GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
prithivMLmods
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
prithivMLmods
Model Tree
WeiboAI/VibeThinker-3B
Input Modalities
Output Modalities
Supported Functionality
prithivMLmods/VibeThinker-3B-heretic_decensored| Parameter | Value |
|---|---|
| direction_index | 21.88 |
| attn.o_proj.max_weight | 1.37 |
| attn.o_proj.max_weight_position | 21.25 |
| attn.o_proj.min_weight | 1.36 |
| attn.o_proj.min_weight_distance | 19.61 |
| mlp.down_proj.max_weight | 1.49 |
| mlp.down_proj.max_weight_position | 31.01 |
| mlp.down_proj.min_weight | 1.48 |
| mlp.down_proj.min_weight_distance | 20.74 |
| Metric | This model | Original model (WeiboAI/VibeThinker-3B) |
|---|---|---|
| KL divergence | 0.0933 | 0 (by definition) |
| Refusals | 6/100 | 64/100 |
bash
pip install transformerspip install acceleratepython
from transformers import AutoTokenizer, AutoModelForCausalLMimport torch model = AutoModelForCausalLM.from_pretrained( "prithivMLmods/VibeThinker-3B-heretic_decensored", torch_dtype="auto", device_map="auto") tokenizer = AutoTokenizer.from_pretrained( "prithivMLmods/VibeThinker-3B-heretic_decensored") messages = [ { "role": "user", "content": "Explain how a transformer model processes text." }] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=512) print( tokenizer.decode( outputs[0][inputs.shape[-1]:], skip_special_tokens=True ))Important Note: This model intentionally reduces built-in refusal mechanisms.
Heretic: Fully automatic censorship removal framework for language models. This project was used to perform the refusal-direction analysis and ablation procedures that form the foundation of this model.
WeiboAI/VibeThinker-3B: The intermediate base model providing the reasoning capabilities used in this release.
Qwen/Qwen2.5-Coder-3B: The foundation model upon which VibeThinker-3B was originally built.
Model Trials & Evaluation: Experimental evaluations, refusal measurements, and optimization trials were conducted and documented during the development process.
pip install transformerspip install acceleratefrom transformers import AutoTokenizer, AutoModelForCausalLMimport torch model = AutoModelForCausalLM.from_pretrained( "prithivMLmods/VibeThinker-3B-heretic_decensored", torch_dtype="auto", device_map="auto") tokenizer = AutoTokenizer.from_pretrained( "prithivMLmods/VibeThinker-3B-heretic_decensored") messages = [ { "role": "user", "content": "Explain how a transformer model processes text." }] inputs = tokenizer.apply_chat_template( messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate( inputs, max_new_tokens=512) print( tokenizer.decode( outputs[0][inputs.shape[-1]:], skip_special_tokens=True ))