sarimahsan101/TinyLlama-1.1B-Alpaca-QLoRA
LoRA-style vs TinyLlama/TinyLlama-1.1B-Chat-v1.0. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of q_proj, v_proj changed, in 22 of 22 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, MLP 0/66, Attention 44/88
2 derivatives checked
- mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-i1-GGUF: Quantization
- mradermacher/TinyLlama-1.1B-Alpaca-QLoRA-GGUF: Same weights, converted