[HN Gopher] Phi-2
___________________________________________________________________
Phi-2
Author : tosh
Score : 25 points
Date : 2023-12-13 21:36 UTC (1 hours ago)
(HTM) web link (huggingface.co)
(TXT) w3m dump (huggingface.co)
| minimaxir wrote:
| These are the newly-released official weights for the 2.7B model
| discussed earlier this week:
| https://news.ycombinator.com/item?id=38614361
|
| Unfortunately it has a non-commercial research license.
| gigel82 wrote:
| No support in llama.cpp yet :(
|
| https://github.com/ggerganov/llama.cpp/issues/3146
| minimaxir wrote:
| Phi-2 uses a lot of custom code which will slow down
| porting/quantization.
| andy99 wrote:
| There sure is a lot of entitlement in those comments. The whole
| point of GGML is it's a framework you can use to build a model.
| If people want one they can use the framework to make one but
| they would rather just complain.
|
| On another related note, what is the architecture of phi? I
| wonder if there are any big impediments to implementing it in
| ggml? I find it telling that we get a big lecture in the readme
| about the societal implications and blabla all CYA stuff but no
| up-front summary of what the model is, just "transformer
| based". Personally I care much more about that than some
| ridiculous stuff about bias.
___________________________________________________________________
(page generated 2023-12-13 23:01 UTC)