github
/
minimind-v
mirror of https://github.com/jingyaogong/minimind-v.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

[update] website content

website
jingyaogong 2026-04-20 16:55:17 +08:00
parent b759dd8b20
commit c9c99a96c0
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
index.html
View File

@ -528,7 +528,7 @@
<!-- Title Section --> <!-- Title Section -->
<div class="title-section"> <div class="title-section">
<p class="tagline pixel-font"> <p class="tagline pixel-font">
Train a 67M Vision-Language Model from zero.<br/> Train a 65M Vision-Language Model from zero.<br/>
2 hours. ¥2.6. One 3090.<br/> 2 hours. ¥2.6. One 3090.<br/>
See the World. See the World.
</p> </p>
@ -537,7 +537,7 @@
<!-- Key Stats --> <!-- Key Stats -->
<div class="stats-section"> <div class="stats-section">
<div class="stat-box"> <div class="stat-box">
<h3>67M</h3> <h3>65M</h3>
<p>Parameters</p> <p>Parameters</p>
</div> </div>
<div class="stat-box"> <div class="stat-box">
@ -598,13 +598,13 @@
<tbody> <tbody>
<tr> <tr>
<td><strong>minimind-3v-moe</strong></td> <td><strong>minimind-3v-moe</strong></td>
<td>202M-A67M</td> <td>200M-A65M</td>
<td>1.0 GB</td> <td>1.0 GB</td>
<td>2026.04.20</td> <td>2026.04.20</td>
</tr> </tr>
<tr> <tr>
<td><strong>minimind-3v</strong></td> <td><strong>minimind-3v</strong></td>
<td>67M</td> <td>65M</td>
<td>0.5 GB</td> <td>0.5 GB</td>
<td>2026.04.20</td> <td>2026.04.20</td>
</tr> </tr>
@ -634,9 +634,9 @@
</div> </div>
<div class="changelog-content"> <div class="changelog-content">
<ul> <ul>
<li>New checkpoints: minimind-3v (67M) / minimind-3v-moe (201M-A67M)</li> <li>New checkpoints: minimind-3v (65M) / minimind-3v-moe (200M-A65M)</li>
<li>Projector: added LayerNorm, token merging switched to 2D pixel-shuffle</li> <li>Projector: added LayerNorm, removed reshape token merging (P32 natively outputs 64 tokens)</li>
<li>Vision Encoder switched to SiglipVisionModel (fixed 256×256)</li> <li>Vision Encoder switched to SiglipVisionModel (P32, fixed 256×256)</li>
<li>Training data moved to ALLaVA-4V (Pretrain 1.27M / SFT 2.9M, merged into single-stage SFT)</li> <li>Training data moved to ALLaVA-4V (Pretrain 1.27M / SFT 2.9M, merged into single-stage SFT)</li>
<li>Freeze strategy: freeze_llm=1 unfreezes first + last layers; Pretrain/SFT defaults now 2/1; max_seq_len 360 → 450</li> <li>Freeze strategy: freeze_llm=1 unfreezes first + last layers; Pretrain/SFT defaults now 2/1; max_seq_len 360 → 450</li>
<li>Misc bugfixes and small tweaks</li> <li>Misc bugfixes and small tweaks</li>
@ -653,7 +653,7 @@
<ul> <ul>
<li>Added minimind-3v (67M) and minimind-3v-moe (201M-A67M) models</li> <li>Added minimind-3v (67M) and minimind-3v-moe (201M-A67M) models</li>
<li>Unified 768+8 architecture, supporting both dense and moe modes</li> <li>Unified 768+8 architecture, supporting both dense and moe modes</li>
<li>Switched Visual Encoder from CLIP to SigLIP2 (siglip2-base-p16-ve)</li> <li>Switched Visual Encoder from CLIP to SigLIP2 (siglip2-base-p16-256-ve)</li>
<li>Replaced QFormer with MLP Projection + reshape compression</li> <li>Replaced QFormer with MLP Projection + reshape compression</li>
<li>Dataset format updated to parquet, mixed data sources, updated tokenizer with image placeholder &lt;|image_pad|&gt;, new WebUI with dynamic model directory scanning and dropdown model switching</li> <li>Dataset format updated to parquet, mixed data sources, updated tokenizer with image placeholder &lt;|image_pad|&gt;, new WebUI with dynamic model directory scanning and dropdown model switching</li>
<li>Model code refactored, LLM/VLM unified for Transformers format</li> <li>Model code refactored, LLM/VLM unified for Transformers format</li>