-
Could someone add a thing that converts 8bit and 24bit bitmaps to 32 automatically
-
Why can't llama understand Chinese so much and can't reply directly in Chinese?
I tested Llama-2-7b-chat-hf again today.
Test using GPU platform: matpool.com
Memory usage:
Open 8BIT occupies 8…
-
I tried quantizing Mamba using HuggingFace/Quanto and ran into the problem of perplexity for `lambada_openai` blowing up (> 1e^37) at lower quantization levels, even though other tasks retained their …
-
Hi there!
Great work with medalpaca! I was trying to reproduce your scores on the USMLE eval sets for **medalpaca 7B** and **medalpaca 13B**. However, when I run the notebook shared in #40, I'm get…
-
如题，在使用games数据集 ，将sample设置为len(sequential_train) 的情况下 训练 + 使用训练后的lora获取predict 再通过evaluate计算dist排序 得到的ndcg以及RECALL水平均只有0.00的水平 无法达到论文中full的效果。是否还需要修改超参数或者进行其他操作呢。
![image](https://github.com/user-atta…
-
**Consistency training fails to converge**
When I use examples/research_projects/consistency_training/train_cm_ct_unconditional.py to train the consistency model, I try to follow the experimental par…
-
# flv 文件格式
## flv header
**9个字节：**
* 8bit: 'F'
* 8bit: 'L'
* 8bit: 'V'
* 8bit: version
* 5bit: type flags reserved
* 1bit: type flags audio
* 1bit: type flags reserved, must be 0
* 1bit: typ…
-
I'm on mlx-lm v0.19.1.
Running the following command with 4bit produced a bug where it would just generate the full 1000 max-tokens and just repeat the last two paragraphs over and over.
```bash…
-
Hello @nishad2m8
I am making a device project, I drew graphics in `SLS`.
The code is running on a device with a `360x360` display connected via `QSPI` bus.
The video shows slow operation.
https…
-
Hi, I'm trying to use fastchat-t5-3b-v1.0 on macOS following the instructions in the README.
```
Simply run the line below to start chatting. It will automatically download the weights from a Hugg…