OBLITERATUS/glm-4-9b-chat-hf-OBLITERATED

Partial fine-tune vs zai-org/glm-4-9b-chat-hf. Partial change: 44% of the weights changed (attention, lm_head, mlp), in 38 of 40 layers.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 38/80, Attention 190/280, lm_head 1/1

2 derivatives checked

• mradermacher/glm-4-9b-chat-hf-OBLITERATED-i1-GGUF: Quantization
• mradermacher/glm-4-9b-chat-hf-OBLITERATED-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse