34 14 8

Hamish Ivison

hamishivi

https://ivison.id.au

AI & ML interests

NLP :)

Recent Activity

updated a dataset 3 days ago

hamishivi/open_scholar_rl_no_refs

updated a model 4 days ago

allenai/Llama-3.1-Tulu-3-405B-DPO

updated a model 4 days ago

allenai/Llama-3.1-Tulu-3-70B-DPO

View all activity

Organizations

hamishivi's activity

New activity in allenai/Llama-3.1-Tulu-3-8B-DPO 4 days ago

Batch Size

#4 opened 4 days ago by

winglian

New activity in allenai/llama-3.1-tulu-2-dpo-8b 2 months ago

How to interpret the performance drop compared with the original llama-3.1-8b?

#1 opened 2 months ago by

Bobi1234

New activity in allenai/open-instruct-gpt4-alpaca-7b 3 months ago

reproducing experiment, looking for some help or advise

#1 opened 3 months ago by

fblgit

commented 2 papers 3 months ago

TESS: Text-to-Text Self-Conditioned Simplex Diffusion

Paper • 2305.08379 • Published May 15, 2023 • 3 •

Large-Scale Data Selection for Instruction Tuning

Paper • 2503.01807 • Published Mar 3 • 12 •

commented 2 papers 4 months ago

TESS 2: A Large-Scale Generalist Diffusion Language Model

Paper • 2502.13917 • Published Feb 19 • 6 •

TESS 2: A Large-Scale Generalist Diffusion Language Model

Paper • 2502.13917 • Published Feb 19 • 6 •

New activity in allenai/open-instruct-cot-7b 5 months ago

Clarification needed: Model outputs garbage text & confusion about model diff vs. full model

#2 opened 5 months ago by

TheFireHacker

New activity in allenai/tulu-3-sft-mixture 6 months ago

tulu_v3.9_open_math_2_gsm8k_50k_0 / tulu-3-sft-personas-math-grade

#4 opened 6 months ago by

RaphaelKalandadze

New activity in allenai/llama-3-tulu-2-8b 10 months ago

Update tokenizer_config.json

#1 opened 10 months ago by

hamishivi

New activity in allenai/tulu-2.5-prompts 11 months ago

The dataset cannot be loaded correctly.

#1 opened 12 months ago by

Qingru

New activity in allenai/tulu-2-13b about 1 year ago

Update tokenizer_config.json

#2 opened about 1 year ago by

chujiezheng

New activity in allenai/tulu-2-dpo-13b about 1 year ago

Update tokenizer_config.json

#4 opened about 1 year ago by

chujiezheng

New activity in allenai/tulu-2-dpo-7b about 1 year ago

add license

#3 opened about 1 year ago by

chujiezheng

New activity in allenai/tulu-2-dpo-13b about 1 year ago

add license

#3 opened about 1 year ago by

chujiezheng

New activity in allenai/tulu-v2-sft-mixture about 1 year ago

The flan subset in tulu-v2-sft-mixture is the same to dolma-flan?

#5 opened about 1 year ago by

speiqin

Is the science subset commercial?

#4 opened about 1 year ago by

huu-ontocord

New activity in allenai/tulu-2-dpo-70b over 1 year ago

Adding `safetensors` variant of this model

#11 opened over 1 year ago by

nouhadziri

New activity in allenai/ultrafeedback_binarized_cleaned over 1 year ago

Why did you remove the TruthfulQA prompts?

#2 opened over 1 year ago by

Filippo

New activity in allenai/open-instruct-llama2-sharegpt-dpo-7b over 1 year ago

Answer different from the dataset

#1 opened over 1 year ago by

celsowm