Bullshit 7B V2 is an open-source language model by faced65r64. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, Quantized, Instruction-Based.
4bit Conversational Endpoints compatible Generated from trainer Instruct Quantized Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/faced65r64/bullshit-7b-v2
Bullshit 7B V2 Parameters and Internals
| LLM Name | Bullshit 7B V2 |
| Repository 🤗 | https://huggingface.co/faced65r64/bullshit-7b-v2 |
| Model Name | contamination-v2 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2026-04-19 |
| Maintainer | faced65r64 |
| Model Type | qwen2 |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|PAD_TOKEN|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Best Alternatives to Bullshit 7B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen2.5 7B Instruct 1M 4bit | 986K / 4.3 GB | 422 | 10 |
| ...B Instruct 1M Unsloth Bnb 4bit | 986K / 7.5 GB | 77 | 3 |
| Qwen2.5 7B Instruct 1M 8bit | 986K / 8.1 GB | 40 | 3 |
| Qwen2.5 7B Instruct 1M 6bit | 986K / 6.2 GB | 23 | 2 |
| Alisia 7B Instruct V1 | 128K / 15.4 GB | 114 | 2 |
| ...5 7B Instruct SFT Meme LoRA V7 | 128K / 15.2 GB | 6 | 0 |
| Gte Qwen2 7B Instruct 4bit DWQ | 128K / 4.3 GB | 67 | 3 |
| Securereview 7B Mlx 4bit | 32K / 4.3 GB | 15 | 2 |
| Distill Qw Test | 32K / 15.2 GB | 5 | 0 |
| Zirel 7B Math | 32K / 15.2 GB | 22 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than faced65r64/bullshit-7b-v2 .
Rank the Bullshit 7B V2 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 52996 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a