Pinkstack commited on
Commit
ec99b1a
·
verified ·
1 Parent(s): 8081def

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ Fine tuned on finetome, pinkchat-sft, pinkchat-dpo, the model is able to generat
18
  ## Additional fine-tuning is needed.
19
  The model does not perform well, yet it does work. It has been fine tuned on 2 billion tokens of mostly syntetic data and some human made data in the sft process.
20
 
21
- Phase 0: In mergekit, we remove 16 layers (out of 28, so 12 layers left) using passthrough.
22
 
23
  Phase 1a: Fine tuning the model on a limited amount of data, lora 16 (21% trained). This phase is to get the model started on generating some sense, mainly for healing the model and nothing else, very low quality text would be generated.
24
 
 
18
  ## Additional fine-tuning is needed.
19
  The model does not perform well, yet it does work. It has been fine tuned on 2 billion tokens of mostly syntetic data and some human made data in the sft process.
20
 
21
+ Phase 0: In mergekit, we remove 16 layers (out of 28, so 12 layers left: Pinkstackorg/Qwen2.5-3Bprunebase-1M) using passthrough.
22
 
23
  Phase 1a: Fine tuning the model on a limited amount of data, lora 16 (21% trained). This phase is to get the model started on generating some sense, mainly for healing the model and nothing else, very low quality text would be generated.
24