TheBlokeAI
/

jackfram_llama-68m-GPTQ

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

jackfram_llama-68m-GPTQ / README.md

TheBloke's picture

Update README.md

b415e46 about 1 year ago

|

171 Bytes

	A 4-bit, 128g, act_order=True GPTQ quantisation of JackFram/llama-68m, a 68 million parameter Llama1 model; created on request for software testing.

	Not for normal usage!