Base model:abacusai/llama-3-sm... Base model:finetune:abacusai/l... Endpoints compatible Lora Mergekit Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/kromcomp/L3-Smaug-r64-LoRA
L3 Smaug R64 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)
L3 Smaug R64 LoRA Parameters and Internals
| LLM Name | L3 Smaug R64 LoRA |
| Repository 🤗 | https://huggingface.co/kromcomp/L3-Smaug-r64-LoRA |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.4 GB |
| Updated | 2025-02-23 |
| Maintainer | kromcomp |
| Model Files | |
| Model Architecture | AutoModel |
| Is Biased | none |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|up_proj|o_proj|lm_head|down_proj|gate_proj|k_proj|v_proj|embed_tokens |
| LoRA Alpha | 64 |
| LoRA Dropout | 0 |
| R Param | 64 |
Best Alternatives to L3 Smaug R64 LoRA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama 3 8B Chat Doctor | 8K / 2.3 GB | 11 | 0 |
| BAEZEL 8B R128 LORA | 0K / 0.7 GB | 0 | 1 |
| ASPIRE 8B R128 LORA | 0K / 0.7 GB | 0 | 1 |
| L3.1 Aura R32 LoRA | 0K / 0.2 GB | 0 | 1 |
| L3.1 Epos R128 LoRA | 0K / 0.7 GB | 0 | 1 |
| Abliteration OVA 8B R128 LORA | 0K / 0.7 GB | 0 | 1 |
| Everything COT 8B R128 LoRA | 0K / 1.5 GB | 0 | 1 |
| OpenBioLLM 8B R64 LoRA | 0K / 0.4 GB | 0 | 1 |
| L3 Kudzu R32 LoRA | 0K / 0.2 GB | 0 | 1 |
| L3.1 Baldur R64 LoRA | 0K / 0.4 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kromcomp/L3-Smaug-r64-LoRA .
Rank the L3 Smaug R64 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? 43515 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227