Untied copy of PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT. Same weights; lm_head.weight is stored as a copy of the input embedding and tie_word_embeddings is false, so trainers that don't support tied LM heads (e.g. prime-rl) can load it. Made with tools/untie_word_embeddings.py from prime-rl.

Qwen3-0.6B-Reverse-Text-SFT

A SFT fine-tune of PrimeIntellect/Qwen3-0.6B. Details here.

Downloads last month: -

Safetensors

Model size

0.8B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT-untied

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

PrimeIntellect/Qwen3-0.6B

Finetuned

(3)

this model

PrimeIntellect
/

Qwen3-0.6B-Reverse-Text-SFT-untied

Qwen3-0.6B-Reverse-Text-SFT

Model tree for PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT-untied

Dataset used to train PrimeIntellect/Qwen3-0.6B-Reverse-Text-SFT-untied