Hamish Ivison

hamishivi

40 20 8

maomaocun's profile picture

LeoHyperlink's profile picture

shootstuff's profile picture

https://ivison.id.au

hamishivi
hamishivi

AI & ML interests

NLP :)

Recent Activity

updated a dataset about 6 hours ago

TMaxxx/TMax-Ablation-No-Difficulty-5K

published a dataset about 6 hours ago

TMaxxx/TMax-Ablation-No-Difficulty-5K

updated a dataset about 8 hours ago

TMaxxx/TMax-Ablation-No-Verifiers-5K

View all activity

Organizations

hamishivi 's collections 10

Tmax v1.1

See https://huggingface.co/collections/allenai/tmax for original release models and datasets.

TMaxxx/qwen35-9b-dppo-hardened-prefilter

Reinforcement Learning • 9B • Updated 1 day ago • 30
TMaxxx/qwen-4b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 4B • Updated 1 day ago • 24
TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 2B • Updated 1 day ago • 35
TMaxxx/qwen-27b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 2.65M • Updated 1 day ago • 30

RLVE

Models for "RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments" - https://arxiv.org/abs/2511.07317

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

Paper • 2511.07317 • Published Nov 10, 2025 • 18
hamishivi/OpenThinker3-1.5B-RLVE

Text Generation • 2B • Updated Nov 11, 2025 • 28 • 2
hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE

Text Generation • 2B • Updated Nov 11, 2025 • 36 • 3

TESS 2

Models associated with the paper "TESS-2: A Large-Scale, Generalist Diffusion Language Model". Code: https://github.com/hamishivi/tess-2

TESS 2: A Large-Scale Generalist Diffusion Language Model

Paper • 2502.13917 • Published Feb 19, 2025 • 6
hamishivi/tess2-v0.3

7B • Updated Feb 20, 2025 • 118 • 5
hamishivi/tess2-v0.1

7B • Updated Feb 20, 2025 • 26
hamishivi/tess2-v0.3-base

7B • Updated Feb 20, 2025 • 8

7b tulu 2.5

a small run at 7b scale with ppo, following the unpacking dpo and ppo paper.

hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm

Text Generation • 7B • Updated Jun 25, 2024 • 20
hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm-value

Token Classification • 7B • Updated Jun 25, 2024 • 14
hamishivi/tulu-v2.5-7b-uf-rm

Text Classification • 7B • Updated Jun 25, 2024 • 11

Tulu V1 Suite

The set of models associated with the paper "How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources".

allenai/tulu-65b

Text Generation • Updated Jun 29, 2023 • 288 • 21
allenai/tulu-30b

Text Generation • Updated Jun 20, 2023 • 289 • 18
allenai/tulu-13b

Text Generation • Updated Jun 20, 2023 • 132 • 8
allenai/tulu-7b

Text Generation • Updated Jun 20, 2023 • 210 • 9

Tmax Extras

Auxiliary datasets for tmax.

hamishivi/agent-task-endless-terminals

Viewer • Updated Jun 1 • 2.49k • 196
hamishivi/agent-task-cli-gym

Viewer • Updated 25 days ago • 1.55k • 148
hamishivi/agent-task-termigen

Viewer • Updated May 13 • 3.56k • 1.32k
hamishivi/agent-task-swe-smith

Updated 25 days ago • 155

Large-Scale Data Selection for Instruction Tuning

Datasets and models associated with the paper "Large-Scale Data Selection for Instruction Tuning" (https://arxiv.org/abs/2503.01807)

Large-Scale Data Selection for Instruction Tuning

Paper • 2503.01807 • Published Mar 3, 2025 • 14
hamishivi/tulu-2-multitask-rrmax-326k-sft

7B • Updated Mar 4, 2025 • 25 • 1
hamishivi/rds-sels-multitask-rrmax-top326k

Viewer • Updated Mar 4, 2025 • 326k • 40 • 1
hamishivi/llama-3.1-tulu-3-multitask-rrmax-939k-sft

Updated Mar 4, 2025 • 8

Tulu 2 Llama 3 Update

Llama 3 models trained on the tulu dataset, following https://arxiv.org/abs/2311.10702 (tulu 2) and https://arxiv.org/abs/2406.09279 (tulu 2.5).

allenai/llama-3.1-tulu-2-dpo-70b

71B • Updated Aug 15, 2024 • 104
allenai/llama-3.1-tulu-2-70b

71B • Updated Aug 15, 2024 • 99
allenai/llama-3.1-tulu-2-70b-uf-mean-rm

70B • Updated Aug 15, 2024 • 100
allenai/llama-3.1-tulu-2-dpo-8b

8B • Updated Aug 15, 2024 • 101 • 2

Tulu V2 Suite

The set of models associated with the Tulu V2 technical report.

allenai/tulu-2-dpo-70b

Text Generation • 69B • Updated Jan 31, 2024 • 369 • 157
allenai/tulu-2-dpo-13b

Text Generation • 13B • Updated May 17, 2024 • 426 • • 21
allenai/tulu-2-dpo-7b

Text Generation • Updated May 14, 2024 • 523 • • 21
allenai/tulu-2-70b

Text Generation • Updated Apr 19, 2024 • 140 • 8

LM Preference Datasets

lmsys/chatbot_arena_conversations

Viewer • Updated Sep 30, 2023 • 33k • 1.68k • 495
Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 30.3k • 2.39k
openai/summarize_from_feedback

Viewer • Updated Jan 3, 2023 • 194k • 2.38k • 222
openai/webgpt_comparisons

Viewer • Updated Dec 19, 2022 • 19.6k • 602 • 242

Tmax v1.1

See https://huggingface.co/collections/allenai/tmax for original release models and datasets.

