Adapter Base model:adapter:casual-auto... Base model:casual-autopsy/l3-u... Finetuned Lora Mergekit Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/kromcomp/L3-Umbral-Mind-r128-LoRA
L3 Umbral Mind R128 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 Umbral Mind R128 LoRA Parameters and Internals
| LLM Name | L3 Umbral Mind R128 LoRA |
| Repository 🤗 | https://huggingface.co/kromcomp/L3-Umbral-Mind-r128-LoRA |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.7 GB |
| Updated | 2025-05-16 |
| Maintainer | kromcomp |
| Model Files | |
| Model Architecture | Adapter |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | lm_head|up_proj|down_proj|gate_proj|k_proj|q_proj|v_proj|embed_tokens|o_proj |
| LoRA Alpha | 128 |
| LoRA Dropout | 0 |
| R Param | 128 |
Best Alternatives to L3 Umbral Mind R128 LoRA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 5 | 0 |
| ...B Lora Rag Citation Generation | 0K / 0 GB | 231 | 2 |
| Flippa V6 | 0K / 0 GB | 245 | 1 |
| Suavemente 8B R128 LORA | 0K / 2.8 GB | 9 | 0 |
| Llama 3 Korean 8B R V 0.1 | 0K / 0 GB | 5 | 0 |
| ...ning Llama 8B Rank 128 Adapter | 0K / 0.7 GB | 14 | 0 |
| ...a 8B Rank 128 INSTRUCT Adapter | 0K / 0.7 GB | 6 | 0 |
| ...a7 4262 4abb 97b1 1879f340d32e | 0K / 0.3 GB | 5 | 0 |
| ...lama 3 1 8B Instruct Orca ORPO | 0K / 0.1 GB | 406 | 2 |
| Llama 3.1 8B Smart Lora | 0K / 0.2 GB | 0 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than kromcomp/L3-Umbral-Mind-r128-LoRA .
Rank the L3 Umbral Mind R128 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? 47377 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227