goichi harada's picture

goichi harada

dahara1

·

https://webbigdata.jp/

dahara1.bsky.social

AI & ML interests

everything!

Recent Activity

updated a model 4 days ago

dahara1/Qwen3-0.6B-executorch-jp

published a model 4 days ago

dahara1/Qwen3-0.6B-executorch-jp

updated a model about 2 months ago

dahara1/shisa-v2.1-qwen3-8b-UD-japanese-imatrix

View all activity

Organizations

New activity in dahara1/DeepSeek-R1-Distill-Qwen-14B-unsloth-jpn about 1 year ago

Update README.md

#1 opened about 1 year ago by

New activity in dahara1/llama3-8b-amd-npu about 1 year ago

Can we run lama3-8b on other npu ?

#2 opened about 1 year ago by

New activity in lmg-anon/vntl-leaderboard over 1 year ago

I came to try again!

#5 opened over 1 year ago by

New activity in webbigdata/ALMA-7B-Ja over 1 year ago

Adding `safetensors` variant of this model

#2 opened over 1 year ago by

New activity in webbigdata/ALMA-7B-Ja-V2 over 1 year ago

Adding Evaluation Results

#1 opened almost 2 years ago by

leaderboard-pr-bot

Adding `safetensors` variant of this model

#2 opened over 1 year ago by

New activity in dahara1/llama3.1-8b-Instruct-amd-npu over 1 year ago

Request for Instructions

#1 opened over 1 year ago by

New activity in google/gemma-2-2b-jpn-it over 1 year ago

tokenizer_config.json is different from gemma-2-2b-it

#8 opened over 1 year ago by

New activity in webbigdata/C3TR-Adapter_gguf over 1 year ago

Hugging Face serverless inference

#3 opened over 1 year ago by

New activity in dahara1/llama3-8b-amd-npu over 1 year ago

Containerization support would be nice.

#1 opened over 1 year ago by

New activity in webbigdata/C3TR-Adapter over 1 year ago

License?

#2 opened over 1 year ago by

New activity in webbigdata/C3TR-Adapter_gguf over 1 year ago

Inquiry on Minimum Configuration and Cost for Running C3TR-Adapter_gguf Model Efficiently

#2 opened over 1 year ago by

Issues with Incomplete Translation Using webbigdata/C3TR-Adapter_gguf with llama.cpp

#1 opened over 1 year ago by

New activity in webbigdata/C3TR-Adapter over 1 year ago

What are the possible values for writing-style?

#1 opened over 1 year ago by

New activity in lmg-anon/vntl-leaderboard over 1 year ago

Since the model has been updated, would it be possible for you to measure the benchmark again?

#4 opened over 1 year ago by

How to add a model

#3 opened over 1 year ago by

New activity in webbigdata/ALMA-7B-Ja almost 2 years ago

Will you be able to finetune alma 13b-r?

#1 opened almost 2 years ago by

New activity in webbigdata/ALMA-7B-Ja-V2-GPTQ-Ja-En almost 2 years ago

お疲れ様です translates to Good evening

#1 opened almost 2 years ago by

New activity in webbigdata/ALMA-7B-Ja-GPTQ-Ja-En about 2 years ago

Error when finetuning this - fp16 vs int8?

#1 opened over 2 years ago by

New activity in open-llm-leaderboard-old/requests about 2 years ago

dahara1_resubmit

#27 opened over 2 years ago by