mradermacher/Teuken-7B-instruct-research-v0.4-GGUF
Same weights, converted vs openGPT-X/Teuken-7B-instruct-research-v0.4. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128
Same weights, converted vs openGPT-X/Teuken-7B-instruct-research-v0.4. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128