-
minicpm-v 能微调做图像分类任务吗？怎样实现？
-
Note that the models run on android are quantized to 4-bit and may lose some performance. The non-quantized models can be found [here](https://github.com/OpenBMB/miniCPM).
我想问下4-bit量化的模型在哪里可以找到呢？想知…
-
Hi, team.
I fine tuned with 15 pairs of one document type. (12 pairs as train, 3 as test)
After 500 epoches, both of training and eval_loss are nearly zero like following.
>
{'loss': 0.0, …
-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing ans…
-
-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing ans…
-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing ans…
-
I'd like to ask how much gpu memory is needed for this model inference and training
-
请问：在cli上运行时，如何使用自定义的数据集；
例如：微调MiniCPM-V时候，找不到对应的sft.sh，只找到了minicpm_2b_sft_chat和minicpm_moe_8x2b；然而利用cli：
**# Experimental environment: A10, 3090, V100, ...
**# 10GB GPU memory**
CUDA_VISIBLE_DEVIC…
-
probably i'm doing something wrong but here it is on Kali linux:
/minicpmv-cli -m ggml-model-Q4_K_M.gguf --mmproj mmproj-model-f16.gguf -c 4096 --temp 0.7 --top-p 0.8 --top-k 100 --repeat-penalty 1…