nenkoru
/

alpaca-lora-7b-onnx-fp16-with-past

Text Generation

Inference Endpoints

Model card Files Files and versions Community

nenkoru commited on Mar 29, 2023

Commit

3691a73

·

1 Parent(s): d50e705

Update README.md

Files changed (1) hide show

README.md +1 -4

README.md CHANGED Viewed

@@ -2,11 +2,8 @@
 license: other
 ---
 # alpaca-lora-7b
-This LoRA trained for 3 epochs and has been converted to int4 via GPTQ method. See the repo below for more info.
-https://github.com/qwopqwop200/GPTQ-for-LLaMa
----
 1. Exported to hf format using https://github.com/tloen/alpaca-lora(float32, no 8bit)
 2. Exported to ONNX format using optimum library(https://github.com/huggingface/optimum/pull/922)(also see fp32 repo)
 3. Loaded vanilla fp32 and then exported to ONNX using optimum library(https://github.com/huggingface/optimum/pull/922) with this:

 license: other
 ---
 # alpaca-lora-7b
+This LoRA trained for 3 epochs.
 1. Exported to hf format using https://github.com/tloen/alpaca-lora(float32, no 8bit)
 2. Exported to ONNX format using optimum library(https://github.com/huggingface/optimum/pull/922)(also see fp32 repo)
 3. Loaded vanilla fp32 and then exported to ONNX using optimum library(https://github.com/huggingface/optimum/pull/922) with this: