Skip to content

Actions: kyegomez/BitNet

Actions

Welcome WorkFlow

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
welcome.yml
59 workflow runs
59 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[BUG] Is activation actually quantized? (I think it's still in f16 or f32) Welcome WorkFlow #75: Issue #75 opened by burichh
February 5, 2025 09:35 23s
February 5, 2025 09:35 23s
Hint for 1bit Multi-head attention Welcome WorkFlow #74: Issue #74 opened by CastleJin
February 1, 2025 14:53 23s
February 1, 2025 14:53 23s
Bitnet RWKV-7 Welcome WorkFlow #73: Issue #73 opened by snapo
January 29, 2025 00:13 30s
January 29, 2025 00:13 30s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.12.4 Welcome WorkFlow #72: Pull request #72 opened by dependabot bot
January 27, 2025 00:37 25s
January 27, 2025 00:37 25s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.12.3 Welcome WorkFlow #71: Pull request #71 opened by dependabot bot
January 20, 2025 00:21 25s
January 20, 2025 00:21 25s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.12.2 Welcome WorkFlow #70: Pull request #70 opened by dependabot bot
November 11, 2024 00:37 24s
November 11, 2024 00:37 24s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.11.0 Welcome WorkFlow #69: Pull request #69 opened by dependabot bot
November 4, 2024 01:02 37s
November 4, 2024 01:02 37s
I wonder what hardware conditions (GPU) the code uses, and why the loss value has been above 5.2 after running the train.py file, and the validation generated unreadable incomprehensible content. Welcome WorkFlow #68: Issue #68 opened by Dayun0925
November 2, 2024 13:19 40s
November 2, 2024 13:19 40s
CUDA Optimization Welcome WorkFlow #67: Issue #67 opened by simulanics
October 20, 2024 13:40 23s
October 20, 2024 13:40 23s
Can it be used in Huggingface models such as stable diffusion and text to image or LLM models Welcome WorkFlow #66: Issue #66 opened by libai-lab
October 20, 2024 05:32 28s
October 20, 2024 05:32 28s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.10.3 Welcome WorkFlow #65: Pull request #65 opened by dependabot bot
October 7, 2024 00:48 25s
October 7, 2024 00:48 25s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.10.2 Welcome WorkFlow #64: Pull request #64 opened by dependabot bot
September 23, 2024 01:04 29s
September 23, 2024 01:04 29s
Question: embeddings 3bits? Welcome WorkFlow #63: Issue #63 opened by telamon
September 19, 2024 21:59 25s
September 19, 2024 21:59 25s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.10.1 Welcome WorkFlow #62: Pull request #62 opened by dependabot bot
September 9, 2024 01:00 30s
September 9, 2024 01:00 30s
Bump pypa/gh-action-pypi-publish from 1.9.0 to 1.10.0 Welcome WorkFlow #61: Pull request #61 opened by dependabot bot
September 2, 2024 00:47 29s
September 2, 2024 00:47 29s
[BUG] cant compile the cuda Welcome WorkFlow #60: Issue #60 opened by huynhducloi00
July 30, 2024 16:27 25s
July 30, 2024 16:27 25s
Fix: Weight quantization sign should be the last operation Welcome WorkFlow #59: Pull request #59 opened by jmbrito01
June 27, 2024 20:54 24s
June 27, 2024 20:54 24s
Create a javascript version that can run in a web browser? Welcome WorkFlow #58: Issue #58 opened by flatsiedatsie
June 26, 2024 18:13 24s
June 26, 2024 18:13 24s
NanoGPT sample Welcome WorkFlow #57: Issue #57 opened by izaxon
June 18, 2024 14:34 32s
June 18, 2024 14:34 32s
Bump pypa/gh-action-pypi-publish from 1.8.14 to 1.9.0 Welcome WorkFlow #56: Pull request #56 opened by dependabot bot
June 17, 2024 00:58 27s
June 17, 2024 00:58 27s
BitNet model performs wrose than Base Transformer Welcome WorkFlow #55: Issue #55 opened by johanssontan
May 16, 2024 06:37 32s
May 16, 2024 06:37 32s
added if else statement to handle post_act_ln Welcome WorkFlow #54: Pull request #54 opened by Hiromasa-H
May 14, 2024 04:25 26s
May 14, 2024 04:25 26s
[BUG] BitFeedForward(post_act_ln=False) results in a TypeError Welcome WorkFlow #53: Issue #53 opened by Hiromasa-H
May 14, 2024 04:22 27s
May 14, 2024 04:22 27s
Expected BitLinear weight to be 1 or -1 Welcome WorkFlow #52: Issue #52 opened by sanjeev-bhandari
April 25, 2024 05:57 29s
April 25, 2024 05:57 29s
what is the purpose of detach here? Welcome WorkFlow #51: Issue #51 opened by Weitian-Wang-Bosch
April 18, 2024 14:57 27s
April 18, 2024 14:57 27s