Openhermes 2B Gemma Sft Qlora is an open-source language model by Ritvik19. Features: 2b LLM, License: gemma, HF Score: 43.9, LLM Explorer Score: 0.17, Arc: 44.4, HellaSwag: 71.6, MMLU: 39.6, TruthfulQA: 40.1, WinoGrande: 67.6.
Adapter Alignment-handbook Base model:adapter:google/gemm... Base model:google/gemma-2b Dataset:ritvik19/open-hermes-2... Finetuned Gemma Generated from trainer Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Ritvik19/openhermes-2b-gemma-sft-qlora
Openhermes 2B Gemma Sft Qlora Benchmarks
ARC: 44.37 vs 96.7 (so35)-54.1%
HellaSwag: 71.58 vs 95.3 (gpt4)-24.9%
MMLU: 39.64 vs 88.3 (so35)-55.1%
TruthfulQA: 40.09 vs 59 (gpt4)-32.1%
WinoGrande: 67.56 vs 87.5 (gpt4)-22.8%
LLME Score: 0.16883
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)
Openhermes 2B Gemma Sft Qlora Parameters and Internals
| LLM Name | Openhermes 2B Gemma Sft Qlora |
| Repository 🤗 | https://huggingface.co/Ritvik19/openhermes-2b-gemma-sft-qlora |
| Base Model(s) | |
| Model Size | 2b |
| Required VRAM | 0 GB |
| Updated | 2026-04-08 |
| Maintainer | Ritvik19 |
| Model Files | |
| Model Architecture | Adapter |
| License | gemma |
| Model Max Length | 2048 |
| Is Biased | none |
| Tokenizer Class | GemmaTokenizer |
| Padding Token | <pad> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|up_proj|k_proj|v_proj|q_proj|gate_proj|o_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to Openhermes 2B Gemma Sft Qlora
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Finetuned Gemma3 | 8K / 5.1 GB | 8 | 0 |
| Gemma 2 2B It Dolly 15K | 0K / 0.1 GB | 5 | 0 |
| Phi Gemma Nlaf V1 | 0K / 0.1 GB | 6 | 0 |
| Gemma Nlaf V1 | 0K / 0 GB | 5 | 0 |
| Phi Gemma Nlaf V0 | 0K / 0.1 GB | 5 | 0 |
| Gemma 2B Nlaf V0 | 0K / 0 GB | 5 | 0 |
| Gemma 2B It Nlai P1 | 0K / 0 GB | 9 | 0 |
| Zephyr 2B Gemma Sft Qlora | 0K / 0 GB | 10 | 0 |
| Gemma 2 2B Norobots | 0K / 0.1 GB | 7 | 0 |
| ...istilabel Intel Orca DPO Pairs | 0K / 0 GB | 10 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than Ritvik19/openhermes-2b-gemma-sft-qlora .
Rank the Openhermes 2B Gemma Sft Qlora 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? 52721 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a