LLM EXPLORER 59,420 MODELS INDEXED

DeepSeek R1 14B Finetuned by mathdong01

By mathdong01 · 9 downloads
HF Repo ↗ Copy URL

DeepSeek R1 14B Finetuned is an open-source language model by mathdong01. Features: 14b LLM, VRAM: 29.7GB, License: apache-2.0, Fine-Tuned, LLM Explorer Score: 0.16.

Base model:finetune:unsloth/de... Base model:unsloth/deepseek-r1...   Conversational   En   Endpoints compatible   Finetuned   Lora   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/mathdong01/DeepSeek-R1-14B-Finetuned 

DeepSeek R1 14B Finetuned Parameters and Internals

LLM NameDeepSeek R1 14B Finetuned
Repository 🤗https://huggingface.co/mathdong01/DeepSeek-R1-14B-Finetuned 
Base Model(s)  DeepSeek R1 Distill Qwen 14B   unsloth/DeepSeek-R1-Distill-Qwen-14B
Model Size14b
Required VRAM29.7 GB
Updated2026-07-02
Maintainermathdong01
Model Files  0.3 GB   5.0 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   4.7 GB: 6-of-6
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Model Max Length131072
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|vision_pad|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|o_proj|q_proj|k_proj|gate_proj|up_proj|down_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to DeepSeek R1 14B Finetuned

Best Alternatives
Context / RAM
Downloads
Likes
...Research Preview 14B Full Book256K / 27.3 GB2521
MING MoE 14B0K / 0.1 GB200
Phi3 14B Unsloth Sft Quip 3bit0K / 0.1 GB110
Phi3 14B Unsloth Sft Quip 2bit0K / 0.1 GB50
ReWiz Qwen 2.5 14B0K / 29.7 GB1725
Note: green Score (e.g. "73.2") means that the model is better than mathdong01/DeepSeek-R1-14B-Finetuned.