LLM EXPLORER 60,645 MODELS INDEXED

Dre Phi by empgces

By empgces · 7 downloads
HF Repo ↗ Copy URL

Dre Phi is an open-source language model by empgces. Features: LLM, VRAM: 7.6GB, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.13.

  4bit Base model:finetune:unsloth/ph... Base model:unsloth/phi-3-mini-...   Conversational   En   Endpoints compatible   Instruct   Lora   Mistral   Pytorch   Quantized   Region:us   Safetensors   Sft   Sharded   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/empgces/dre_phi 

Dre Phi Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, mistral, trl, sft
Additional Notes 
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameDre Phi
Repository 🤗https://huggingface.co/empgces/dre_phi 
Base Model(s)  ...hi 3 Mini 4K Instruct Bnb 4bit   unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Required VRAM7.6 GB
Updated2026-05-13
Maintainerempgces
Instruction-BasedYes
Model Files  0.1 GB   5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Quantization Type4bit
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesup_proj|v_proj|q_proj|gate_proj|down_proj|o_proj|k_proj
LoRA Alpha32
LoRA Dropout0
R Param32

Best Alternatives to Dre Phi

Best Alternatives
Context / RAM
Downloads
Likes
...emo Instruct 2407 EXL2 8bpw H80K / 12.6 GB77
Phi 3 Mini 4K CodeInstruct0K / 7.6 GB100
...3 Mini 4K Instruct Text To Sql0K / 7.6 GB120
Phi 3 Mini 4K Python0K / 7.6 GB6321
VLM2Vec LoRA0K / 0 GB9611
Pipi0K / 2.4 GB130
... Mini 4K Instruct Chinese Lora0K / 0 GB86
Falcon Camel Math Instruct0K / 0 GB21
Instruct Igel 0010K / 12.9 GB1347
Note: green Score (e.g. "73.2") means that the model is better than empgces/dre_phi.