AxionLab-official commited on
Commit
5badbd7
·
verified ·
1 Parent(s): 080798f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -17,7 +17,7 @@ datasets:
17
 
18
  <div align="center">
19
 
20
- # CMA 8M
21
 
22
  ### Channel-Mixing Attention at 7.85 million parameters.
23
 
@@ -33,7 +33,7 @@ A compact generalist language model built to study channel mixing at small scale
33
 
34
  ## Overview
35
 
36
- CMA 8M is a **7,849,161-parameter** Channel-Mixing Attention generalist
37
  causal language model trained for 40,000 steps. It pairs a compact nine-layer
38
  architecture with the unmodified native GPT-S 4,096-token tokenizer.
39
 
@@ -64,7 +64,7 @@ This repository contains a custom Transformers architecture. Load it with
64
  ```python
65
  from transformers import AutoModelForCausalLM, AutoTokenizer
66
 
67
- repo_id = "User01110/cma-8M"
68
 
69
  tokenizer = AutoTokenizer.from_pretrained(
70
  repo_id,
 
17
 
18
  <div align="center">
19
 
20
+ # SupraCMA 8M
21
 
22
  ### Channel-Mixing Attention at 7.85 million parameters.
23
 
 
33
 
34
  ## Overview
35
 
36
+ SupraCMA 8M is a **7,849,161-parameter** Channel-Mixing Attention generalist
37
  causal language model trained for 40,000 steps. It pairs a compact nine-layer
38
  architecture with the unmodified native GPT-S 4,096-token tokenizer.
39
 
 
64
  ```python
65
  from transformers import AutoModelForCausalLM, AutoTokenizer
66
 
67
+ repo_id = "SupraLabs/SupraCMA-8M"
68
 
69
  tokenizer = AutoTokenizer.from_pretrained(
70
  repo_id,