LLM EXPLORER 59,420 MODELS INDEXED

GRAG MERGED PHI 3.5 MINI 4B ORPOxSFT HESSIAN AI by MR-Eder

By MR-Eder · 15 downloads
HF Repo ↗ Copy URL

GRAG MERGED PHI 3.5 MINI 4B ORPOxSFT HESSIAN AI is an open-source language model by MR-Eder. Features: 4b LLM, VRAM: 7.7GB, Context: 128K, Merged, LLM Explorer Score: 0.16.

  Merged Model   Autotrain compatible Base model:avemio/grag-phi-3.5... Base model:avemio/grag-phi-3.5...   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MR-Eder/GRAG-MERGED-PHI-3.5-MINI-4B-ORPOxSFT-HESSIAN-AI 

GRAG MERGED PHI 3.5 MINI 4B ORPOxSFT HESSIAN AI Parameters and Internals

LLM NameGRAG MERGED PHI 3.5 MINI 4B ORPOxSFT HESSIAN AI
Repository 🤗https://huggingface.co/MR-Eder/GRAG-MERGED-PHI-3.5-MINI-4B-ORPOxSFT-HESSIAN-AI 
Base Model(s)  avemio/GRAG-PHI-3.5-MINI-4B-ORPO-HESSIAN-AI   avemio/GRAG-PHI-3.5-MINI-4B-SFT-HESSIAN-AI   avemio/GRAG-PHI-3.5-MINI-4B-ORPO-HESSIAN-AI   avemio/GRAG-PHI-3.5-MINI-4B-SFT-HESSIAN-AI
Merged ModelYes
Model Size4b
Required VRAM7.7 GB
Updated2024-12-28
MaintainerMR-Eder
Model Typellama
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.46.2
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to GRAG MERGED PHI 3.5 MINI 4B ORPOxSFT HESSIAN AI

Best Alternatives
Context / RAM
Downloads
Likes
4Bcpt256K / 8.8 GB50
HoldMy4BKTO256K / 8.8 GB50
Xgen Small 4B Instruct R256K / 17.7 GB544
Xgen Small 4B Base R256K / 17.7 GB303
SJT 4B146K / 7.6 GB70
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB3940116
Nemotron W 4b MagLight 0.1128K / 9.2 GB93
Loxa 4B128K / 16 GB80
Nemotron W 4b Halo 0.1128K / 9.2 GB223
Aura 4B128K / 9 GB2414
Note: green Score (e.g. "73.2") means that the model is better than MR-Eder/GRAG-MERGED-PHI-3.5-MINI-4B-ORPOxSFT-HESSIAN-AI.