jan-hq/LlamaCorn-1.1B-Chat
Full fine-tune vs TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T. Fine-tune: 100% of the weights changed, across 22 of 22 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 24/45, MLP 66/66, Attention 88/88
4 derivatives checked
- mradermacher/LlamaCorn-1.1B-Chat-i1-GGUF: Quantization
- mradermacher/LlamaCorn-1.1B-Chat-GGUF: Same weights, converted
- jan-hq/TinyJensen-1.1B-Chat: Full fine-tune
- jan-hq/TinyJensen-1.1B: Full fine-tune