Ryan Shrott

Broken?

3

I can’t get this to work anymore. Anyone still use it successfully?

Playwright bug? ValueError: Synchronous browser not provided to navigate_browser

2

Error I am getting: ``` > Entering new AgentExecutor chain... I need to navigate to the TechCrunch website and search for an article about Clubhouse. Action: navigate_browser Action Input: https://techcrunch.com/Traceback...

Please add support for GPTQ models

6

I'd love to run this model with VLLM, but I get an error currently due to quantization! https://huggingface.co/TheBloke/Llama-2-13B-chat-GPTQ

Any fine-tuning example notebooks?

An existing connection was forcibly closed by the remote host

2

I get this error periodically in some of my apps. Is it a Deta issue or an issue with my server? Not sure. Any idea what the cause could be?...

I just started playing with this library. All the examples in the readme work correctly. I see the output of doorbell.live_streaming_json. It gives me a 'sip_to' ID. Anyway, I basically...

As the title says, how can I parallelize this? ``` def generate_output(row): inputs = tokenizer(prompt, return_tensors="pt")["input_ids"] outputs = model.generate(inputs, max_new_tokens=185, temperature=0.0, eos_token_id=tokenizer.encode("}")[0]) result = tokenizer.decode(outputs[0]) completion = extract_completion(result) for index,...

How to get faster inference?

1

I added my RTX 3080 to swarm using: conda install pytorch pytorch-cuda=11.7 -c pytorch -c nvidia pip install git+https://github.com/bigscience-workshop/petals python -m petals.cli.run_server enoch/llama-65b-hf --adapters timdettmers/guanaco-65b But I still find my...

How to upload to hub and use model later on?

3

I am following this basic tutorial, and I'm wondering how I save the fine tuned model and use it later on? For example, in this tutorial, we fine tune a...