
gptq
compressed-tensors
quantized
cybersecurity
reasoning
Model card Files
xet
 Community

Foundation-Sec-8B-Reasoning-INT8-W8A16

8-bit W8A16 (GPTQ / compressed-tensors) quantization of fdtn-ai/Foundation-Sec-8B-Reasoning.

Downloads last month
10
Safetensors
Model size
8B params
Tensor type
I32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Varadrajan/Foundation-Sec-8B-Reasoning-INT8-W8A16

Base model

meta-llama/Llama-3.1-8B
Finetuned
fdtn-ai/Foundation-Sec-8B
Finetuned
fdtn-ai/Foundation-Sec-8B-Reasoning
Quantized
(11)
this model

Collection including Varadrajan/Foundation-Sec-8B-Reasoning-INT8-W8A16