fancyfeast/llama-joycaption-beta-one-hf-llava
Full fine-tune vs google/siglip2-so400m-patch14-384. Fine-tune: 93% of the weights changed, across 26 of 27 layers.
Tensors changed: Embeddings 3/3, Norms 104/112, MLP 104/112, Attention 208/220, other 0/1
12 derivatives checked
- mradermacher/llama-joycaption-beta-one-hf-llava-GGUF: Same weights, converted (fewer layers)
- mradermacher/llama-joycaption-beta-one-hf-llava-i1-GGUF: Quantization (fewer layers)
- NeoChen1024/llama-joycaption-beta-one-hf-llava-FP8-Dynamic: Quantization
- filvyb/llama-joycaption-beta-one-hf-llava-GGUF: Quantization (fewer layers)
- etenszyn/joycaption-beta-llava-gptq-4bit: Quantization
- n0kovo/llama-joycaption-beta-one-hf-llava-mlx-8Bit: Quantization
- enet45/llama-joycaption-beta-one-hf-llava-mlx-8Bit: Quantization
- H1coM/llama-joycaption-beta-one-hf-llava-Q4_K_M-GGUF: Quantization (fewer layers)
- Jasaga7818/llama-joycaption-beta-one-hf-llava-Q4_K_M-GGUF: Quantization (fewer layers)
- enet45/llama-joycaption-beta-one-hf-llava-mlx-4Bit: Quantization
- NeoChen1024/llama-joycaption-beta-one-hf-llava-GPTQ-4bit-sym-autoround: Quantization
- Malur1911/llama-joycaption-beta-one-hf-llava-Q4_K_M-GGUF: Quantization (fewer layers)
12 other repos hold byte-for-byte identical weight files.