Base model:failspy/llama-3-70b... Base model:finetune:failspy/ll... Endpoints compatible Instruct Lora Mergekit Peft Region:us Safetensors
Llama 3 70B Instruct 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)
Llama 3 70B Instruct Abliterated LORA Parameters and Internals
| Model Type |
| |
| Additional Notes |
|
| LLM Name | Llama 3 70B Instruct Abliterated LORA |
| Repository 🤗 | https://huggingface.co/mlabonne/Llama-3-70B-Instruct-abliterated-LORA |
| Base Model(s) | |
| Model Size | 70b |
| Required VRAM | 1.7 GB |
| Updated | 2024-11-22 |
| Maintainer | mlabonne |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | AutoModel |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | lm_head|gate_proj|q_proj|k_proj|o_proj|v_proj|down_proj|up_proj |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
Best Alternatives to Llama 3 70B Instruct Abliterated LORA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeLlama 70B Instruct GGUF | 0K / 25.5 GB | 2965 | 56 |
| Meta Llama 3 70B Instruct GGUF | 0K / 26.4 GB | 285 | 3 |
| DAD Model V2 70B Q4 | 0K / 42.5 GB | 5 | 0 |
| Swallow 70B Instruct GGUF | 0K / 29.4 GB | 90 | 8 |
| Leo Hessianai 70B Chat GGUF | 0K / 29.3 GB | 197 | 1 |
| ...tablelm Instruct Beta 70B GGUF | 0K / 29.3 GB | 799 | 12 |
| Dolphin 2.2 70B GGUF | 0K / 29.3 GB | 436 | 18 |
| Llama 2 70B Orca 200K GGUF | 0K / 29.3 GB | 1195 | 22 |
| ...e Llama 2 70B Instruct V2 GGUF | 0K / 29.3 GB | 329 | 10 |
| Platypus2 70B Instruct GGUF | 0K / 29.3 GB | 192 | 11 |
Rank the Llama 3 70B Instruct 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? 38199 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110