hcnote/SparkMuse-4B

Full fine-tune vs XHToken/Spark-X2.5-4B. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 1/1, Norms 5/73, MLP 108/108, Attention 108/108

3 derivatives checked

• mradermacher/SparkMuse-4B-i1-GGUF: Quantization
• mradermacher/SparkMuse-4B-GGUF: Same weights, converted
• yachen4ever/SparkMuse-4B-MLX-4bit: Quantization

On the Hub · Downloads on Model Pulse