R
RunPod•7d ago
annasuhstuff

No config error /

Hello everyone, i have finetuned unsloth/Phi-3-mini-4k-instruct, and then pushed my model to Huggingface repo. One of the problems is - OSError: We couldn't connect to 'https://huggingface.co' to load this file, couldn't find it in the cached files and it looks like alsokit/eLM-mini-4B-4K-4bit-v01-merged-4bit is not the path to a directory containing a file named config.json. But I have config.json file (see screenshot) Also there are other errors among that error (please see the second screenshot) Can anyone help me?
No description
No description
3 Replies
nerdylive
nerdylive•7d ago
Did you have the model in network storage? Or try using hf token to authenticate
annasuhstuff
annasuhstuff•7d ago
When I create an endpoint, i just pass my hj token in environment variables HF_TOKEN : hf_blablabla (i copy the token from my hf account)
digigoblin
digigoblin•7d ago
"Could not connect" implies that Hugging Face may have been down again
Want results from more Discord servers?
Add your server
More Posts
Getting data in/out of a community cloud podFor Secure Cloud pods, you're able to dump to a Network Volume, and either manually download that orDistributing model across multiple GPUs using vLLMvLLM has parameter TENSOR_PARALLEL_SIZE to distribute model across multiple GPUs but is this parametworker no executethis worker "ir6fwdhb34ujm7" run but no execute, why????Environment Variable in ServerlessHello, quick question, how do I pass environment variables in a request for serverless endpoint? EspWhen does IP of pod change?When does the IP of the pod changes? Does it change when we restart/pause the pod or only when we deHow does the soft check on workers limit work?I've noticed that the first soft cap is about 100$ so i guess that having a balance that's more thanStuck in the initializationSeems that I'm stuck in the intiialization loop e.g. ``` 2024-06-24T10:47:39Z worker is ready 2024-0cannot stream openai compatible response outI have the below code for streaming the response, the generator is working but cannnot stream the repossible to take image from dockerhubHi I want to be able to pull an image from dockerhub and use on my 100gb network volume storage0 GPU pod makes no senseI have network storage attached to my pods. I don't care if a GPU gets taken from me, but it's very