8BitStudio commited on
Commit
9ecefd4
·
verified ·
1 Parent(s): 871f0c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -3
README.md CHANGED
@@ -3,6 +3,45 @@ license: apache-2.0
3
  language:
4
  - en
5
  pipeline_tag: text-generation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ---
7
 
8
  ![Sekai-1](Sekai-1.png)
@@ -58,6 +97,4 @@ Paris<|im_end|>
58
  ## Limitations
59
 
60
  Sekai-1 is a 95.6M-parameter model. It makes factual mistakes, loses track in long conversations, and is weak at multi-step reasoning and math beyond simple arithmetic.
61
- It has no safety tuning or refusal behaviour, so don't use it anywhere that needs either. It understands English only. Check responses for the things that matter.
62
-
63
- ##
 
3
  language:
4
  - en
5
  pipeline_tag: text-generation
6
+ tags:
7
+ - small-language-model
8
+ - slm
9
+ - tiny-llm
10
+ - tinyllm
11
+ - 100m
12
+ - sub-100m
13
+ - efficient
14
+ - efficient-llm
15
+ - compute-efficient
16
+ - from-scratch
17
+ - pretrained-from-scratch
18
+ - base-and-chat
19
+ - chat
20
+ - conversational
21
+ - instruct
22
+ - sft
23
+ - causal-lm
24
+ - text-generation
25
+ - english
26
+ - llama
27
+ - decoder-only
28
+ - transformer
29
+ - cpu
30
+ - cpu-inference
31
+ - edge
32
+ - on-device
33
+ - low-resource
34
+ - consumer-gpu
35
+ - single-gpu
36
+ - gpu
37
+ - open-slm-leaderboard
38
+ - leaderboard
39
+ - research
40
+ - education
41
+ - hobbyist
42
+ - indie
43
+ - sekai
44
+ - sekai-1
45
  ---
46
 
47
  ![Sekai-1](Sekai-1.png)
 
97
  ## Limitations
98
 
99
  Sekai-1 is a 95.6M-parameter model. It makes factual mistakes, loses track in long conversations, and is weak at multi-step reasoning and math beyond simple arithmetic.
100
+ It has no safety tuning or refusal behavior, so don't use it anywhere that needs either. It understands English only. Check responses for the things that matter.