TMaxxx/qwen35-9b-dppo-hardened-prefilter

Reinforcement Learning • 9B • Updated 1 day ago • 30
TMaxxx/qwen-4b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 4B • Updated 1 day ago • 24
TMaxxx/qwen-2b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 2B • Updated 1 day ago • 35
TMaxxx/qwen-27b-dppo-hardened-prefilter-sc3

Reinforcement Learning • 2.65M • Updated 1 day ago • 30

Tmax Extras

Auxiliary datasets for tmax.

hamishivi/agent-task-endless-terminals

Viewer • Updated Jun 1 • 2.49k • 196
hamishivi/agent-task-cli-gym

Viewer • Updated 25 days ago • 1.55k • 148
hamishivi/agent-task-termigen

Viewer • Updated May 13 • 3.56k • 1.32k
hamishivi/agent-task-swe-smith

Updated 25 days ago • 155

RLVE

Models for "RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments" - https://arxiv.org/abs/2511.07317

RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments

Paper • 2511.07317 • Published Nov 10, 2025 • 18
hamishivi/OpenThinker3-1.5B-RLVE

Text Generation • 2B • Updated Nov 11, 2025 • 28 • 2
hamishivi/Nemotron-Research-Reasoning-Qwen-1.5B-v2-RLVE

Text Generation • 2B • Updated Nov 11, 2025 • 36 • 3

Large-Scale Data Selection for Instruction Tuning

Datasets and models associated with the paper "Large-Scale Data Selection for Instruction Tuning" (https://arxiv.org/abs/2503.01807)

Large-Scale Data Selection for Instruction Tuning

Paper • 2503.01807 • Published Mar 3, 2025 • 14
hamishivi/tulu-2-multitask-rrmax-326k-sft

7B • Updated Mar 4, 2025 • 25 • 1
hamishivi/rds-sels-multitask-rrmax-top326k

Viewer • Updated Mar 4, 2025 • 326k • 40 • 1
hamishivi/llama-3.1-tulu-3-multitask-rrmax-939k-sft

Updated Mar 4, 2025 • 8

TESS 2

Models associated with the paper "TESS-2: A Large-Scale, Generalist Diffusion Language Model". Code: https://github.com/hamishivi/tess-2

TESS 2: A Large-Scale Generalist Diffusion Language Model

Paper • 2502.13917 • Published Feb 19, 2025 • 6
hamishivi/tess2-v0.3

7B • Updated Feb 20, 2025 • 118 • 5
hamishivi/tess2-v0.1

7B • Updated Feb 20, 2025 • 26
hamishivi/tess2-v0.3-base

7B • Updated Feb 20, 2025 • 8

Tulu 2 Llama 3 Update

Llama 3 models trained on the tulu dataset, following https://arxiv.org/abs/2311.10702 (tulu 2) and https://arxiv.org/abs/2406.09279 (tulu 2.5).

allenai/llama-3.1-tulu-2-dpo-70b

71B • Updated Aug 15, 2024 • 104
allenai/llama-3.1-tulu-2-70b

71B • Updated Aug 15, 2024 • 99
allenai/llama-3.1-tulu-2-70b-uf-mean-rm

70B • Updated Aug 15, 2024 • 100
allenai/llama-3.1-tulu-2-dpo-8b

8B • Updated Aug 15, 2024 • 101 • 2

7b tulu 2.5

a small run at 7b scale with ppo, following the unpacking dpo and ppo paper.

hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm

Text Generation • 7B • Updated Jun 25, 2024 • 20
hamishivi/tulu-v2.5-7b-uf-mean-7b-uf-rm-value

Token Classification • 7B • Updated Jun 25, 2024 • 14
hamishivi/tulu-v2.5-7b-uf-rm

Text Classification • 7B • Updated Jun 25, 2024 • 11

Tulu V2 Suite

The set of models associated with the Tulu V2 technical report.

allenai/tulu-2-dpo-70b

Text Generation • 69B • Updated Jan 31, 2024 • 369 • 157
allenai/tulu-2-dpo-13b

Text Generation • 13B • Updated May 17, 2024 • 426 • • 21
allenai/tulu-2-dpo-7b

Text Generation • Updated May 14, 2024 • 523 • • 21
allenai/tulu-2-70b

Text Generation • Updated Apr 19, 2024 • 140 • 8

Tulu V1 Suite

The set of models associated with the paper "How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources".

allenai/tulu-65b

Text Generation • Updated Jun 29, 2023 • 288 • 21
allenai/tulu-30b

Text Generation • Updated Jun 20, 2023 • 289 • 18
allenai/tulu-13b

Text Generation • Updated Jun 20, 2023 • 132 • 8
allenai/tulu-7b

Text Generation • Updated Jun 20, 2023 • 210 • 9

LM Preference Datasets

lmsys/chatbot_arena_conversations

Viewer • Updated Sep 30, 2023 • 33k • 1.68k • 495
Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 30.3k • 2.39k
openai/summarize_from_feedback

Viewer • Updated Jan 3, 2023 • 194k • 2.38k • 222
openai/webgpt_comparisons

Viewer • Updated Dec 19, 2022 • 19.6k • 602 • 242