issues
search
THUDM
/
AgentTuning
AgentTuning: Enabling Generalized Agent Abilities for LLMs
https://thudm.github.io/AgentTuning/
1.36k
stars
95
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Clarification on SFT required
#65
emrecanacikgoz
opened
2 days ago
0
Does the docker contain the training dataset?
#64
zhiyuanc2001
closed
1 month ago
0
About AgentInstruct dataset
#63
listentomi
opened
3 months ago
0
How do you select the prompt for AlfWorld?
#62
HCHCXY
opened
3 months ago
0
是否用TGI封装过的模型都可以进行测试？
#61
YinSonglin1997
opened
4 months ago
0
Can you open source the unfiltered dataset
#59
whi497
opened
4 months ago
0
训练数据中指令与模型行为不匹配
#58
haichao592
opened
6 months ago
0
本地模型
#57
lz2021211161
closed
7 months ago
0
请问哪里可以找到工作里对于数据库方面的训练数据
#56
Mucalinda2436
closed
8 months ago
1
魔塔上的 AgentInstruct 数据集的 conversation 都是空值
#55
XianglongTan
opened
8 months ago
0
weight decay确定是0.1吗？
#54
Fu-Dayuan
closed
8 months ago
1
貌似hotpotqa测试脚本跑不起来？
#53
Fu-Dayuan
opened
9 months ago
1
训练数据是如何采样的？
#52
Fu-Dayuan
closed
9 months ago
3
if it is possible to conduct RLHF from env
#51
SHITIANYU-hue
opened
9 months ago
1
Can you point to the ShareGPT filtered/cleaned data used?
#50
harshraj172
closed
9 months ago
1
Can I run AgentInstruct data on the AgentBench?
#49
harshraj172
opened
10 months ago
1
可以给个简单点的工具调用示例吗
#48
qq594495953
opened
10 months ago
1
期待用 Qwen72B 训练的模型。
#47
milomoon
closed
10 months ago
1
基于fastchat部署，推理异常
#46
ruifengma
opened
11 months ago
3
请问下agentlm-7b最少需要多少显存可以推理
#45
nicolasNi
closed
11 months ago
5
关于TRAJECTORY FILTERING问题
#44
QingChengLineOne
closed
11 months ago
3
Finetuning with Mistral or Yi?
#43
jFkd1
closed
11 months ago
1
除了用docker运行，还有其他方式可以运行AgentLM吗？
#42
caizhuoyue77
closed
11 months ago
6
通用数据如何筛选
#41
LuoKaiGSW
opened
12 months ago
7
Dataset details 中找不到reward的计算方式
#40
DryPilgrim
closed
12 months ago
5
AgentTuning 7b evaluate in HH， not expect as paper result
#39
Dhaizei
opened
12 months ago
13
关于dataset statics 和 download
#38
DryPilgrim
closed
12 months ago
3
关于数据集
#37
DryPilgrim
closed
12 months ago
0
Number of training steps
#36
Mayer123
closed
12 months ago
1
微调显存
#35
Reason-Wang
closed
12 months ago
1
agent tuning和toolbench的区别
#34
Connor-Shen
closed
12 months ago
1
Start TGI worker
#33
mayilin0714
closed
1 year ago
1
关于reward
#32
DryPilgrim
closed
12 months ago
2
requests.exceptions.MissingSchema: Invalid URL '127.0.0.123332/generate': No scheme supplied. Perhaps you meant https://127.0.0.123332/generate?
#31
mayilin0714
closed
1 year ago
1
请教reward分数的各种情况
#30
DryPilgrim
closed
1 year ago
1
Inference with `vllm`
#29
yc1999
closed
1 year ago
1
Updated Contributors Section
#28
mohitd404
opened
1 year ago
0
Adding Contributors Section in readme.md file.
#27
mohitd404
closed
11 months ago
0
Fix typos
#26
HKABIG
closed
1 year ago
1
Create CONTRIBUTING.md
#25
0Armaan025
opened
1 year ago
0
Add license
#24
dalvishruti14
closed
1 year ago
0
Updated README with Badges
#23
Killer2OP
closed
7 months ago
1
Create LICENSE
#22
Killer2OP
closed
7 months ago
1
Auto comment
#21
shraddha761
closed
1 year ago
1
Update README.md
#20
shraddha761
closed
1 year ago
1
Grammer mistake in readme
#19
shraddha761
closed
1 year ago
1
什么时候上魔塔社区
#18
QingChengLineOne
closed
1 year ago
1
论文中Table 2中的数字的含义和计算方式
#17
DryPilgrim
closed
1 year ago
2
论文中的问题
#16
QingChengLineOne
closed
1 year ago
1
Updated language of README.md file
#15
rohan37kumar
closed
1 year ago
0
Next