ModelCloud
/

glm-4-9b-gptq-4bit

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Qubitium commited on Jun 7

Commit

a91cdc4

•

1 Parent(s): 30bc8e3

sync

Files changed (1) hide show

config.json +1 -0

config.json CHANGED Viewed

@@ -11,6 +11,7 @@
   "attention_softmax_in_fp32": true,
   "auto_map": {
     "AutoConfig": "configuration_chatglm.ChatGLMConfig",
     "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",

   "attention_softmax_in_fp32": true,
   "auto_map": {
     "AutoConfig": "configuration_chatglm.ChatGLMConfig",
+    "AutoGPTQForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
     "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",