prithivMLmods/Gliese-CUA-Tool-Call-8B
Full fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 2/2, Norms 117/122, MLP 280/280, Attention 324/324, lm_head 1/1
4 derivatives checked
- mradermacher/Gliese-CUA-Tool-Call-8B-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gliese-CUA-Tool-Call-8B-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/Gliese-CUA-Tool-Call-8B-GGUF: Same weights, converted (fewer layers)
- prithivMLmods/Gliese-CUA-Tool-Call-8B-Localization-GGUF: Full fine-tune (fewer layers)