Nottybro commited on
Commit
f0d4cf4
·
verified ·
1 Parent(s): 019e4fd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -2
README.md CHANGED
@@ -1,5 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # WIGIP-1 v2
2
 
 
 
 
 
 
 
3
  ## Stage 1 – Text Pre-Training (ViT-Style Transformer)
4
 
5
  WIGIP-1 v2 is an experimental research model exploring **Vision Transformer (ViT) style architectures for text modeling**, implemented using **JAX + Flax** with **Fully Sharded Data Parallelism (FSDP)** via `pjit`.
@@ -78,5 +101,4 @@ This phase is intended to test whether **ViT-style inductive biases** can learn
78
  ## ⚠️ Disclaimer
79
 
80
  This is **research code** and an **experimental architecture**.
81
- Results are preliminary and **not production-ready**.
82
-
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - allenai/c4
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ tags:
9
+ - jax
10
+ - fsdp
11
+ - vision-transformer
12
+ - text-generation
13
+ - experimental
14
+ ---
15
+ # WIGIP-1 v2
16
+
17
+
18
  # WIGIP-1 v2
19
 
20
+ > **⚠️ implementation & Training Scripts:**
21
+ > The full source code, JAX training loops, and architecture definitions are available on my GitHub:
22
+ > 🔗 **[Click here to view the Training Scripts on GitHub](https://github.com/nurric-ai/Wigip_v2_1.7B_ViT)**
23
+
24
+ ---
25
+
26
  ## Stage 1 – Text Pre-Training (ViT-Style Transformer)
27
 
28
  WIGIP-1 v2 is an experimental research model exploring **Vision Transformer (ViT) style architectures for text modeling**, implemented using **JAX + Flax** with **Fully Sharded Data Parallelism (FSDP)** via `pjit`.
 
101
  ## ⚠️ Disclaimer
102
 
103
  This is **research code** and an **experimental architecture**.
104
+ Results are preliminary and **not production-ready**.