LLM EXPLORER 59,420 MODELS INDEXED

Qwen 0.5 IRPO 3e 6 2ep 1alp 0lam by JayHyeon

By JayHyeon · 5 downloads
HF Repo ↗ Copy URL

Qwen 0.5 IRPO 3e 6 2ep 1alp 0lam is an open-source language model by JayHyeon. Features: 494m LLM, VRAM: 2GB, Context: 32K, LLM Explorer Score: 0.18.

  Arxiv:1910.09700   Endpoints compatible   Feature-extraction   Qwen2   Region:us   Safetensors   Text-embeddings-inference
Model Card on HF 🤗: https://huggingface.co/JayHyeon/Qwen_0.5-IRPO_3e-6-2ep_1alp_0lam 

Qwen 0.5 IRPO 3e 6 2ep 1alp 0lam Parameters and Internals

LLM NameQwen 0.5 IRPO 3e 6 2ep 1alp 0lam
Repository 🤗https://huggingface.co/JayHyeon/Qwen_0.5-IRPO_3e-6-2ep_1alp_0lam 
Model Size494m
Required VRAM2 GB
Updated2026-08-08
MaintainerJayHyeon
Model Typeqwen2
Model Files  2.0 GB
Model ArchitectureQwen2Model
Context Length32768
Model Max Length32768
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen 0.5 IRPO 3e 6 2ep 1alp 0lam

Best Alternatives
Context / RAM
Downloads
Likes
...en 0.5 IRPO 3e 7 1ep 1alp 0lam32K / 2 GB70
...wen 0.5 DPO 3e 7 1ep 0alp 0lam32K / 2 GB70
...wen 0.5 DPO 3e 7 2ep 0alp 0lam32K / 2 GB50
...en 0.5 IRPO 5e 7 1ep 1alp 0lam32K / 2 GB60
...wen 0.5 DPO 5e 7 2ep 0alp 0lam32K / 2 GB50
...wen 0.5 DPO 3e 6 2ep 0alp 0lam32K / 2 GB70
....5 MDPO 0.5 3e 7 2ep 0alp 0lam32K / 2 GB70
...en 0.5 DPOP 3e 7 2ep 0alp 5lam32K / 2 GB140
...en 0.5 IRPO 5e 7 2ep 1alp 0lam32K / 2 GB70
...en 0.5 DPOP 3e 7 1ep 0alp 5lam32K / 2 GB50
Note: green Score (e.g. "73.2") means that the model is better than JayHyeon/Qwen_0.5-IRPO_3e-6-2ep_1alp_0lam.