Rename GLM-4.7-PRISM-IQ1_S-patched.gguf to GLM-4.7-PRISM-IQ1_S.gguf

Delete GLM-4.7-PRISM-IQ1_S.gguf

Upload fixed GGUF (tokenizer + MTP patches applied)

Add original GLM-4.7 chat_template

Fix: Set special=true for thinking tokens and add to additional_special_tokens

Fix: Set special=true for thinking tokens (151350, 151351)

Fix: Set num_nextn_predict_layers to 0 to fix MTP tensor issue

Upload README.md with huggingface_hub

Upload GLM-4.7-PRISM-IQ1_S.gguf with huggingface_hub

Upload GLM-4.7-PRISM-IQ1_S.gguf with huggingface_hub

Upload GLM-4.7-PRISM-IQ1_S.gguf with huggingface_hub

Upload GLM-4.7-PRISM-IQ1_S.gguf with huggingface_hub

Update README.md

Update README.md

Delete GLM-4.7-PRISM-imatrix.dat

Delete GLM-4.7-PRISM-IQ4_XS.gguf

Delete GLM-4.7-PRISM-IQ1_S.gguf

Upload README.md with huggingface_hub

Upload GLM-4.7-PRISM-IQ4_XS.gguf with huggingface_hub

Upload GLM-4.7-PRISM-IQ1_S.gguf with huggingface_hub

Upload GLM-4.7-PRISM-imatrix.dat with huggingface_hub

Delete GLM-4.7-PRISM-IQ4_XS.gguf with huggingface_hub

Delete GLM-4.7-PRISM-F16.gguf.part2 with huggingface_hub

Delete GLM-4.7-PRISM-F16.gguf.part1 with huggingface_hub

Update README.md

Upload F16 GGUF part 2/2 (258GB)

Upload F16 GGUF part 1/2 (400GB)

Upload IQ4_XS GGUF quantization (177GB)

Update README.md

Update abliteration_config.json

Update abliteration_config.json

Upload GLM-4.7 PRISM abliterated model (safetensors)

Update README.md

Add README.md

initial commit