CodeAlpaca – Instruction following code generation model
1–10 of 50 posts
Re: CodeAlpaca – Instruction following code generation model
#2The results are pretty good; I wish they'd just publish the models so we can run the inference locally (not too many people have access to 8xA100 to train themselves, though I appreciate including the training data and instructions too).
Re: CodeAlpaca – Instruction following code generation model
#3> The code runs on a 8xA100 80GB, but can also run on 8xA10040GB or 4xA100 with lower batch size and gradient accumulation steps. To get the GPUs, I suggest using Lambda Labs, best pricing for the best hardware.
I wonder how much it was total in $ for the fine-tuning.
Also, does anyone have some sort of table/formula that relates MB/GB of training data to $ for fine-tuning?
Re: CodeAlpaca – Instruction following code generation model
#4"Model weights aren't part of the release for now, to respect OpenAI TOS and LLaMA license."
I feel like the whole Open Source ML scene is slowed down by a strong chilling effect. Everyone seems to be afraid to release models.
Meanwhile, other models are freely available up to alpaca 30b:
https://github.com/underlines/awesome-marketing-datascience/...
Re: CodeAlpaca – Instruction following code generation model
#5The results are pretty good; I wish they'd just publish the models so we can run the inference locally (not too many people have access to 8xA100 to train themselves, though I appreciate including the training data and instructions too).
Llama may not be licensed for people to share since you need to apply to get one from Facebook for non commercial use. I think it's more of a license issue
Hopefully similar work can be done with LoRA so the fine-tuning is not as expensive
Re: CodeAlpaca – Instruction following code generation model
#6"Model weights aren't part of the release for now, to respect OpenAI TOS and LLaMA license." I feel like the whole Open Source ML scene is slowed down by a strong chilling effect. Everyone seems to be afraid to release models. Meanwhile, other models are freely available up to alpaca 30b: https://github.com/underlines/awesome-marketing-datascience/...
I don’t understand why Facebook hasn’t taken down the original magnet links in its own repository.
Re: CodeAlpaca – Instruction following code generation model
#7https://github.com/wsxiaoys/awesome-ai-coding
Great time to start an awesome AI coding list!
Re: CodeAlpaca – Instruction following code generation model
#8"Model weights aren't part of the release for now, to respect OpenAI TOS and LLaMA license." I feel like the whole Open Source ML scene is slowed down by a strong chilling effect. Everyone seems to be afraid to release models. Meanwhile, other models are freely available up to alpaca 30b: https://github.com/underlines/awesome-marketing-datascience/...
I don’t understand why Facebook hasn’t taken down the original magnet links in its own repository.
Why would they?
Re: CodeAlpaca – Instruction following code generation model
#9> The code runs on a 8xA100 80GB, but can also run on 8xA10040GB or 4xA100 with lower batch size and gradient accumulation steps. To get the GPUs, I suggest using Lambda Labs, best pricing for the best hardware. I wonder how much it was total in $ for the fine-tuning. Also, does anyone have some sort of table/formula that relates MB/GB of training data to $ for fine-tuning?
Stanford only spent $500 to fine-tune LLAMA for humam instruction with 52k instructions generated by GPT-3. This probably costs less. The use of GPT to generate the instruction data instead of humans is the massive cost reduction. The actual training for fine-tuning on GPUs is relatively cheap.
Re: CodeAlpaca – Instruction following code generation model
#10> The code runs on a 8xA100 80GB, but can also run on 8xA10040GB or 4xA100 with lower batch size and gradient accumulation steps. To get the GPUs, I suggest using Lambda Labs, best pricing for the best hardware. I wonder how much it was total in $ for the fine-tuning. Also, does anyone have some sort of table/formula that relates MB/GB of training data to $ for fine-tuning?
Probably in the hundreds of dollar for 7B model, and may be a thousand or two for the 13B at worst