bugs-and-issues

623 threads · Page 12 of 13

Use of user data 5 messages
Hello, I would like to invest in MISTRAL AI but I cannot find any document or website 4 messages
"Limit exceeded" but I'm starting now 2 messages
autogen + paying for api 10 messages
How to best prompt for json response when using complete API? 36 messages
Allow CORS requests please 38 messages
stream mode splits SSE message mid-json, causing problems with some http client/json parser 3 messages
API usage stats, and rate limit 6 messages
API Timeouts or 521 Response 13 messages
API key notworking 30 messages
API Error code 521 7 messages
Seeking collaboration (Offering 4 x RTX 4090 machine for training in return) 11 messages
Can anyone help for prepare datasets 11 messages
Context size of mistral-7B-Instruct-v0.2 2 messages
Embeddings model 6 messages
Initialization of Mixtral-8x7B 3 messages
Cannot run example from documentation: Mistral on Azure with SkyPilot 8 messages
Is it possible to remove the alternating user assistant restriction? 4 messages
API models giving multi-turn responses 4 messages
I would like to swap openAI and pay Mistral per 1M tokens but I have a few questions please. 4 messages
invalid_request_filter code 2201 with default javascript client 6 messages
API rate limit exceeded 3 messages
Fine tune mistralai/Mistral-7B-Instruct-v0.2 4 messages
Explain section 3.1 of privacy policy better 5 messages
API feature request: stop sequences 15 messages
api open-source
Bad API request size limit? 4 messages
API Usage 11 messages
Platform: Internal Server Error when sending context longer than 4k 14 messages
401s on the API? 16 messages
English words synonyms 3 messages
Email verification code was not sent 7 messages
urgent la-plateforme
support email in the docs is not active! 3 messages
models in docs not available on hf 2 messages
Est-ce Mistral adapté à mon projet 15 messages
Requirement to install Mistral 7B on local server 11 messages
Stop the model from using knowledge past certain date 3 messages
Can't get things working on AWS.. 6 messages
How to modify the SentencePiece tokenizer to not split the chatml tokens? 7 messages
RAG +Mistral7B+Instructor model embeddings 10 messages
How incremental learning is done in LLMs? 2 messages
Need an LLM Expert 28 messages
Using Mistral with Spotify api in colab 4 messages
CUDA unknown error 3 messages
Support for German 4 messages
Fine Tuning Mistral on AMD GPU's? 4 messages
Mistral for an agent/tools driven langchain app 2 messages
Code complete? 9 messages
Responses often truncate far short of 4096 tokens, sometimes "### Human:" glitches in output 8 messages
Few-shot prompting help 17 messages
Tokenization/Encoding 4 messages