Rickard Edén
neph1
AI & ML interests
applying, dataset creation, finetuning, loras
Recent Activity
new activity
about 15 hours ago
a-r-r-o-w/LTX-Video-0.9.1-diffusers:transformer updated?
new activity
about 16 hours ago
neph1/bellman-7b-mistral-instruct-v0.2:Unquantized version
updated
a model
about 16 hours ago
neph1/bellman-7b-mistral-instruct-v0.2
Articles
Organizations
neph1's activity
posted
an
update
28 days ago
Post
1108
For those interested in game development I've released an experimental finetune of Qwen2.5-Coder for Unity.
neph1/Qwen2.5-Coder-7B-Instruct-Unity
It's using a mix of open source datasets + one specifically made for this (also OS) with multiple responses.
Also thinking about making a code completion model, or one to have more architectural discussions with.
neph1/Qwen2.5-Coder-7B-Instruct-Unity
It's using a mix of open source datasets + one specifically made for this (also OS) with multiple responses.
Also thinking about making a code completion model, or one to have more architectural discussions with.
- 1 reply
posted
an
update
3 months ago
Post
576
Bellman, the Swedish finetune, has once again returned in his biggest incarnation yet, at 12b. Based on Mistral-Nemo-Instruct:
neph1/Mistral-Nemo-Instruct-bellman-12b
posted
an
update
6 months ago
Post
778
Bellman Swedish finetune based on llama3.1 8b is now available:
neph1/llama-3.1-instruct-bellman-8b-swedish
More quants and fp16 are coming. Working out some issues with colab..
neph1/llama-3.1-instruct-bellman-8b-swedish
More quants and fp16 are coming. Working out some issues with colab..
posted
an
update
7 months ago
Post
594
I've noticed some people are still downloading
neph1/sd-seer-griffin-3b
Should I make an update based on a more modern architecture? (griffin-3b is llama (1!))
Should I make an update based on a more modern architecture? (griffin-3b is llama (1!))
- 1 reply
posted
an
update
7 months ago
Post
757
First real version of bellman based on llama 3 instruct 8b has been released!
neph1/llama-3-instruct-bellman-8b-swedish
Close to 16k examples, including 250 rows from my translated codefeedback dataset and a number of non-copyrighted stories.
Two quants are up in the gguf folder. I'll work on adding more quants in the coming days.
neph1/llama-3-instruct-bellman-8b-swedish
Close to 16k examples, including 250 rows from my translated codefeedback dataset and a number of non-copyrighted stories.
Two quants are up in the gguf folder. I'll work on adding more quants in the coming days.
reacted to
stas's
post with 👍
12 months ago
Post
Do you have a hidden massive storage leak thanks to HF hub models and datasets revisions adding up and not getting automatically deleted?
Here is how to delete all old revisions and only keeping
In terminal A:
Do not answer the prompt and proceed with my instructions.
(note your tmp file will have a different path, so adjust it below)
In terminal B:
The perl one-liner uncommented out all lines that had
Now go back to terminal A and hit: N, Y, Y, so it looks like:
Done.
If you messed up with the prompt answering you still have
For more details and additional techniques please see https://github.com/stas00/ml-engineering/tree/master/storage#huggingface-hub-caches
Here is how to delete all old revisions and only keeping
main in a few quick steps and no tedious manual editing.In terminal A:
$ pip install huggingface_hub["cli"] -U
$ huggingface-cli delete-cache --disable-tui
File to edit: /tmp/tmpundr7lky.txt
0 revisions selected counting for 0.0. Continue ? (y/N)Do not answer the prompt and proceed with my instructions.
(note your tmp file will have a different path, so adjust it below)
In terminal B:
$ cp /tmp/tmpedbz00ox.txt cache.txt
$ perl -pi -e 's|^#(.*detached.*)|$1|' cache.txt
$ cat cache.txt >> /tmp/tmpundr7lky.txtThe perl one-liner uncommented out all lines that had
(detached) in it - so can be wiped out. And then we pasted it back into the tmp file huggingface-cli expects to be edited.Now go back to terminal A and hit: N, Y, Y, so it looks like:
0 revisions selected counting for 0.0. Continue ? (y/N) n
89 revisions selected counting for 211.7G. Continue ? (y/N) y
89 revisions selected counting for 211.7G. Confirm deletion ? (Y/n) yDone.
If you messed up with the prompt answering you still have
cache.txt file which you can feed again to the new tmp file it'll create when you run huggingface-cli delete-cache --disable-tui again.For more details and additional techniques please see https://github.com/stas00/ml-engineering/tree/master/storage#huggingface-hub-caches