mradermacher/Qwen-1.8B-none_DepressionDetection_v2-GGUF

Same weights, converted vs Moriacrafter/Qwen-1.8B-none_DepressionDetection_v2. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: lm_head 0/1, Attention 0/72, Norms 0/49, MLP 0/72, Embeddings 0/1

On the Hub · Downloads on Model Pulse