8-bit Autotrain compatible Base model:neversleep/nethena-... Base model:quantized:neverslee... Bitsandbytes Endpoints compatible Generated from trainer Llama Lora Region:us
Model Card on HF 🤗: https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA
Nethena 20B Glue 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)
Nethena 20B Glue LORA Parameters and Internals
| LLM Name | Nethena 20B Glue LORA |
| Repository 🤗 | https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA |
| Base Model(s) | |
| Model Size | 20b |
| Required VRAM | 3.1 GB |
| Updated | 2025-08-29 |
| Maintainer | athirdpath |
| Model Files | |
| Model Architecture | AutoModelForCausalLM |
| License | cc-by-nc-4.0 |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | [PAD] |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|k_proj|v_proj|o_proj|down_proj|up_proj|gate_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.05 |
| R Param | 128 |
Best Alternatives to Nethena 20B Glue LORA
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MedGPT OSS 20B | 0K / 41.6 GB | 8 | 0 |
| ...5e 4 Imdb Peft Adapter Removed | 0K / 41.2 GB | 2 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than athirdpath/Nethena-20b-Glue-LORA .
Rank the Nethena 20B Glue 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? 50995 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124