Duxiaoman-DI/XuanYuan

Issues

• xuanyuan3_70b_report文档

  #43 opened 2 months ago by Jasonzh8
  0

• 请问 XuanYuan3-70B-Chat 的 8bit/4bit 量化模型权重有计划提供吗

  #42 opened 3 months ago by LuneZ99
  0

• Llama3-XuanYuan3-70B-Chat 评测效果

  #41 opened 3 months ago by lllfx
  0

• 奖励模型的margin计算

  #40 opened 3 months ago by Jsjgjhg
  0

• 二维码过期

  #39 opened 3 months ago by Jsjgjhg
  0

• 二维码过期了。。。

  #38 opened 4 months ago by lty365
  1

• 关于混合微调的数据格式

  #37 opened 4 months ago by zyzyyy123
  1

• XuanYuan-6B-Chat-4bit输出乱码怎么办？

  #35 opened 5 months ago by hujunyi96
  0

• 微信二维码已经过期

  #34 opened 6 months ago by janglichao
  0

• 请问训练轩辕的千亿大模型需要多少GPU资源？

  #4 opened a year ago by tangsipeng
  4

• 6B-chat在A100上推理

  #33 opened 6 months ago by sunyclj
  1

• modelscope下载模型，调用时报错OSError: Error no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack

  #29 opened 9 months ago by huangizi
  4

• HuggingFace下载XuanYuan-6B-Chat-4bit模型，执行示例代码报错：OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory model/XuanYuan-6B-Chat-4bit.

  #32 opened 7 months ago by zhangxume
  1

• 请问下微调数据生成的self-qa技术开源了吗

  #24 opened 9 months ago by evyy1234
  1

• 环境配置一直不成功？可以给一个详细的说明吗

  #31 opened 7 months ago by Daniel-bupt
  0

• 13B chat的基座模型是什么？

  #30 opened 8 months ago by bruceguo123
  0

• 怎么实现流式输出

  #28 opened 9 months ago by yuanboao
  0

• 可否提供一个gradio的运行demo？

  #27 opened 9 months ago by GordonDongZHAO
  1

• 在FinanceIQ上XUANYUAN-13B指标比XUANYUAN2-70B指标高不少

  #26 opened 9 months ago by Line290
  0

• 强化学习阶段训练数据量

  #25 opened 9 months ago by jdcmj
  0

• xuanyuan6B-chat 在3090推理很慢

  #23 opened 9 months ago by mosthandsomeman
  0

• vllm 推理

  #22 opened 9 months ago by liuainlp
  0

• 支持长文本输入吗？

  #21 opened 10 months ago by Go4miii
  3

• 你好，开源60G高质量中文金融数据有国内下载地址吗？

  #20 opened 10 months ago by AnYingLieShouTuT
  4

• When will Ollama be supported

  #19 opened 10 months ago by dessun888
  1

• 国内已经不能上HuggingFace，请提供一个国内的模型下载地址。

  #17 opened a year ago by auendx
  1

• 13B模型训练数据量级

  #18 opened a year ago by echo-valor
  0

• 增量预训练阶段的配置

  #16 opened a year ago by tzt101
  0

• 金融数据集

  #15 opened a year ago by bpwl0121
  4

• 轩辕增量预训练分阶段数据集疑问

  #14 opened a year ago by echo-valor
  1

• 最低 CUDA 版本要求

  #8 opened a year ago by LuneZ99
  1

• 指令数据集开源

  #11 opened a year ago by rattlesnakey
  1

• vllm暂时不支持量化模型

  #10 opened a year ago by Alsac
  1

• 如何stream方式输出？

  #12 opened a year ago by tutu329
  1

• 如何用GPT-4修改题目的格式

  #13 opened a year ago by xjwhy
  0

• 金融评测缺少LLaMA-2-70B的对比

  #9 opened a year ago by young-chao
  1

• 请问可以提供更为完整的调用代码吗？

  #7 opened a year ago by liuyukid
  1

• 提示模板的例子？

  #3 opened a year ago by bittteerr
  1

• 请问后续会有13B或者7B、6B版本的量化版本吗？

  #1 opened a year ago by Pythonpa
  1

• 国内有镜像吗？

  #2 opened a year ago by JoelSeniorLiang
  1

• 群链接已经失效了，可以再更新下群吗

  #6 opened a year ago by echo-valor
  1