kinokokoro/mistral-nemo-webnovels
Updated
•
2
Shisa.AI
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
shisa-ai's activity
leonardlin
updated
a
model
about 2 months ago
leonardlin
posted
an
update
6 months ago
Post
1897
My weekened project ended up being doing some testing between torchtune, axolotl, and unsloth. I *think* it's a 1:1 comparison of what LoRA fine-tuning performance looks like between the different hardware I have in my dev boxes (4090, 3090, 7900 XTX, W7900) with a few other interesting tidbits.
Tonight I wrote up a WandB report (the panel editor is super broken in Firefox 😔) that sums up some of the more interesting bits from the results: https://wandb.ai/augmxnt/train-bench/reports/torchtune-vs-axolotl-vs-unsloth-Trainer-Comparison--Vmlldzo4MzU3NTAx
Tonight I wrote up a WandB report (the panel editor is super broken in Firefox 😔) that sums up some of the more interesting bits from the results: https://wandb.ai/augmxnt/train-bench/reports/torchtune-vs-axolotl-vs-unsloth-Trainer-Comparison--Vmlldzo4MzU3NTAx
leonardlin
posted
an
update
7 months ago
Post
2459
Maybe of interest, I just finished a long writeup of my weekend project exploring Qwen 2 7B Instruct's Chinese censorship: https://huggingface.co/blog/leonardlin/chinese-llm-censorship-analysis
I also have an accompanying model and dataset (and codebase) for those curious to poke around:
* augmxnt/Qwen2-7B-Instruct-deccp
* augmxnt/deccp
I also have an accompanying model and dataset (and codebase) for those curious to poke around:
* augmxnt/Qwen2-7B-Instruct-deccp
* augmxnt/deccp
leonardlin
updated
10
models
7 months ago
shisa-ai/shisa-v1-qwen2-7b
Text Generation
•
Updated
•
23
•
5
shisa-ai/shisa-v1-llama3-70b-gguf
Updated
•
54
shisa-ai/shisa-v1-llama3-8b-gguf
Updated
•
63
shisa-ai/shisa-v1-llama3-70b
Text Generation
•
Updated
•
27
•
3
shisa-ai/shisa-v1-llama3-70b.2e5
Text Generation
•
Updated
•
17
•
1
shisa-ai/shisa-v1-llama3-8b.neftune
Text Generation
•
Updated
•
18
shisa-ai/shisa-v1-llama3-8b.lr-5e6
Text Generation
•
Updated
•
11
•
1
shisa-ai/shisa-v1-mistral0.3-7b
Text Generation
•
Updated
•
15
shisa-ai/shisa-v1-phi3-14b
Text Generation
•
Updated
•
16
•
2
shisa-ai/shisa-v1-llama3-8b
Text Generation
•
Updated
•
185
•
3
leonardlin
posted
an
update
7 months ago
Post
1935
Interesting, I've just seen the my first HF spam on one of my new model uploads:
shisa-ai/shisa-v1-llama3-70b - someone has an SEO spam page as a HF space attached to the model!?! Wild. Who do I report this to?
-
- 4 replies
leonardlin
posted
an
update
7 months ago
Post
1606
For those with an interest in JA language models, this Llama 3 70B test ablation looks like it is the current strongest publicly released, commercially usable, open model available. A lot of caveats I know, but it also matches
shisa-ai/shisa-v1-llama3-70b
augmxnt/ultra-orca-boros-en-ja-v1
gpt-3.5-turbo-0125's JA performance, which is worth noting, and is tuned *exclusively* with the old shisa-v1 dataset (so it's chart position will be very short lived).shisa-ai/shisa-v1-llama3-70b
augmxnt/ultra-orca-boros-en-ja-v1
-
- 2 replies
leonardlin
updated
4
models
7 months ago
leonardlin
posted
an
update
7 months ago
Post
1942
With slurm figured out and ablations humming along, I though I'd update and post my understanding of the legal status of training data in Japan. It is in general, much clearer in the US: https://huggingface.co/blog/leonardlin/ai-training-data-in-japan