12 37 3

Sean McLeish PRO

smcleish

https://mcleish7.github.io/

AI & ML interests

None yet

Recent Activity

updated a model about 4 hours ago

smcleish/0.6b-embed-4b-instruct-cs-16-summary-mean-1024-mlp-ov256

updated a collection about 11 hours ago

compression

published a model about 11 hours ago

smcleish/0.6b-embed-4b-instruct-cs-16-summary-mean-1024-mlp-ov256

View all activity

Organizations

Collections 2

Papers 6

models 57

smcleish/0.6b-embed-4b-instruct-cs-16-summary-mean-1024-mlp-ov256

Updated about 11 hours ago

smcleish/Qwen3-Embedding-0.6b-embed-4b-instruct-cs-16-summary-mean-1024-attn-mlp-ov256-stage-3-1e-5

Updated 10 days ago

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-3

Updated 14 days ago

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-2

Updated 17 days ago

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data

Updated 20 days ago

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-attn-mlp-ov256-chunksize-8

Updated 22 days ago

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-attn-mlp-ov256

Updated 23 days ago

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-100

Text Generation • 2B • Updated Jan 22

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-200

Text Generation • 2B • Updated Jan 22 • 1

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-300

Text Generation • 2B • Updated Jan 22 • 3

View 57 models

datasets 4

Sean McLeish PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

smcleish/Qwen3-Embedding-0.6b-embed-4b-instruct-cs-16-summary-mean-1024-attn-mlp-ov256-stage-3-1e-5

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-3

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-2

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data

CarperAI/github-diffs-deduped

bigcode/github-commits-diff-dedup-pjjs-april

ASSERT-KTH/megadiff-single-function

ASSERT-KTH/megadiff

smcleish/Qwen3-Embedding-0.6b-embed-4b-instruct-cs-16-summary-mean-1024-attn-mlp-ov256-stage-3-1e-5

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-3

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-2

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data

CarperAI/github-diffs-deduped

bigcode/github-commits-diff-dedup-pjjs-april

ASSERT-KTH/megadiff-single-function

ASSERT-KTH/megadiff

Papers 6

models 57

smcleish/0.6b-embed-4b-instruct-cs-16-summary-mean-1024-mlp-ov256

smcleish/Qwen3-Embedding-0.6b-embed-4b-instruct-cs-16-summary-mean-1024-attn-mlp-ov256-stage-3-1e-5

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-3

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Inst-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data-run-2

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-lr-1e5-16384-short-data

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-attn-mlp-ov256-chunksize-8

smcleish/Qwen3-Embedding-0.6B-Qwen3-4B-Instruct-2507-cs16-summary_mean-bst1024-attn-mlp-ov256

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-100

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-200

smcleish/deepscaler-1.5b-8k-reproduce-first-run-with-shuffle-8k-300-chkpt-step-300

datasets 4

smcleish/deepscaler_outputs

smcleish/error_at_k_saved_start_0_end_20000_num_completions_10

smcleish/retrofitting-llama-fineweb-edu-tokenized

smcleish/scaling-laws-cache

Sean McLeish PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 6

models 57 Sort: Recently updated

datasets 4 Sort: Recently updated

models 57

datasets 4