Base model:adapter:failspy/met... Base model:failspy/meta-llama-... Endpoints compatible Instruct Lora Mergekit Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B
Llama 3 Instruct Abliteration LoRA 8B 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)
Llama 3 Instruct Abliteration LoRA 8B Parameters and Internals
| LLM Name | Llama 3 Instruct Abliteration LoRA 8B |
| Repository 🤗 | https://huggingface.co/grimjim/Llama-3-Instruct-abliteration-LoRA-8B |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2025-02-05 |
| Maintainer | grimjim |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | AutoModel |
| License | llama3 |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|k_proj|up_proj|v_proj|o_proj|down_proj|q_proj|lm_head |
| LoRA Alpha | 32 |
| LoRA Dropout | 0 |
| R Param | 32 |
Best Alternatives to Llama 3 Instruct Abliteration LoRA 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Abliteration OVA 8B R128 LORA | 0K / 0.7 GB | 0 | 2 |
| L3 Unaligned R256 LoRA | 0K / 1.5 GB | 0 | 1 |
| AblDWP LoRA | 0K / 0.4 GB | 0 | 1 |
| Llama31 Eros Lora | 0K / 0.2 GB | 0 | 1 |
| Talktoai | 0K / 16.1 GB | 0 | 2 |
| Llama 3 8B Instruct Checkit | 0K / 0.2 GB | 0 | 1 |
| ...3 8B Instruct Ct2 Int8 Float16 | 0K / 8 GB | 24 | 0 |
| ...a Llama 3 8B Instruct Ct2 Int8 | 0K / 8 GB | 5 | 0 |
| ...lama 3 LimaRP Instruct LoRA 8B | 0K / 2.7 GB | 20 | 0 |
| Llama 3 Instruct LiPPA LoRA 8B | 0K / 2.7 GB | 11 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than grimjim/Llama-3-Instruct-abliteration-LoRA-8B .
Rank the Llama 3 Instruct Abliteration LoRA 8B 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? 42577 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227