LLM EXPLORER 59,420 MODELS INDEXED

Minerva 7B by Triangle104

By Triangle104 · 9 downloads
HF Repo ↗ Copy URL

Minerva 7B is an open-source language model by Triangle104. Features: 7b LLM, VRAM: 15.2GB, Context: 32K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.24.

  Merged Model   Arxiv:2306.01708 Base model:eva-unit-01/eva-qwe... Base model:huihui-ai/qwen2.5-7...   Base model:spestly/athena-1-7b   Conversational   Endpoints compatible   Instruct   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Triangle104/Minerva-7b 

Minerva 7B Parameters and Internals

LLM NameMinerva 7B
Repository 🤗https://huggingface.co/Triangle104/Minerva-7b 
Base Model(s)  EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1   Athena 1 7B   huihui-ai/Qwen2.5-7B-Instruct-abliterated   EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1   Spestly/Athena-1-7B   huihui-ai/Qwen2.5-7B-Instruct-abliterated
Merged ModelYes
Model Size7b
Required VRAM15.2 GB
Updated2026-03-06
MaintainerTriangle104
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.46.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|PAD_TOKEN|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Minerva 7B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M986K / 15.4 GB52534373
Hush Qwen2.5 7B RP V1.4 1M986K / 15.2 GB102
Qwen2.5 7B RRP 1M986K / 15.2 GB56
Qwen2.5 7B CelestialHarmony 1M986K / 14.8 GB87
Q2.5 Instruct 1M Harmony986K / 15.2 GB42
Impish QWEN 7B 1M986K / 15.2 GB46
COCO 7B Instruct 1M986K / 15.2 GB94
Apollo 7B986K / 15.2 GB80
Graph R1 7B986K / 15.3 GB73
Qwen2.5 7B Sky R1 Mini986K / 15.2 GB60
Note: green Score (e.g. "73.2") means that the model is better than Triangle104/Minerva-7b.