-
修改SGLang 框架对 BAAI/bge-reranker-v2-gemma 模型适配,并进行推理加速
## 测试配置
- **硬件**: NVIDIA A10 GPU
- **序列长度**: 512
## 性能结果
下表对比了不同批量大小下,原始推理与 SGLang 加速推理的时间表现:
此次推理过程中使用的 query 和 document 数据均为随机生成,长度和为…
-
Hello,
Beam later version is V2 and they did drastic changes to their SDK and client that makes most of the training (fine-tuning) and inference code useless. There is no "beam run" and so on...
…
-
I tried to reproduce your gemma2B reward model training again and found that the reward model architecture fine tuned with internlm2 had an output header of 1. I downloaded your GRM-Gemma-2B-Sftrug re…
-
Please add Qwen2 support
```
EETQ_CAUSAL_LM_MODEL_MAP = {
"llama": LlamaEETQForCausalLM,
"baichuan": BaichuanEETQForCausalLM,
"gemma": GemmaEETQForCausalLM
}
```
-
hello. I am getting an error when running the sample below.
The request file does not exist in the original source,
I copied and used the preprocessor_config.json file in the same model family.
…
-
Compile the database of learning materials that contains longer and more reasonable materials.
-
```
[Gemma - http-nio-8181-exec-266 (2022-04-21 11:13:33,376)] ERROR ubic.gemma.core.visualization.ExperimentalDesignVisualizationServiceImpl.sortVectorDataByDesign(121) | Did not find cached layout …
-
Hello Authors,
Thank you for your incredible work and the comprehensive experiments presented in the paper.
I have a question regarding the implementation of attacks. Specifically, some attacks,…
-
Affected datasets: GSE86193, GSE207533, GSE6565, GSE29361.
The list is not exhaustive, I just gathered them from error logs.
```
[Gemma - http-nio-8181-exec-360 (2024-02-28 11:51:17,011)] ERROR…
-
### Can't render **_Latex_** like **matrices** and **mathematical formulas**.
version: LM studio - 0.3.5.
LLM: qwen2.5 7B Q4_K_M.
![Screenshot 2024-12-03 082302](https://github.com/user-attachments…