GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
OMCHOKSI108
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
OMCHOKSI108
Model Tree
Qwen/Qwen2.5-Coder-3B
Input Modalities
Output Modalities
Supported Functionality
This repository is a documented mirror/fork of the original VibeThinker-3B model. Original model credits belong to WeiboAI and contributors.
| Resource | Link |
|---|---|
| This Mirror | OMCHOKSI108/VibeThinker-3B |
| Original HF Model | WeiboAI/VibeThinker-3B |
| Original GitHub | WeiboAI/VibeThinker |
| This GitHub Fork | OMCHOKSI108/VibeThinkerModel |
| Technical Report | arXiv:2606.16140 |
| Original README | ORIGINAL_README.md (preserved verbatim) |
This is a documented mirror of the original VibeThinker-3B model weights for learning, experimentation, and structured usage. It includes:
No model weights have been modified. No additional training or fine-tuning has been performed.
VibeThinker-3B is a 3-billion-parameter dense reasoning model developed by WeiboAI. It is built upon Qwen2.5-Coder-3B and post-trained with an upgraded Spectrum-to-Signal (SSP) pipeline. The model is designed for tasks with reliable verification signals, including:
The technical report shows that VibeThinker-3B can reach frontier-level performance on several verifiable reasoning benchmarks while remaining much smaller than typical frontier reasoning systems.
VibeThinker-3B follows the Spectrum-to-Signal Principle (SSP) introduced in VibeThinker-1.5B. The SFT stage constructs a broad spectrum of valid reasoning trajectories, while the RL stage amplifies correct reasoning signals using verifiable rewards.
The training pipeline contains the following stages:
For full details, see the original model card and the technical report.
bash
pip install transformers>=4.54.0For better inference performance:
bash
pip install vllm==0.10.1# orpip install sglang>=0.4.9.post6python
from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "WeiboAI/VibeThinker-3B", # or "OMCHOKSI108/VibeThinker-3B" low_cpu_mem_usage=True, torch_dtype="bfloat16", device_map="auto",)tokenizer = AutoTokenizer.from_pretrained( "WeiboAI/VibeThinker-3B", trust_remote_code=True,)python
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig model = AutoModelForCausalLM.from_pretrained( "OMCHOKSI108/VibeThinker-3B", low_cpu_mem_usage=True, torch_dtype="bfloat16", device_map="auto",)tokenizer = AutoTokenizer.from_pretrained( "OMCHOKSI108/VibeThinker-3B", trust_remote_code=True,) messages = [{"role": "user", "content": "What is the sum of the first 100 prime numbers?"}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device) outputs = model.generate( **inputs, generation_config=GenerationConfig( max_new_tokens=40960, do_sample=True, temperature=0.6, top_p=0.95, top_k=None, ),)response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(response)| Precision | Min VRAM | Recommended GPU |
|---|---|---|
| bfloat16 | ~8 GB | RTX 3070+ / A10G+ |
| float32 | ~16 GB | A100+ |
Original model credits belong to WeiboAI and contributors.
See ATTRIBUTION.md for full details.
The model repository is licensed under the MIT License (inherited from the original).
pip install vllm==0.10.1# orpip install sglang>=0.4.9.post6from transformers import AutoModelForCausalLM, AutoTokenizer model = AutoModelForCausalLM.from_pretrained( "WeiboAI/VibeThinker-3B", # or "OMCHOKSI108/VibeThinker-3B" low_cpu_mem_usage=True, torch_dtype="bfloat16", device_map="auto",)tokenizer = AutoTokenizer.from_pretrained( "WeiboAI/VibeThinker-3B", trust_remote_code=True,)from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig model = AutoModelForCausalLM.from_pretrained( "OMCHOKSI108/VibeThinker-3B", low_cpu_mem_usage=True, torch_dtype="bfloat16", device_map="auto",)tokenizer = AutoTokenizer.from_pretrained( "OMCHOKSI108/VibeThinker-3B", trust_remote_code=True,) messages = [{"role": "user", "content": "What is the sum of the first 100 prime numbers?"}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device) outputs = model.generate( **inputs, generation_config=GenerationConfig( max_new_tokens=40960, do_sample=True, temperature=0.6, top_p=0.95, top_k=None, ),)response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(response)