Abliterated Autotrain compatible Base model:finetune:lgai-exaon... Base model:lgai-exaone/exaone-... Chat Conversational Custom code En Exaone Exaone-deep Ko Lg-ai Region:us Safetensors Uncensored
Model Card on HF 🤗: https://huggingface.co/huihui-ai/Huihui-EXAONE-Deep-2.4B-abliterated
Huihui EXAONE Deep 2.4B Abliterated 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)
Huihui EXAONE Deep 2.4B Abliterated Parameters and Internals
| LLM Name | Huihui EXAONE Deep 2.4B Abliterated |
| Repository 🤗 | https://huggingface.co/huihui-ai/Huihui-EXAONE-Deep-2.4B-abliterated |
| Base Model(s) | |
| Model Size | 2.4b |
| Required VRAM | 4.8 GB |
| Updated | 2025-07-11 |
| Maintainer | huihui-ai |
| Model Type | exaone |
| Model Files | |
| Supported Languages | en ko |
| Model Architecture | ExaoneForCausalLM |
| License | other |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.52.4 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | [PAD] |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
| Activation Function | silu |
Best Alternatives to Huihui EXAONE Deep 2.4B Abliterated
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| EXAONE 3.5 2.4B Instruct | 32K / 9.7 GB | 149802 | 164 |
| EXAONE Deep 2.4B | 32K / 4.8 GB | 23034 | 94 |
| ... 3.5 2.4B Instruct Abliterated | 32K / 10.8 GB | 1185 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than huihui-ai/Huihui-EXAONE-Deep-2.4B-abliterated .
Rank the Huihui EXAONE Deep 2.4B Abliterated 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? 49533 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124