Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / THUDM/AgentTuning issues and pull requests

#64 - Does the docker contain the training dataset?

Issue - State: closed - Opened by zhiyuanc2001 2 months ago

#64 - Does the docker contain the training dataset?

Issue - State: closed - Opened by zhiyuanc2001 2 months ago

#63 - About AgentInstruct dataset

Issue - State: open - Opened by listentomi 3 months ago

#63 - About AgentInstruct dataset

Issue - State: open - Opened by listentomi 3 months ago

#62 - How do you select the prompt for AlfWorld?

Issue - State: open - Opened by HCHCXY 4 months ago

#62 - How do you select the prompt for AlfWorld?

Issue - State: open - Opened by HCHCXY 4 months ago

#59 - Can you open source the unfiltered dataset

Issue - State: open - Opened by whi497 5 months ago

#59 - Can you open source the unfiltered dataset

Issue - State: open - Opened by whi497 5 months ago

#58 - 训练数据中指令与模型行为不匹配

Issue - State: open - Opened by haichao592 7 months ago

#58 - 训练数据中指令与模型行为不匹配

Issue - State: open - Opened by haichao592 7 months ago

#57 - 本地模型

Issue - State: closed - Opened by lz2021211161 8 months ago

#57 - 本地模型

Issue - State: closed - Opened by lz2021211161 8 months ago

#56 - 请问哪里可以找到工作里对于数据库方面的训练数据

Issue - State: closed - Opened by Mucalinda2436 9 months ago - 1 comment

#54 - weight decay确定是0.1吗？

Issue - State: closed - Opened by Fu-Dayuan 10 months ago - 1 comment

#54 - weight decay确定是0.1吗？

Issue - State: closed - Opened by Fu-Dayuan 10 months ago - 1 comment

#53 - 貌似hotpotqa测试脚本跑不起来？

Issue - State: open - Opened by Fu-Dayuan 10 months ago - 1 comment

#53 - 貌似hotpotqa测试脚本跑不起来？

Issue - State: open - Opened by Fu-Dayuan 10 months ago - 1 comment

#52 - 训练数据是如何采样的？

Issue - State: closed - Opened by Fu-Dayuan 10 months ago - 3 comments

#52 - 训练数据是如何采样的？

Issue - State: closed - Opened by Fu-Dayuan 10 months ago - 3 comments

#51 - if it is possible to conduct RLHF from env

Issue - State: open - Opened by SHITIANYU-hue 10 months ago - 1 comment

#51 - if it is possible to conduct RLHF from env

Issue - State: open - Opened by SHITIANYU-hue 10 months ago - 1 comment

#50 - Can you point to the ShareGPT filtered/cleaned data used?

Issue - State: closed - Opened by harshraj172 10 months ago - 1 comment

#50 - Can you point to the ShareGPT filtered/cleaned data used?

Issue - State: closed - Opened by harshraj172 10 months ago - 1 comment

#49 - Can I run AgentInstruct data on the AgentBench?

Issue - State: open - Opened by harshraj172 11 months ago - 1 comment

#49 - Can I run AgentInstruct data on the AgentBench?

Issue - State: open - Opened by harshraj172 11 months ago - 1 comment

#48 - 可以给个简单点的工具调用示例吗

Issue - State: open - Opened by qq594495953 11 months ago - 1 comment

#48 - 可以给个简单点的工具调用示例吗

Issue - State: open - Opened by qq594495953 11 months ago - 1 comment

#47 - 期待用 Qwen72B 训练的模型。

Issue - State: closed - Opened by milomoon 11 months ago - 1 comment

#46 - 基于fastchat部署，推理异常

Issue - State: open - Opened by ruifengma 12 months ago - 3 comments

#46 - 基于fastchat部署，推理异常

Issue - State: open - Opened by ruifengma 12 months ago - 3 comments

#45 - 请问下agentlm-7b最少需要多少显存可以推理

Issue - State: closed - Opened by nicolasNi 12 months ago - 5 comments

#45 - 请问下agentlm-7b最少需要多少显存可以推理

Issue - State: closed - Opened by nicolasNi 12 months ago - 5 comments

#44 - 关于TRAJECTORY FILTERING问题

Issue - State: closed - Opened by QingChengLineOne 12 months ago - 3 comments

#44 - 关于TRAJECTORY FILTERING问题

Issue - State: closed - Opened by QingChengLineOne 12 months ago - 3 comments

#43 - Finetuning with Mistral or Yi?

Issue - State: closed - Opened by jFkd1 12 months ago - 1 comment

#43 - Finetuning with Mistral or Yi?

