Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
model_name: SmolLM2_Thinks
|
|
@@ -5,10 +142,22 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
- sft
|
| 7 |
- trl
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
licence: license
|
| 9 |
-
|
| 10 |
-
-
|
| 11 |
-
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Model Card for SmolLM2_Thinks
|
|
@@ -51,10 +200,7 @@ Cite TRL as:
|
|
| 51 |
```bibtex
|
| 52 |
@misc{vonwerra2022trl,
|
| 53 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 59 |
-
}
|
| 60 |
-
```
|
|
|
|
| 1 |
+
|
| 2 |
+
Hugging Face's logo Hugging Face
|
| 3 |
+
|
| 4 |
+
Models
|
| 5 |
+
Datasets
|
| 6 |
+
Spaces
|
| 7 |
+
Docs
|
| 8 |
+
Enterprise
|
| 9 |
+
Pricing
|
| 10 |
+
|
| 11 |
+
reaperdoesntknow
|
| 12 |
+
/
|
| 13 |
+
SmolLM2_Thinks
|
| 14 |
+
Text Generation
|
| 15 |
+
Transformers
|
| 16 |
+
PyTorch
|
| 17 |
+
English
|
| 18 |
+
llama
|
| 19 |
+
Generated from Trainer
|
| 20 |
+
sft
|
| 21 |
+
trl
|
| 22 |
+
proof
|
| 23 |
+
cot
|
| 24 |
+
reasoning
|
| 25 |
+
symbioticai
|
| 26 |
+
calculus
|
| 27 |
+
logic
|
| 28 |
+
SFT
|
| 29 |
+
TRL
|
| 30 |
+
datasets
|
| 31 |
+
finetune
|
| 32 |
+
conversational
|
| 33 |
+
text-generation-inference
|
| 34 |
+
Model card
|
| 35 |
+
Files and versions
|
| 36 |
+
xet
|
| 37 |
+
Community
|
| 38 |
+
Settings
|
| 39 |
+
SmolLM2_Thinks/
|
| 40 |
+
|
| 41 |
+
license
|
| 42 |
+
|
| 43 |
+
datasets
|
| 44 |
+
|
| 45 |
+
language
|
| 46 |
+
|
| 47 |
+
metrics
|
| 48 |
+
|
| 49 |
+
base_model
|
| 50 |
+
|
| 51 |
+
new_version
|
| 52 |
+
|
| 53 |
+
pipeline_tag
|
| 54 |
+
|
| 55 |
+
library_name
|
| 56 |
+
|
| 57 |
+
tags
|
| 58 |
+
|
| 59 |
+
Eval Results
|
| 60 |
+
View doc
|
| 61 |
+
1
|
| 62 |
+
2
|
| 63 |
+
3
|
| 64 |
+
4
|
| 65 |
+
5
|
| 66 |
+
6
|
| 67 |
+
7
|
| 68 |
+
8
|
| 69 |
+
9
|
| 70 |
+
10
|
| 71 |
+
11
|
| 72 |
+
12
|
| 73 |
+
13
|
| 74 |
+
14
|
| 75 |
+
15
|
| 76 |
+
16
|
| 77 |
+
17
|
| 78 |
+
18
|
| 79 |
+
19
|
| 80 |
+
20
|
| 81 |
+
21
|
| 82 |
+
22
|
| 83 |
+
23
|
| 84 |
+
24
|
| 85 |
+
25
|
| 86 |
+
26
|
| 87 |
+
27
|
| 88 |
+
28
|
| 89 |
+
29
|
| 90 |
+
30
|
| 91 |
+
31
|
| 92 |
+
32
|
| 93 |
+
33
|
| 94 |
+
34
|
| 95 |
+
35
|
| 96 |
+
36
|
| 97 |
+
37
|
| 98 |
+
38
|
| 99 |
+
39
|
| 100 |
+
40
|
| 101 |
+
41
|
| 102 |
+
42
|
| 103 |
+
43
|
| 104 |
+
44
|
| 105 |
+
45
|
| 106 |
+
46
|
| 107 |
+
47
|
| 108 |
+
48
|
| 109 |
+
49
|
| 110 |
+
50
|
| 111 |
+
51
|
| 112 |
+
52
|
| 113 |
+
53
|
| 114 |
+
54
|
| 115 |
+
55
|
| 116 |
+
56
|
| 117 |
+
57
|
| 118 |
+
58
|
| 119 |
+
59
|
| 120 |
+
60
|
| 121 |
+
61
|
| 122 |
+
62
|
| 123 |
+
63
|
| 124 |
+
64
|
| 125 |
+
65
|
| 126 |
+
β
|
| 127 |
+
β
|
| 128 |
+
β
|
| 129 |
+
β
|
| 130 |
+
β
|
| 131 |
+
β
|
| 132 |
+
β
|
| 133 |
+
β
|
| 134 |
+
β
|
| 135 |
+
β
|
| 136 |
+
β
|
| 137 |
+
β
|
| 138 |
---
|
| 139 |
library_name: transformers
|
| 140 |
model_name: SmolLM2_Thinks
|
|
|
|
| 142 |
- generated_from_trainer
|
| 143 |
- sft
|
| 144 |
- trl
|
| 145 |
+
- proof
|
| 146 |
+
- cot
|
| 147 |
+
- reasoning
|
| 148 |
+
- symbioticai
|
| 149 |
+
- calculus
|
| 150 |
+
- logic
|
| 151 |
+
- SFT
|
| 152 |
+
- TRL
|
| 153 |
+
- transformers
|
| 154 |
+
- datasets
|
| 155 |
+
- finetune
|
| 156 |
licence: license
|
| 157 |
+
datasets:
|
| 158 |
+
- AI-MO/NuminaMath-1.5
|
| 159 |
+
language:
|
| 160 |
+
- en
|
| 161 |
---
|
| 162 |
|
| 163 |
# Model Card for SmolLM2_Thinks
|
|
|
|
| 200 |
```bibtex
|
| 201 |
@misc{vonwerra2022trl,
|
| 202 |
title = {{TRL: Transformer Reinforcement Learning}},
|
| 203 |
+
Commit directly to the main branch
|
| 204 |
+
Open as a pull request to the main branch
|
| 205 |
+
Commit changes
|
| 206 |
+
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
|
|
|
|
|
|
|
|
|