-
The title explains
https://huggingface.co/stabilityai/stablelm-zephyr-3b
-
### Your current environment
- vLLM CPU v0.5.3.post1
- Model: stabilityai/stablelm-3b-4e1t
- Dtype: FP16 or BF16
- AMD EPYC - 32 Core Processor
- RAM: 100 GB
### 🐛 Describe the bug
vLLM CPU v…
-
![gN5JmWWk jpg-small](https://github.com/PreternaturalAI/mlx-swift-chat/assets/5306992/7b5e0252-a528-4f3c-9ef3-67a68660def1)
-
### Your current environment
```text
Can't run since running on dockerized cluster. Using latest pip install for both vLLM and transformers + CUDA 12.1
```
### 🐛 Describe the bug
Running …
-
Hello, @YTianZHU . I read the Differential Transformer paper and found it very interesting.
Thank you so much for your work.
I was wondering how you visualized the attention scores in Figure 1:
![Ima…
-
-
### Question
Thanks for your excellent work! When I try to fine-tune with the LLM as StableLM1.6B, I am confused about the tokenizer inconsistency.
As the ./scripts/stablelm/finetune.sh requires, …
-
## 🐛 Bug Crash on iPads and iPhones with less than 4 gb of ram
A couple of weeks ago I could run mlc chat iOS app on my iPad with 3 gb of ram, but now I can't, It crashes when I try to run st…
-
大佬,如果我写个PR来加 [stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t),您会接受吗?🙇🏽
-
Is it possible to get embeddings from the model for my input text?
I.e. could I replace GTP3 calls from OpenAI with some python code and this model?