prithivMLmods/Gliese-OCR-7B-Post1.0
Full fine-tune vs prithivMLmods/Camel-Doc-OCR-062825. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/2, Norms 61/122, MLP 280/280, Attention 324/324, lm_head 1/1
5 derivatives checked
- prithivMLmods/Gliese-OCR-7B-Post1.0-GGUF: Same weights, converted (fewer layers)
- mradermacher/Gliese-OCR-7B-Post1.0-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gliese-OCR-7B-Post1.0-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/Gliese-OCR-7B-Post2.0-final: Full fine-tune
- prithivMLmods/Delorme_1-OCR-7B-Post1.0: Full fine-tune