THUDM/chatglm2-6b · Discussions

#80 opened 21 days ago by

zxyy123

Any support for adding system instructions similar as chatGPT?

#79 opened 25 days ago by

timpan

apply_query_key_layer_scaling 的用途是什么呢

#78 opened 28 days ago by

yywind

Update tokenizer_config.json

#77 opened about 2 months ago by

LeeSAIF

有ft加速版吗，很需要，万分感谢

#76 opened about 2 months ago by

chaochaoli

what is the multi_query_group_num in config.json?

#75 opened about 2 months ago by

lg920810

关于chatglm2-6b进行P-tuning v2出现效果不佳情况的一个记录或讨论

#74 opened about 2 months ago by

LittleGreen

如何在创建模型时就使用int4？

#73 opened about 2 months ago by

shamankk

分词器tokenizer错误，无法识别到eos字符

#72 opened about 2 months ago by

zheng-nlper

compatible with DirectML

#71 opened about 2 months ago by

davinwang

如何将本地文本文件制作成.bin的模型文件？

#70 opened about 2 months ago by

shantone

微调后推理报错 IndexError: piece id is out of range.

#69 opened about 2 months ago by

lyy0905

chatgml2_6b

#68 opened about 2 months ago by

dailywsx

fix modeling_chatglm.py error: `-` operator, with a bool tensor is not supported

#67 opened about 2 months ago by

shibing624

多卡微调，位置编码显示shape错误，单卡可正常运行

#66 opened about 2 months ago by

smiling-xu

add get_output_embeddings()

#65 opened about 2 months ago by

ranchlai

add get_output_embeddings()

#64 opened about 2 months ago by

ranchlai

prBr

#63 opened about 2 months ago by

JeoHw

🚩 Report

#62 opened about 2 months ago by

fangg2000

Create hh

#60 opened 2 months ago by

0xMonia

如何拿到输入句子的embedding

#59 opened 2 months ago by

GuiltyInori

尽情->敬请用尽情期待多少感觉有点怪?

#58 opened 2 months ago by

fj4444

about underscore character

#57 opened 2 months ago by

captainst

You may consider adding `ignore_mismatched_sizes=True` in the model `from_pretrained` method.

#56 opened 2 months ago by

EthanMiao

模型并行出错并给出修改方案

#54 opened 2 months ago by

yuanzhoulvpi

有无最大生成长度，突然停止生成

#53 opened 2 months ago by

Squidwargg

模型使用ptv2微调后其他能力下降该如何解决

#52 opened 2 months ago by

couldn

🚩 Report

#51 opened 2 months ago by

leyong

微调后模型预测一直为空，我是使用readme中的参数微调的，但是使用的基座模型是量化4版本，不知道是不是这个原因

4

#50 opened 2 months ago by

couldn

add set_input_embedding to support resize token embedding

#49 opened 2 months ago by

Yes365

Update README.md

#48 opened 2 months ago by

Arjun2001

Update README.md

#47 opened 2 months ago by

Arjun2001

请问，chatGLM-6b自动更新后就是chatGLM2-6b吗？

#46 opened 2 months ago by

lysen963

Openllm调用GLM

#45 opened 2 months ago by

cat13

有没有quantization_kernels.c和quantization_kernels_parallel.c文件下载

#43 opened 2 months ago by

haaaaaaaa1

本地加载失败？

#39 opened 3 months ago by

enozhu

建议forward函数参数增加full_attention_mask

#35 opened 3 months ago by

zkwhandan

为啥Model Database的Hosted inference API不能直接用哇

#34 opened 3 months ago by

chrisliang

GGML version please!

#33 opened 3 months ago by

Hoioi

BatchEncoding error

#32 opened 3 months ago by

thirdHand

when use oobabooga/ext-generation-webui load this mode ，the chat message was blank and the terminal reponse error：IndexError: list index out of range

#29 opened 3 months ago by

elven2023

Utilizing chatglm2-6b for Downstream Classification Tasks

#28 opened 3 months ago by

CeroShrijver

TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

4

#24 opened 3 months ago by

lizongran

unable to access 'https://Model Database.co/THUDM/chatglm2-6b/': Recv failure: Connection reset by peer

8

#22 opened 3 months ago by

RogerChen

tokenizer.bos_token_id is None

4

#20 opened 3 months ago by

yourui

ptuning微调报错'ChatGLMModel' object has no attribute 'prefix_encoder'