Hugging Face's logo

Blackroot
/
Llama-2-13B-Storywriter-LORA

Model card Files Community
3
Blackroot commited on
Commit
401f03e
•
1 Parent(s): ab0b7e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -6
README.md CHANGED
@@ -1,8 +1,14 @@
1
- ---
2
- library_name: peft
3
- ---
 
 
 
 
 
4
  ## Training procedure
5
 
 
6
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - load_in_8bit: False
@@ -14,7 +20,5 @@ The following `bitsandbytes` quantization config was used during training:
14
  - bnb_4bit_quant_type: fp4
15
  - bnb_4bit_use_double_quant: False
16
  - bnb_4bit_compute_dtype: float32
17
- ### Framework versions
18
-
19
 
20
- - PEFT 0.5.0.dev0
 
1
+ Join the Coffee & AI Discord for AI Stuff and things!
2
+ [![Discord](https://img.shields.io/discord/232596713892872193?logo=discord)](https://discord.gg/2JhHVh7CGu)
3
+
4
+
5
+ https://huggingface.co/TheBloke/Llama-2-13B-GGML
6
+ https://huggingface.co/TheBloke/Llama-2-13B-GPTQ
7
+
8
+
9
  ## Training procedure
10
 
11
+ PEFT:
12
 
13
  The following `bitsandbytes` quantization config was used during training:
14
  - load_in_8bit: False
 
20
  - bnb_4bit_quant_type: fp4
21
  - bnb_4bit_use_double_quant: False
22
  - bnb_4bit_compute_dtype: float32
 
 
23
 
24
+ This ran on for 3500 -- 3 epochs on an in testing storywriting dataset. Training took 14 hours on a 3090 Ti.