-
I am using the following code to send a simple query to h2ogpt:
```
import sys
from gradio_utils.grclient import GradioClient
def read_prompt_from_file(file_path):
with open(file_path, 'r…
-
Q1) any minimum requirement for running h2ogpt docker ?
should GPU have at least N GB ?
- got " torch.cuda.OutOfMemoryError: CUDA out of memory."
- at now , using GeForce RTX…
-
### Describe the bug
In gradio 4 only, for objects like chatbot, once streaming some response, can't navigate anywhere to any other tabs or scroll the scroll bar of the chat window. Everything get…
-
```
>>> import torch
>>> from transformers import pipeline
>>> from transformers import pipeline
>>> generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-20b", torch_dtype=torch.bfloat16, trust…
-
### Describe the bug
Running " huggingface-cli download gpt2" failed in the end:
OSError: Consistency check failed: file should be of size 125162496 but has size 90309182 (64-8bits.tflite).
We a…
-
I want to host a python agent on Gradio. It all works good. Im struggling when wanting to display not only the answer but also the AgentExecutor chain. How can I edit the code, so that also the AgentE…
-
- **(1) Describe the bug 简述**
[PROXY] 网络代理状态：已配置。配置信息如下： {'http': '127.0.0.1:10809', 'https': '127.0.0.1:10809'}
[API_KEY] 本项目现已支持OpenAI和API2D的api-key。也支持同时填写多个api-key，如API_KEY="openai-key1,openai-…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
CUDA_VISIBLE_DEVICES=0 python3.10 api_demo.py \
--model_name_or_path ../model/Yi-34B-Chat-4bits \
…
-
**UPD: the solution is [down below](https://github.com/THUDM/CogVLM/issues/138#issuecomment-1852893708)**
---
Is this even working on Windows?
I tried to follow your official guide, but pip faile…
-
### System Info
I have a question&answer over docs chatbot application, that uses the RetrievalQAWithSourcesChain and ChatPromptTemplate. In langchain version 0.0.238 it used to return sources but …