-
-
### System Info
- A800-SXM4-40GB
- Driver Version: 535.129.03
- CUDA Version: 12.4
- tensorrt-llm==0.15.0.dev2024101500
### Who can help?
_No response_
### Information
- [ ] The official example …
-
Chào bác, cám ơn bác đã đóng góp model, em có thử sử dụng model với RAG để sử dụng cho công việc, thì bị lỗi này:
RuntimeError: Failed to create LLM 'mpt' from 'models/PhoGPT-4B-Chat-Q4_K_M.gguf'.
…
-
**例行检查**
[//]: # '方框内填 x 表示打钩'
- [ ] 我已确认目前没有类似 issue
- [ ] 我已完整查看过项目 README，以及[项目文档](https://doc.tryfastgpt.ai/docs/intro/)
- [ ] 我使用了自己的 key，并确认我的 key 是可正常使用的
- [ ] 我理解并愿意跟进此 issue，协助测试和提供反…
-
Các probs anh mentor liệt kê (phần nào đã xử lý sẽ được in nghiêng)
- [ ] 1. Tốc độ upload, embedding và tạo database chậm. Nên nghiên cứu cách để tăng tốc lên.
- [ ] 2. Tạo luồng chat …
-
This is an amazing work. I have been working on something that would require me to evaluate the generated outputs of models like Mistral, using a prompt like:
`"Fill the [MASK] token in the sentence.…
-
We want to collect snapshot telemetry specifically for our investigations UI, to track how users are using this new app once it's enabled.
## Acceptance criteria
* Unmapped snapshot telemetry is be…
-
**Feature description**
Suggest to build a Action (and Role) for DB operation such as DB connection and make data visualization from DB basic on LLM.
The Aciton/Role can be:
1. connect to DB …
-
### Your current environment
部署指令：
vllm serve /root/autodl-fs/llm_models/qwen/Qwen2-7B-Instruct --enable-lora --lora-modules bi-lora=/root/autodl-fs/saves/Qwen2-7B-Instruct/lora/sft/checkpoint-1500/…
-
I am currently working on a problem to rerank tools (retrieving the appropriate tool for LLM), but the cross-encoder models are not converging.
Here is an example:
query: give me btc price
tool: ge…