LLM EXPLORER 59,420 MODELS INDEXED

Kurtis SmolLM2 135M Instruct DPO by ethicalabs

By ethicalabs · 21 downloads
HF Repo ↗ Copy URL

Kurtis SmolLM2 135M Instruct DPO is an open-source language model by ethicalabs. Features: 135m LLM, VRAM: 0.5GB, Context: 8K, License: mit, Instruction-Based, LLM Explorer Score: 0.17.

Base model:ethicalabs/kurtis-s... Base model:finetune:ethicalabs...   Conversational Dataset:mrs83/kurtis mental he...   En   Endpoints compatible   Instruct   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO 

Kurtis SmolLM2 135M Instruct DPO Parameters and Internals

LLM NameKurtis SmolLM2 135M Instruct DPO
Repository 🤗https://huggingface.co/ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO 
Base Model(s)  Kurtis SmolLM2 135M Instruct   ethicalabs/Kurtis-SmolLM2-135M-Instruct
Model Size135m
Required VRAM0.5 GB
Updated2026-07-14
Maintainerethicalabs
Model Typellama
Instruction-BasedYes
Model Files  0.5 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length8192
Model Max Length8192
Transformers Version4.46.2
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to Kurtis SmolLM2 135M Instruct DPO

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 135M Instruct8K / 0.3 GB1857297388
SmolLM2 135M Reasoning 5K8K / 0.3 GB2763
... Subtitle Postprocessor Merged8K / 0.5 GB161
SmolLM2 135M Instruction Tuned8K / 0.3 GB100
SmolLM2 Rethink 135M8K / 0.5 GB62
SmolLM2 135M Instruct8K / 0.3 GB48873
SmolLM2 135M Instruct Ita8K / 0.1 GB240
...molLM2 135M Instruct Reasoning8K / 0.3 GB70
...wre324 R1 SmolLM2 135M Distill8K / 0.5 GB80
Kurtis SmolLM2 135M Instruct8K / 0.5 GB200
Note: green Score (e.g. "73.2") means that the model is better than ethicalabs/Kurtis-SmolLM2-135M-Instruct-DPO.