rl-research/DR-Tulu-No-RLER-8B

Partial fine-tune vs rl-research/DR-Tulu-SFT-8B. Partial change: 85% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/1, Norms 73/145, MLP 108/108, Attention 144/144, lm_head 0/1

2 derivatives checked

• mradermacher/DR-Tulu-No-RLER-8B-i1-GGUF: Quantization
• mradermacher/DR-Tulu-No-RLER-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse