kinokokoro/ds_train
Viewer • Updated • 49.7M • 13
AI & ML interests
JA LLM & Data
Recent Activity
Aratako
updated a
dataset about 2 months ago
Aratako
published a
dataset about 2 months ago
NekoMikoReimu
updated a
dataset about 2 months ago
NekoMikoReimu
published a
dataset about 2 months ago
Aratako
updated a
dataset about 2 months ago
Aratako
published a
dataset about 2 months ago
Aratako
updated a
dataset about 2 months ago
Aratako
published a
dataset about 2 months ago
Aratako
updated a
dataset about 2 months ago
Aratako
published a
dataset about 2 months ago
Aratako
authored a
paper 4 months ago
Aratako
submitted a
paper to Daily Papers 4 months ago
leonardlin
posted an update 8 months ago
Post
2350
We just released our latest Shisa V2.1 Japanese multi-lingual models: https://huggingface.co/collections/shisa-ai/shisa-v21
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
Besides updates to our 14B, and 70B, we have a new LFM2-based 1.2B, Llama 3.2-based 3B, and Qwen 3-based 8B, all with class-leading Japanese language capabilities.
Per usual, lots of details in the Model Cards for those interested.
- 1 reply
leonardlin
posted an update about 1 year ago
Post
510
I'm excited to announce the official release of our Shisa V2 405B model:
shisa-ai/shisa-v2-llama3.1-405b
It's the strongest model ever trained in Japan, and even goes toe-to-toe w/ GPT-4o and DeepSeek-V3 in JA MT-Bench.
For all the details, be sure to check out post and overview report here: https://shisa.ai/posts/shisa-v2-405b/
shisa-ai/shisa-v2-llama3.1-405b
It's the strongest model ever trained in Japan, and even goes toe-to-toe w/ GPT-4o and DeepSeek-V3 in JA MT-Bench.
For all the details, be sure to check out post and overview report here: https://shisa.ai/posts/shisa-v2-405b/
leonardlin
posted an update about 1 year ago
Post
2592
BTW, in case anyone wants to kick the tires, test their 日本語, I have our Shisa V2 405B model up and running temporarily: https://chat.shisa.ai/
- 3 replies
leonardlin
posted an update over 1 year ago
Post
2719
Happy to announce the release of Shisa V2, our latest generation of our bilingual Japanese-English language models. After hundreds of ablations and months of work, we're releasing some of the strongest open Japanese models at 7B, 8B, 12B, 14B, 32B and 70B! Full announcement here https://shisa.ai/posts/shisa-v2/ or visit the Shisa V2 HF collection: shisa-ai/shisa-v2-67fc98ecaf940ad6c49f5689
leonardlin
updated 2
models almost 2 years ago
leonardlin
posted an update about 2 years ago
Post
2153
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
- 1 reply
leonardlin
posted an update about 2 years ago
Post
2546
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