LyJonathan commited on
Commit
ff2d60d
·
verified ·
1 Parent(s): b2b004f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -0
README.md CHANGED
@@ -1,3 +1,47 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ datasets:
4
+ - HuggingFaceFW/fineweb-edu
5
+ - EleutherAI/the_pile_deduplicated
6
+ - HuggingFaceTB/dclm-edu
7
+ - HuggingFaceTB/finemath
8
+ - HuggingFaceTB/smollm-corpus
9
+ - wikimedia/wikipedia
10
+ - Harley-ml/lesswrong
11
+ - Harley-ml/HFMC
12
+ - AxiomicLabs/NPset-2-Python-Edu
13
+ language:
14
+ - en
15
+ tags:
16
+ - er
17
+ - fromziro
18
+ - fromzero
19
+ - harley-ml
20
+ - lyjonathan
21
+ - small
22
+ - slm
23
+ - orez
24
+ - sfz
25
  ---
26
+
27
+ **Note**: This model belongs to the **Er** SLM family. All models in the Er family are trained using the same tokenizer, dataset, and token count.
28
+
29
+ # Er-Large
30
+
31
+ ## Summary
32
+ ```
33
+ Task: Text-Generation
34
+ Total training time: 5 days
35
+ Inputs: text
36
+ Outputs: text
37
+ Params: 31,944,632
38
+ Final Loss: 2.404
39
+ Important Benchmark Scores:
40
+ 1. ARC Easy - ....%
41
+ 2. BLiMP - ....%
42
+ 3. HellaSwag - ....%
43
+ 4. ArithMark-2.0 - ....%
44
+ Framework: PyTorch, transformers
45
+ Author: Paul Courneya, Jonathan Ly
46
+ ```
47
+