danielpark
/

gorani-100k-llama2-13b-instruct

Text Generation

bitsandbytes, transformers, peft, accelerate, bitsandbytes, datasets, deepspeed, trl

Model card Files Files and versions Community

danielpark commited on Oct 7, 2023

Commit

3e3680a

·

1 Parent(s): 0700430

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -51,6 +51,7 @@ The model weights and dataset have not been properly curated yet and are strictl
 ## Revision Infomations
 Revision 1: [6d30494fa8da84128499d55075eef57094336d03](https://huggingface.co/danielpark/gorani-100k-llama2-13b-instruct/commit/6d30494fa8da84128499d55075eef57094336d03)
 - max_seq_length = 2048, partially modified tokenizer(related with pad token), default train param, tokenizer need to be fixed (refer 10k tokenizer)
 <details>

 ## Revision Infomations
 Revision 1: [6d30494fa8da84128499d55075eef57094336d03](https://huggingface.co/danielpark/gorani-100k-llama2-13b-instruct/commit/6d30494fa8da84128499d55075eef57094336d03)
+- 19.74k fine-tuned model weight
 - max_seq_length = 2048, partially modified tokenizer(related with pad token), default train param, tokenizer need to be fixed (refer 10k tokenizer)
 <details>