Views
No views yet
[!CAUTION] ⚠️ Warning: This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use Alpaca template.
mistralai/Mistral-7B-v0.1 was lightly trained on a custom dataset to uncensor the model and train it on Cthulhu mythos.v1.0 Training Steps: 100Alpaca template to prevent errors. The dataset was specifically calibrated using Alpaca format due to issues with ChatML tokenizer.\n### Instruction:\n \n### Response:\n1<<<<<<
2 # --- 4. Load Tokenizer ---
3 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, local_files_only=True)
4 if tokenizer.pad_token is None:
5 tokenizer.pad_token = tokenizer.eos_token
6 tokenizer.padding_side = "right"
7======
8 # --- 4. Load Tokenizer ---
9 tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH, local_files_only=True)
10
11 # FIX: Use <unk> (ID 0) for padding instead of EOS (ID 2)
12 # This prevents the model from learning to stop generating prematurely
13 tokenizer.pad_token_id = 0 # unk_token_id for Mistral/Llama
14 tokenizer.padding_side = "right"
15>>>>>>