Issue - State: closed - Opened by jFkd1 12 months ago - 1 comment

#42 - 除了用docker运行，还有其他方式可以运行AgentLM吗？

Issue - State: closed - Opened by caizhuoyue77 about 1 year ago - 6 comments

#42 - 除了用docker运行，还有其他方式可以运行AgentLM吗？

Issue - State: closed - Opened by caizhuoyue77 about 1 year ago - 6 comments

#41 - 通用数据如何筛选

Issue - State: open - Opened by LuoKaiGSW about 1 year ago - 7 comments

#41 - 通用数据如何筛选

Issue - State: open - Opened by LuoKaiGSW about 1 year ago - 7 comments

#40 - Dataset details 中找不到reward的计算方式

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 5 comments

#40 - Dataset details 中找不到reward的计算方式

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 5 comments

#39 - AgentTuning 7b evaluate in HH， not expect as paper result

Issue - State: open - Opened by Dhaizei about 1 year ago - 13 comments

#39 - AgentTuning 7b evaluate in HH， not expect as paper result

Issue - State: open - Opened by Dhaizei about 1 year ago - 13 comments

#38 - 关于dataset statics 和 download

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 3 comments

#38 - 关于dataset statics 和 download

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 3 comments

#37 - 关于数据集

Issue - State: closed - Opened by DryPilgrim about 1 year ago

#37 - 关于数据集

Issue - State: closed - Opened by DryPilgrim about 1 year ago

#36 - Number of training steps

Issue - State: closed - Opened by Mayer123 about 1 year ago - 1 comment

#36 - Number of training steps

Issue - State: closed - Opened by Mayer123 about 1 year ago - 1 comment

#35 - 微调显存

Issue - State: closed - Opened by Reason-Wang about 1 year ago - 1 comment

#35 - 微调显存

Issue - State: closed - Opened by Reason-Wang about 1 year ago - 1 comment

#34 - agent tuning和toolbench的区别

Issue - State: closed - Opened by Connor-Shen about 1 year ago - 1 comment

#34 - agent tuning和toolbench的区别

Issue - State: closed - Opened by Connor-Shen about 1 year ago - 1 comment

#33 - Start TGI worker

Issue - State: closed - Opened by mayilin0714 about 1 year ago - 1 comment

#33 - Start TGI worker

Issue - State: closed - Opened by mayilin0714 about 1 year ago - 1 comment

#32 - 关于reward

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 2 comments

#32 - 关于reward

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 2 comments

#30 - 请教reward分数的各种情况

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 1 comment

#30 - 请教reward分数的各种情况

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 1 comment

#29 - Inference with `vllm`

Issue - State: closed - Opened by yc1999 about 1 year ago - 1 comment

#29 - Inference with `vllm`

Issue - State: closed - Opened by yc1999 about 1 year ago - 1 comment

#28 - Updated Contributors Section

Pull Request - State: open - Opened by mohitd404 about 1 year ago

#28 - Updated Contributors Section

Pull Request - State: open - Opened by mohitd404 about 1 year ago

#27 - Adding Contributors Section in readme.md file.

Issue - State: closed - Opened by mohitd404 about 1 year ago

#27 - Adding Contributors Section in readme.md file.

Issue - State: closed - Opened by mohitd404 about 1 year ago

#26 - Fix typos

Pull Request - State: closed - Opened by HKABIG about 1 year ago - 1 comment

#26 - Fix typos

Pull Request - State: closed - Opened by HKABIG about 1 year ago - 1 comment

#25 - Create CONTRIBUTING.md

Pull Request - State: open - Opened by 0Armaan025 about 1 year ago

#25 - Create CONTRIBUTING.md

Pull Request - State: open - Opened by 0Armaan025 about 1 year ago

#24 - Add license

Issue - State: closed - Opened by dalvishruti14 about 1 year ago

#24 - Add license

Issue - State: closed - Opened by dalvishruti14 about 1 year ago

#23 - Updated README with Badges

Pull Request - State: closed - Opened by Killer2OP about 1 year ago - 1 comment

#22 - Create LICENSE

Pull Request - State: closed - Opened by Killer2OP about 1 year ago - 1 comment

#22 - Create LICENSE

Pull Request - State: closed - Opened by Killer2OP about 1 year ago - 1 comment

#21 - Auto comment

Issue - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#21 - Auto comment

Issue - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#20 - Update README.md

Pull Request - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#20 - Update README.md

Pull Request - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#19 - Grammer mistake in readme

Issue - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#19 - Grammer mistake in readme

Issue - State: closed - Opened by shraddha761 about 1 year ago - 1 comment

#18 - 什么时候上魔塔社区

Issue - State: closed - Opened by QingChengLineOne about 1 year ago - 1 comment

#17 - 论文中Table 2中的数字的含义和计算方式

Issue - State: closed - Opened by DryPilgrim about 1 year ago - 2 comments

#16 - 论文中的问题

Issue - State: closed - Opened by QingChengLineOne about 1 year ago - 1 comment

#15 - Updated language of README.md file

Pull Request - State: closed - Opened by rohan37kumar about 1 year ago

#14 - added comments in agent.py for each function

Pull Request - State: closed - Opened by bhargavshirin about 1 year ago - 1 comment

#13 - Update README.md

Pull Request - State: closed - Opened by harshhere905 about 1 year ago

#12 - fine-tune code

Issue - State: closed - Opened by faaany about 1 year ago - 1 comment

#11 - Model Output Length

Issue - State: closed - Opened by HeimingX about 1 year ago - 2 comments

#10 - 论文中关于损失函数E的问题

Issue - State: closed - Opened by Dhaizei about 1 year ago - 7 comments

#9 - 微调

Issue - State: closed - Opened by Dhaizei about 1 year ago - 2 comments

#8 - 交互轨迹的Reward如何得到

Issue - State: closed - Opened by jiezhangGt about 1 year ago - 1 comment

#6 - fix: typos in AgentBench.old/src/tasks/card_game/judger/judger.py

Pull Request - State: closed - Opened by shresthasurav about 1 year ago