LLM EXPLORER 60,645 MODELS INDEXED

LORA DeepHermes R1 Reasoning Llama 8B Rank 128 Adapter by DavidAU

By DavidAU · 6 downloads
HF Repo ↗ Copy URL

LORA DeepHermes R1 Reasoning Llama 8B Rank 128 Adapter is an open-source language model by DavidAU. Features: 8b LLM, VRAM: 0.7GB, License: apache-2.0, LLM Explorer Score: 0.17.

  128k context   Adapter Base model:adapter:nousresearc... Base model:nousresearch/deephe...   Brainstorming   Deepseek   En   Finetuned   General usage   Llama 3 lora   Llama 3.1 lora   Lora   Lora adapter   Mergekit   Peft   Problem solving   Reasoning   Region:us   Safetensors   Solve riddles   Thinking
Model Card on HF 🤗: https://huggingface.co/DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-128-adapter 

LORA DeepHermes R1 Reasoning Llama 8B Rank 128 Adapter Parameters and Internals

LLM NameLORA DeepHermes R1 Reasoning Llama 8B Rank 128 Adapter
Repository 🤗https://huggingface.co/DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-128-adapter 
Base Model(s)  ...eepHermes 3 Llama 3 8B Preview   NousResearch/DeepHermes-3-Llama-3-8B-Preview
Model Size8b
Required VRAM0.7 GB
Updated2025-10-31
MaintainerDavidAU
Model Files  0.7 GB
Supported Languagesen
Model ArchitectureAdapter
Licenseapache-2.0
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Moduleslm_head|down_proj|up_proj|q_proj|v_proj|embed_tokens|k_proj|o_proj|gate_proj
LoRA Alpha128
LoRA Dropout0
R Param128

Best Alternatives to LORA DeepHermes R1 Reasoning Llama 8B Rank 128 Adapter

Best Alternatives
Context / RAM
Downloads
Likes
... 3 8B Instruct Bvr Finetune V38K / 16.1 GB70
...Max H3 Prompt Rewriter LoRA 8B0K / 2.8 GB13726
Triage Qwen3 8B Lora0K / 0.2 GB131
...alized Harm V1 Qwen3 8B Seed430K / 0.2 GB101
Fovis0K / 0.1 GB391
Welles0K / 0 GB91
Drv Corrected Opd Qwen3 Vl 8B0K / 0.3 GB61
...eta Llama 3 8B Instruct Amazon0K / 0 GB60
Victor Triage Lora Llama3.1 8B0K / 0.1 GB70
Flippa V60K / 0 GB81
Note: green Score (e.g. "73.2") means that the model is better than DavidAU/LORA-DeepHermes-R1-Reasoning-Llama-8B-rank-128-adapter.