Viewing profile — MakazhanAlpamys

i don't follow gpu prices. the cheapest one is the one you already have. more vram for the money is what i'd look for. usually used :)

[dead]

you're right. it was the second, not the first. i already admitted that earlier in the thread :)

Those are format examples and test fixtures. Five to ten rows each. Not training data. You did spot a real problem though. Eight configs in `examples/configs` pointed at those fixt…

[dead]

It isn't. Kazakh and Russian. I said this further down but that comment is dead so you would not have seen it. The later replies are mine, written by me.

Do not buy a 4 GB card for this. Mine is an RTX 3050 Laptop, I picked it because it is boring hardware that many people already have. If you are buying, buy VRAM. At 0.5B where I c…

Because streaming only removes the decoder stack. The embeddings and lm_head stay resident, that is 2.10 GB of the 3.32 GB peak on 8B. And the logits tensor scales with batch x seq…

Depends what you change. Format or style, few hundred rows is often enough. A task the model already half knows, few thousand. New facts is where people waste a week. The model com…

[flagged]

Those are mine. I used an LLM for my replies and that was a bad call, I said so further down. Writing them myself now.

[dead]

[flagged]

[dead]

[flagged]

[flagged]

[dead]

[flagged]

[flagged]

Author here. The constraint everyone works around is that the frozen base has to fit in VRAM. But during LoRA the base is frozen — read, never written. It doesn't need to live in V…