Hugging Face's logo

SmallDoge
/
Doge-60M-Instruct

Question Answering
Transformers
Safetensors
English
doge
text-generation
trl
sft
dpo
custom_code
Model card Files Community
2
JingzeShi commited on
Commit
8a246e9
路
verified 路
1 Parent(s): b414371

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -2
README.md CHANGED
@@ -89,7 +89,9 @@ We build the Doge-Instruct by first SFT on [SmolTalk](https://huggingface.co/dat
89
  | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
90
  |---|---|---|---|---|---|---|
91
  | [Doge-20M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-20M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 8e-4 | 0.25M | bfloat16 |
 
92
  | [Doge-60M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-60M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 6e-4 | 0.25M | bfloat16 |
 
93
  | [Doge-160M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-160M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 4e-4 | 0.25M | bfloat16 |
94
  | [Doge-320M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-320M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 2e-4 | 0.25M | bfloat16 |
95
 
@@ -97,7 +99,9 @@ We build the Doge-Instruct by first SFT on [SmolTalk](https://huggingface.co/dat
97
  | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
98
  |---|---|---|---|---|---|---|
99
  | [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 8e-5 | 0.125M | bfloat16 |
 
100
  | [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 6e-5 | 0.125M | bfloat16 |
 
101
  | [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 4e-5 | 0.125M | bfloat16 |
102
  | [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 2e-5 | 0.125M | bfloat16 |
103
 
@@ -106,8 +110,10 @@ We build the Doge-Instruct by first SFT on [SmolTalk](https://huggingface.co/dat
106
 
107
  | Model | IFEval (Prompt Strict Acc) | MMLU | BBH | ARC | PIQA | HellaSwag | tokens / s on i7-11 CPU |
108
  |---|---|---|---|---|---|---|---|
109
- | [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | 7.3 | 26.3 | 18.3 | 29.2 | 57.8 | 27.8 | 142 |
110
- | [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | 7.4 | 27.5 | 27.7 | 37.5 | 61.4 | 32.1 | 62 |
 
 
111
  | [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | 16.8 | 29.7 | 29.1 | 42.8 | 64.1 | 37.1 | 28 |
112
  | [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | 28.5 | 30.3 | 31.9 | 51.7 | 71.0 | 50.6 | 16 |
113
 
 
89
  | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
90
  |---|---|---|---|---|---|---|
91
  | [Doge-20M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-20M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 8e-4 | 0.25M | bfloat16 |
92
+ | [Doge-20M-MoE-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-20M-MoE-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 8e-4 | 0.25M | bfloat16 |
93
  | [Doge-60M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-60M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 6e-4 | 0.25M | bfloat16 |
94
+ | [Doge-120M-MoE-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-120M-MoE-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 6e-4 | 0.25M | bfloat16 |
95
  | [Doge-160M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-160M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 4e-4 | 0.25M | bfloat16 |
96
  | [Doge-320M-Instruct-SFT](https://huggingface.co/SmallDoge/Doge-320M-Instruct-SFT) | [smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smoltalk) | 2 | 2048 | 2e-4 | 0.25M | bfloat16 |
97
 
 
99
  | Model | Training Data | Epochs | Content Length | LR | Batch Size | Precision |
100
  |---|---|---|---|---|---|---|
101
  | [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 8e-5 | 0.125M | bfloat16 |
102
+ | [Doge-20M-MoE-Instruct](https://huggingface.co/SmallDoge/Doge-20M-MoE-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 8e-5 | 0.125M | bfloat16 |
103
  | [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 6e-5 | 0.125M | bfloat16 |
104
+ | [Doge-120M-MoE-Instruct](https://huggingface.co/SmallDoge/Doge-120M-MoE-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 6e-5 | 0.125M | bfloat16 |
105
  | [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 4e-5 | 0.125M | bfloat16 |
106
  | [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | [ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) | 2 | 1024 | 2e-5 | 0.125M | bfloat16 |
107
 
 
110
 
111
  | Model | IFEval (Prompt Strict Acc) | MMLU | BBH | ARC | PIQA | HellaSwag | tokens / s on i7-11 CPU |
112
  |---|---|---|---|---|---|---|---|
113
+ | [Doge-20M-Instruct](https://huggingface.co/SmallDoge/Doge-20M-Instruct) | 9.2 | 26.3 | 18.3 | 29.2 | 57.8 | 27.8 | 142 |
114
+ | [Doge-20M-MoE-Instruct](https://huggingface.co/SmallDoge/Doge-20M-MoE-Instruct) | 13.7 | 26.5 | 26.3 | 31.1 | 58.2 | 27.9 | 132 |
115
+ | [Doge-60M-Instruct](https://huggingface.co/SmallDoge/Doge-60M-Instruct) | 9.4 | 27.5 | 27.7 | 37.5 | 61.4 | 32.1 | 62 |
116
+ | [Doge-120M-MoE-Instruct](https://huggingface.co/SmallDoge/Doge-120M-MoE-Instruct) | 24.4 | 28.2 | 30.1 | 44.2 | 62.1 | 36.3 | 58 |
117
  | [Doge-160M-Instruct](https://huggingface.co/SmallDoge/Doge-160M-Instruct) | 16.8 | 29.7 | 29.1 | 42.8 | 64.1 | 37.1 | 28 |
118
  | [Doge-320M-Instruct](https://huggingface.co/SmallDoge/Doge-320M-Instruct) | 28.5 | 30.3 | 31.9 | 51.7 | 71.0 | 50.6 | 16 |
119