-
模型:https://modelscope.cn/models/OpenBMB/MiniCPM-V-2_6
通常,多模态大模型微调会使用自定义数据集进行微调。在这里,我们将展示可直接运行的demo。
在开始微调之前,请确保您的环境已准备妥当。
```bash
git clone https://github.com/modelscope/swift.git
cd swift
…
-
how do I set a timeout? If the generation is on the CPU (for example, Mixtral 8x22b), then it falls off after a timeout.
-
Titan exposes a subset of ElasticSearch features. ElasticSearch allows customized tokenizers and filters. Proper use of es to index Titan propertykeys would allow Titan to take advantage of these po…
-
I am building a tool which would extract data from a potentially large JSON. If data is ndjson, then it is easy to read it line by line and extract data from each separate object. But if data is in a …
mitar updated
2 weeks ago
-
I used a fine-tuned llama2 model and built it with awq-int4, tp_size=4 max_input_length=8000, max_output_length=8000with tensorrt-llm.
The model runs perfectly under tensorrt-llm.
When I use Trito…
-
# Introduction
I would like to discuss a change in `aeson` to introduce an explicit sharing in `Key`, and actually, all `Text` values used during `decode`.
My motivation comes from the fact that…
-
### Describe the bug
A call to `.filter` occasionally hangs (after the filter is complete, according to tqdm)
There is a trace produced
```
Exception ignored in:
Traceback (most recent call …
-
### Your current environment
python 3.10
vllm 0.5.4
### 🐛 Describe the bug
There is no problem running with the official demo:
```
from transformers import AutoTokenizer
from PIL i…
-
### Feature request
Fu et al. propose a novel decoding technique that accelerates greedy decoding on Llama 2 and Code-Llama by 1.5-2x across various parameters sizes, without a draft model. This meth…
-
Hello - I notice that the chat arena version of fastchat-t5-3b-v1.0 provides quite different answers from the model compared to when it is downloaded manually and run using fastchat.serve.cli --model-…