Can we use GPT3.5? about gpt-llm-trainer HOT 6 CLOSED

I tried 3.5 today on two small runs, one of 10 and the other of 30 examples. They yielded 2 and 25 valids, respectively. I had to adjust to gpt-3.5-turbo-16k.

The reason I was doing this is because I was trying to isolate the out of memory problem that is preventing me from successfully using gpt-llm-trainer, and was tired of spending money on gpt-4 runs. ;-)

from gpt-llm-trainer.

I used model="gpt-3.5-turbo", and it ran correctly. I can't comment on the quality of the GTP output as I actually don't need it, I just tried as a test.

from gpt-llm-trainer.

@fredzannarbor @Afo92 Thank your for the confirmation.

from gpt-llm-trainer.

I am facing this issue, with the default model
OSError: NousResearch/llama-2-7b-chat-hf is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo with use_auth_token or log in with huggingface-cli login and pass use_auth_token=True.

any idea what is to be done?
I tried my own sharded model but got me some other error

from gpt-llm-trainer.

I used model_name = "meta-llama/Llama-2-7b-chat-hf" and then

access_token = "hf_YOUR TOKEN HER!"
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    use_auth_token=access_token,
    quantization_config=bnb_config,
    device_map=device_map
)

from gpt-llm-trainer.

@Afo92 Gotcha thank you!

from gpt-llm-trainer.