-
## Why
推薦・機械学習勉強会は、推薦や機械学習、その周辺技術を通じてサービスを改善することにモチベーションのある人達の集まりです。ニュースやブログから論文まで、気になったものについてお互い共有しましょう！
発信のため、ここは **public** にしてあります。外部からの参加をご希望の方は松村(https://twitter.com/yu__ya4) まで DM を送るか、Wa…
-
### System Info
Ubuntu 22.04
Python 3.12.3
### Who can help?
@Narsil @zucchini-nlp
### Information
- [ ] The official example scripts
- [X] My own modified scripts
### Tasks
- [ ] An official…
-
### System Info
1. Below are my dependencies version.
```
flash_attn==2.6.3
numpy==1.24.4
Pillow==10.4.0
Requests==2.32.3
transformers==4.44.2
accelerate==0.34.0
peft==0.12.0
datasets==2…
-
I have tried to install nemo_toolkit==2.0.0.rc0
but it shows error:
RuntimeError: causal_conv1d is only supported on CUDA 11.6 and above. Note: make sure nvcc has a supported version by running n…
-
### Frontend Version
1.4.7
### Expected Behavior
Interactive nodes from GLSL pack https://github.com/patriciogonzalezvivo/comfyui_glslnodes to work as intended (be interactive)
vec2 (pos)
vec3 (p…
-
- This issue focuses on the technical courses we take about LLM, we'll put the paper part in
https://github.com/xp1632/DFKI_working_log/issues/70
---
1. **ChainForge** https://chainforge.ai/ …
-
官方文档里的微调内容：如果想要对awq、gptq量化的模型进行qlora微调，你需要进行提前量化。例如可以对原始模型使用swift export进行量化。然后使用以下命令进行微调，你需要指定--quant_method来指定对应量化的方式：
CUDA_VISIBLE_DEVICES=0 swift sft \
--model_type qwen1half-7b-chat \
…
-
### 请提出你的问题
1、请问有没有比较好的思路？
2、如果权重文件已经转换为paddle的形式，对于paddlenlp模型库中不存在的大模型，我们是否可以使用快速验证？
…
-
I have been trying to play around with the QAT pipeline with LLM text generation. I have adopted the code from `examples/nlp/text-generation/quantize_causal_lm_model.py` and used gpt2-small for my mo…
-
@wxy-nlp I can not find pdb file [os.path.join('data-bin/scaffolding-pdbs/' + pdb + '_motif.pdb') ] when run scaffold_generate.py, Can you provide it？(https://github.com/microsoft/evodiff/tree/ma…