Resources

View closed (15)

Adding `safetensors` variant of this model

#38 opened 16 days ago by

SFconvertbot

Adding Evaluation Results

#36 opened about 1 year ago by

leaderboard-pr-bot

流式的什么时候出啊

#35 opened about 1 year ago by

dingxiang000

[AUTOMATED] Model Memory Requirements

#34 opened about 1 year ago by

model-sizer-bot

合并差值模型与原始llama模型后，模型生成乱码输出，请问base模型使用的是llama-13b还是llama-13b-chat？

#33 opened about 1 year ago by

jamestang2190

在使用模型对话输入的时候有乱码

#32 opened over 1 year ago by

jt12341

LLaMa这个模型权重有提供链接么？

#31 opened over 1 year ago by

LycheeX

能给出转换后的3个pytorch bin文件的sha256sum吗？

#30 opened over 1 year ago by

bash99

写文章时，输出的token数量没有达到max tokens时，输出的句子不完整。

#29 opened over 1 year ago by

lale314

中文对话，模型总吐英文

#28 opened over 1 year ago by

BestSongEver

--num-gpus 2 error

#26 opened over 1 year ago by

zjtzpanxb

Step 2 error:The size of tensor a (32000) must match the size of tensor b (39424) at non-singleton dimension 0

#25 opened over 1 year ago by

zjtzpanxb

体验执行compute报错

#21 opened over 1 year ago by

Kaibiao

体验报错

#20 opened over 1 year ago by

Kaibiao

为什么分词里没有pad_id?

#19 opened over 1 year ago by

cos0sin0

训练样例有吗？模型怎么微调呢

#12 opened over 1 year ago by

XiangHG

如何让模型能以stream方式输出?

#10 opened over 1 year ago by

zlei

返回的内容为啥要用<s></s>包起来，而且包含了输入

#9 opened over 1 year ago by

SuperMoonWalker

为什么权重文件比原版llama-13b还小？

#8 opened over 1 year ago by

yuemengrui

不支持流式输出？

#7 opened over 1 year ago by

betterme

llama.cpp format?

#5 opened over 1 year ago by

joorei

请问一下“效果评估 ”结果是使用哪种测评方式？

#4 opened over 1 year ago by

wandyli

Does this violate the LLaMA model license?

#3 opened over 1 year ago by

Cornmonster