Skip to content

Actions: gkielian/ReaLLMASIC_nanogpt

Install Then Test GQA Variations

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
235 workflow runs
235 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Add viewer for npz
Install Then Test GQA Variations #135: Commit bca1b0d pushed by gkielian
September 7, 2024 04:25 3m 27s add_factorization_and_steering
September 7, 2024 04:25 3m 27s
Add code for finetuning with FIRE
Install Then Test GQA Variations #134: Commit 5a7528b pushed by gkielian
September 6, 2024 16:23 3m 18s add_fire_finetuning
September 6, 2024 16:23 3m 18s
Update sample.py with eval parameters
Install Then Test GQA Variations #133: Commit 457ce68 pushed by gkielian
September 5, 2024 21:04 3m 22s add_sample_eval_block_size_update
September 5, 2024 21:04 3m 22s
Add update block size to train.py for evaluation
Install Then Test GQA Variations #132: Commit 0a6d65e pushed by gkielian
September 5, 2024 18:48 3m 17s add_training_block_size_update
September 5, 2024 18:48 3m 17s
Add files for experimenting w/wte factorization
Install Then Test GQA Variations #131: Commit d5414dd pushed by gkielian
September 5, 2024 18:02 3m 27s merge_factorization
September 5, 2024 18:02 3m 27s
Add support for steering vectors
Install Then Test GQA Variations #130: Commit 5d3dcbb pushed by gkielian
September 2, 2024 10:11 1m 34s merge_factorization
September 2, 2024 10:11 1m 34s
Add sweep scripts for facilitating exploration
Install Then Test GQA Variations #129: Commit 12202fa pushed by gkielian
September 2, 2024 07:21 3m 11s merge_factorization
September 2, 2024 07:21 3m 11s
Add option for LR decay
Install Then Test GQA Variations #128: Commit 7f9f6c5 pushed by gkielian
September 2, 2024 07:17 3m 7s merge_factorization
September 2, 2024 07:17 3m 7s
Add import export of scaling matrices
Install Then Test GQA Variations #127: Commit bd77c1e pushed by gkielian
August 31, 2024 23:21 1m 41s merge_factorization
August 31, 2024 23:21 1m 41s
Refactor wte_mapping to handle mixture of data
Install Then Test GQA Variations #126: Commit 861a72f pushed by gkielian
August 31, 2024 19:52 3m 13s merge_factorization
August 31, 2024 19:52 3m 13s
Add MLP Expansion factor control and sweep
Install Then Test GQA Variations #125: Commit 981c8dd pushed by gkielian
August 31, 2024 19:03 3m 10s add_mlp_expansion_factor
August 31, 2024 19:03 3m 10s
Merge pull request #245 from klei22/add_softmax_context_benchmark
Install Then Test GQA Variations #124: Commit f4c0781 pushed by gkielian
August 31, 2024 18:59 3m 10s add_mlp_expansion_factor
August 31, 2024 18:59 3m 10s
Add numpy npy viewer and heatmap genertor
Install Then Test GQA Variations #123: Commit 97ff3c2 pushed by gkielian
August 29, 2024 05:45 3m 9s merge_factorization
August 29, 2024 05:45 3m 9s
Add option for weight tying
Install Then Test GQA Variations #122: Commit d1ad166 pushed by gkielian
August 28, 2024 23:09 3m 30s merge_factorization
August 28, 2024 23:09 3m 30s
Add option to just sample directly from train.py
Install Then Test GQA Variations #121: Commit 5ff65fa pushed by gkielian
August 28, 2024 21:11 3m 32s merge_factorization
August 28, 2024 21:11 3m 32s
Add factorization
Install Then Test GQA Variations #120: Commit 8e99a7a pushed by gkielian
August 28, 2024 20:41 3m 22s merge_factorization
August 28, 2024 20:41 3m 22s
Add backprop intermediate value recompute option
Install Then Test GQA Variations #119: Commit f64a039 pushed by gkielian
August 28, 2024 20:36 3m 34s merge_factorization
August 28, 2024 20:36 3m 34s
Add boolean format compatible with experiments
Install Then Test GQA Variations #118: Commit b14f8a3 pushed by gkielian
August 26, 2024 18:15 3m 10s add_softrelumax_fire_sweep
August 26, 2024 18:15 3m 10s
Add progress bar to train.py
Install Then Test GQA Variations #117: Commit 937ffae pushed by gkielian
August 25, 2024 03:32 3m 9s add_progress_bar
August 25, 2024 03:32 3m 9s
Remove stray 'e's from Github Editor
Install Then Test GQA Variations #116: Commit 2ca0958 pushed by klei22
August 24, 2024 05:53 2m 19s add_training_estimates
August 24, 2024 05:53 2m 19s
Fix stray 'e'
Install Then Test GQA Variations #115: Commit 2188a2e pushed by klei22
August 24, 2024 05:50 1m 40s add_training_estimates
August 24, 2024 05:50 1m 40s
Fix stray typos
Install Then Test GQA Variations #114: Commit 3b0f459 pushed by klei22
August 24, 2024 05:48 1m 23s add_training_estimates
August 24, 2024 05:48 1m 23s
Fix typos in train.py
Install Then Test GQA Variations #113: Commit ed275fb pushed by klei22
August 24, 2024 05:46 1m 25s add_training_estimates
August 24, 2024 05:46 1m 25s
Merge branch 'master' into add_training_sample_option
Install Then Test GQA Variations #112: Commit 57ff63e pushed by klei22
August 24, 2024 05:44 3m 6s add_training_sample_option
August 24, 2024 05:44 3m 6s
Merge branch 'master' into add_training_estimates
Install Then Test GQA Variations #111: Commit 858bc2f pushed by klei22
August 24, 2024 05:41 1m 26s add_training_estimates
August 24, 2024 05:41 1m 26s