bhenrym14
/

airoboros-33b-gpt4-1.4.1-PI-8192-GPTQ

Text Generation

Inference Endpoints

Model card Files Files and versions Community

bhenrym14 commited on Jul 3, 2023

Commit

2453b75

·

1 Parent(s): ea63000

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -5,7 +5,7 @@ datasets:
 # RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (GPTQ)
 ## Overview
-This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (merged model GPTQ Quantization, and LoRA weights) with several key modifications:
 - Context length extended to 8192 by RoPE Scaled Embeddings, but NOT via the superHOT LoRA. I started with base Llama-33b.
 - Training sequences beyond 2048 have the target truncated to equal 2048.
 - Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4
@@ -32,7 +32,7 @@ Recent advancements in extending context by RoPE scaling ([kaiokendev](https://k
 ## Quantization:
-The merged model was quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True). The adapter weights and config are also uploaded.
 ## Prompting:

 # RoPE Scaled QLoRA Finetune of airoboros-33b-gpt4-1.4.1 (GPTQ)
 ## Overview
+This is [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) (merged model with GPTQ Quantization) with several key modifications:
 - Context length extended to 8192 by RoPE Scaled Embeddings, but NOT via the superHOT LoRA. I started with base Llama-33b.
 - Training sequences beyond 2048 have the target truncated to equal 2048.
 - Used airoboros-gpt4-1.4.1 dataset instead of airoboros-gpt4-1.4
 ## Quantization:
+The merged model was quantized with AutoGPTQ (bits = 4, group_size = 128, desc_act = True).
 ## Prompting: