7 1 month ago

Experimental version of glm-4.7-flash

tools thinking
ollama run pdevine/glm-4.7-flash:int8

Details

1 month ago

0239b4ae15ab · 34GB ·

{ "architectures": [ "Glm4MoeLiteForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0,
{ "_from_model_config": true, "eos_token_id": [ 154820, 154827, 154829 ], "pad_token_id": 154820, "t
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 154820, "content"
{ "added_tokens_decoder": { "154820": { "content": "<|endoftext|>", "single_word": false, "lstrip":
{{ .Prompt }}
632 tensors

Readme

No readme