LLM EXPLORER 59,420 MODELS INDEXED

Gemma 7B Lora Distilabel Intel Orca DPO Pairs by glenn2

By glenn2 · 5 downloads

Gemma 7B Lora Distilabel Intel Orca DPO Pairs is an open-source language model by glenn2. Features: 2b LLM, License: mit, LLM Explorer Score: 0.14, Arc: 49.2, HellaSwag: 71.8, MMLU: 41.5, GSM8K: 17.3.

  Adapter Base model:adapter:google/gemm...   Base model:google/gemma-2b   Dpo   Finetuned   Generated from trainer   Lora   Peft   Region:us   Safetensors   Trl

Gemma 7B Lora Distilabel Intel Orca DPO Pairs Parameters and Internals

LLM NameGemma 7B Lora Distilabel Intel Orca DPO Pairs
Repository πŸ€—https://huggingface.co/glenn2/gemma-7b-lora-distilabel-intel-orca-dpo-pairs 
Base Model(s)  Gemma 2B   google/gemma-2b
Model Size2b
Required VRAM0 GB
Updated2026-05-27
Maintainerglenn2
Model Files  0.0 GB   0.0 GB
Model ArchitectureAdapter
Licensemit
Is Biasednone
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|q_proj|up_proj|o_proj|v_proj|down_proj|k_proj
LoRA Alpha8
LoRA Dropout0
R Param8

Best Alternatives to Gemma 7B Lora Distilabel Intel Orca DPO Pairs

Best Alternatives
Context / RAM
Downloads
Likes
Finetuned Gemma38K / 5.1 GB50
Kokolok 2.0 Vision0K / 0 GB381
Gemma 2 2B It Dolly 15K0K / 0.1 GB50
Openhermes 2B Gemma Sft Qlora0K / 0 GB70
Phi Gemma Nlaf V10K / 0.1 GB50
Gemma Nlaf V10K / 0 GB80
Phi Gemma Nlaf V00K / 0.1 GB50
Gemma 2B Nlaf V00K / 0 GB50
Gemma 2B It Nlai P10K / 0 GB60
Zephyr 2B Gemma Sft Qlora0K / 0 GB110
Note: green Score (e.g. "73.2") means that the model is better than glenn2/gemma-7b-lora-distilabel-intel-orca-dpo-pairs.