Hugging Face's logo

HermitQ
/
NPCAlign-DPO

PEFT
Safetensors
English
lora
dpo
rlhf
npc
roleplay
dialogue
game-ai
Model card Files
xet
 Community
1
HermitQ commited on
Commit
00b975d
·
verified ·
1 Parent(s): 52d7a2d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -32,8 +32,10 @@ on the base Llama model.** See Usage section.
32
 
33
  ## Usage
34
  > **Note:** The base model [`meta-llama/Meta-Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) is a gated model. You must accept Meta's license and set your `HF_TOKEN` before loading.
 
35
  from peft import PeftModel
36
  ...
 
37
  # Step 1: Load base + SFT, merge
38
  sft = PeftModel.from_pretrained(base, "HermitQ/NPCAlign-SFT")
39
  merged = sft.merge_and_unload()
 
32
 
33
  ## Usage
34
  > **Note:** The base model [`meta-llama/Meta-Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) is a gated model. You must accept Meta's license and set your `HF_TOKEN` before loading.
35
+
36
  from peft import PeftModel
37
  ...
38
+
39
  # Step 1: Load base + SFT, merge
40
  sft = PeftModel.from_pretrained(base, "HermitQ/NPCAlign-SFT")
41
  merged = sft.merge_and_unload()