LLM EXPLORER 62,155 MODELS INDEXED

Qwen3 Sft Feedback With Proof Repair Rl 125 Unmasked by formalmathatepfl

By formalmathatepfl · 31 downloads
HF Repo ↗ Copy URL

Qwen3 Sft Feedback With Proof Repair Rl 125 Unmasked is an open-source language model by formalmathatepfl. Features: 8.2b LLM, VRAM: 16.4GB, Context: 32K, LLM Explorer Score: 0.28.

  Qwen3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked 

Qwen3 Sft Feedback With Proof Repair Rl 125 Unmasked Parameters and Internals

LLM NameQwen3 Sft Feedback With Proof Repair Rl 125 Unmasked
Repository 🤗https://huggingface.co/formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked 
Model Size8.2b
Required VRAM16.4 GB
Updated2026-09-25
Maintainerformalmathatepfl
Model Typeqwen3
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.5 GB: 4-of-4
Model ArchitectureQwen3ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.57.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to Qwen3 Sft Feedback With Proof Repair Rl 125 Unmasked

Best Alternatives
Context / RAM
Downloads
Likes
...nical Understanding Model V2.1128K / 16.4 GB50
...en 3 Panda Agi 3.3 DPO 8epochs80K / 16.4 GB710
Intern S1 Mini Lm64K / 16.4 GB3070
Ice AI40K / 16.4 GB8575
KSTU T Lite 2.140K / 16.4 GB3850
IPAI1.040K / 6.4 GB1341
Diallm Qwen Sft Aus40K / 16.4 GB460
Diallm Qwen Sft Brit40K / 16.4 GB360
Diallm Qwen Sft Ind40K / 16.4 GB50
Diallm Qwen Sft All40K / 16.4 GB70
Note: green Score (e.g. "73.2") means that the model is better than formalmathatepfl/qwen3-sft-feedback-with-proof-repair-rl-125-unmasked.