GLM-iprompt
GLM-iprompt copied to clipboard
THUDM
Apply Iprompt on GLM with innovative new methods. Currently support Chinese QA, English QA and Chinese poem generation.
``` 9, 1701, 50238, 30995, 27545, 30001, 41489, 4474, 6883, 20045, 5147, 12213, 28588, 15418, 40812, 29381, 47872, 25410, 46473, 1863, 20409, 49002, 15781, 45629, 2637, 23811, 6320, 15177, 15984,...
I am not sure whether there are scripts running for smaller model as `GLM-2b` and `roberta-large`? `model_glm_roberta_large.sh` exists
Hi, I found that there are some wrong arguments. in inference_poems_iprompt.py, line 357 the code is: logits, *mem_kv = model( tokens[:, index:], position_ids[..., index: counter+1], attention_mask[..., index: counter+1, :counter+1], #...
您好！我尝试联系了邮箱 [email protected]，但暂时没有得到回应。感觉可能暂时没留意到邮箱，请问能在这里进行联系吗？