Hugging Face's logo

v000000
/
L3.1-Niitorm-8B-DPO-t0.0001

Text Generation
Transformers
Safetensors
llama
Merge
dpo
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
2
v000000 commited on
Commit
e695cdc
•
1 Parent(s): b4d596a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -22,11 +22,11 @@ DPO Gutenberg Finetune version. RP model, Niitama 1.1 as a base, nearswapped wit
22
 
23
  -------------------------------------------------------------------------------
24
 
25
- ## finetune and merge
26
 
27
  This is a merge and finetune of pre-trained language models.
28
 
29
- *Resultant merge finetuned* on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) for 1 epoch 1.5e-5 learning rate.
30
 
31
  ## Merge Details
32
  ### Merge Method
@@ -59,7 +59,7 @@ dtype: bfloat16
59
  out_type: float16 #oops
60
  ```
61
 
62
- *Resultant merge finetuned* on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) for 1 epoch 1.5e-5 learning rate.
63
 
64
  # Prompt Template:
65
  ```bash
 
22
 
23
  -------------------------------------------------------------------------------
24
 
25
+ ## Finetune and merge
26
 
27
  This is a merge and finetune of pre-trained language models.
28
 
29
+ *Resultant merge finetuned* on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) for 1 epoch, 1.5e-5 learning rate.
30
 
31
  ## Merge Details
32
  ### Merge Method
 
59
  out_type: float16 #oops
60
  ```
61
 
62
+ *Resultant merge finetuned* on [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1) for 1 epoch, 1.5e-5 learning rate.
63
 
64
  # Prompt Template:
65
  ```bash