Ara Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b-in... Deu Endpoints compatible Eng Fra Instruct Ita Jpn Kor Lora Mergekit Peft Por Region:us Rus Safetensors Spa Tha Vie Zho
Model Card on HF 🤗: https://huggingface.co/nbeerbower/Qwen2.5-32B-abliterated-LORA
Qwen2.5 32B Abliterated LORA Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Qwen2.5 32B Abliterated LORA Parameters and Internals
| LLM Name | Qwen2.5 32B Abliterated LORA |
| Repository 🤗 | https://huggingface.co/nbeerbower/Qwen2.5-32B-abliterated-LORA |
| Base Model(s) | |
| Model Size | 32b |
| Required VRAM | 1.1 GB |
| Updated | 2025-05-17 |
| Maintainer | nbeerbower |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | up_proj|o_proj|gate_proj|q_proj|embed_tokens|k_proj|lm_head|down_proj|v_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
Rank the Qwen2.5 32B Abliterated LORA 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? 47402 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227