tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Feat: Add example for Mistral (#644)

Browse Source 
* Feat: Add example for Mistral

* chore: turn off flash

* chore: add is_mistral_derived_model

* chore: update following PR
This commit is contained in:
NanoCode012
2023-09-28 20:15:00 +09:00
committed by GitHub
parent 383f88d7a7
commit eb41f76f92
3 changed files with 79 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -413,9 +413,10 @@ tokenizer_legacy:
# this is reported to improve training speed on some models
resize_token_embeddings_to_32x:
# used to identify if the model is falcon/llama based
# used to identify which the model is based on
is_falcon_derived_model:
is_llama_derived_model:
is_mistral_derived_model:
# whether you are training a 4-bit GPTQ quantized model
gptq: true