Hugging Face's logo

FlofloB
/
83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit

Text Generation
Transformers
PyTorch
Safetensors
English
qwen2
text-generation-inference
unsloth
trl
sft
conversational
Eval Results
Inference Endpoints
Model card Files Community
2
FlofloB leaderboard-pr-bot commited on
Commit
0573634
•
1 Parent(s): 4c4d366

Adding Evaluation Results (#2)

Browse files

- Adding Evaluation Results (60c5d276ba63d408ef472d86eaf54a99a8daed9b)


Co-authored-by: Open LLM Leaderboard PR Bot <leaderboard-pr-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +113 -5
README.md CHANGED
@@ -1,5 +1,7 @@
1
  ---
2
- base_model: unsloth/qwen2.5-0.5b-instruct-bnb-4bit
 
 
3
  tags:
4
  - text-generation-inference
5
  - transformers
@@ -7,11 +9,104 @@ tags:
7
  - qwen2
8
  - trl
9
  - sft
10
- license: apache-2.0
11
- language:
12
- - en
13
  datasets:
14
  - UncovAI/fineweb_CC-MAIN-2024-18_100k_output_UncovAI_83362
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
  # Uploaded model
@@ -22,4 +117,17 @@ datasets:
22
 
23
  This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
24
 
25
- [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
  tags:
6
  - text-generation-inference
7
  - transformers
 
9
  - qwen2
10
  - trl
11
  - sft
12
+ base_model: unsloth/qwen2.5-0.5b-instruct-bnb-4bit
 
 
13
  datasets:
14
  - UncovAI/fineweb_CC-MAIN-2024-18_100k_output_UncovAI_83362
15
+ model-index:
16
+ - name: 83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
17
+ results:
18
+ - task:
19
+ type: text-generation
20
+ name: Text Generation
21
+ dataset:
22
+ name: IFEval (0-Shot)
23
+ type: HuggingFaceH4/ifeval
24
+ args:
25
+ num_few_shot: 0
26
+ metrics:
27
+ - type: inst_level_strict_acc and prompt_level_strict_acc
28
+ value: 28.69
29
+ name: strict accuracy
30
+ source:
31
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
32
+ name: Open LLM Leaderboard
33
+ - task:
34
+ type: text-generation
35
+ name: Text Generation
36
+ dataset:
37
+ name: BBH (3-Shot)
38
+ type: BBH
39
+ args:
40
+ num_few_shot: 3
41
+ metrics:
42
+ - type: acc_norm
43
+ value: 8.13
44
+ name: normalized accuracy
45
+ source:
46
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
47
+ name: Open LLM Leaderboard
48
+ - task:
49
+ type: text-generation
50
+ name: Text Generation
51
+ dataset:
52
+ name: MATH Lvl 5 (4-Shot)
53
+ type: hendrycks/competition_math
54
+ args:
55
+ num_few_shot: 4
56
+ metrics:
57
+ - type: exact_match
58
+ value: 0.0
59
+ name: exact match
60
+ source:
61
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
62
+ name: Open LLM Leaderboard
63
+ - task:
64
+ type: text-generation
65
+ name: Text Generation
66
+ dataset:
67
+ name: GPQA (0-shot)
68
+ type: Idavidrein/gpqa
69
+ args:
70
+ num_few_shot: 0
71
+ metrics:
72
+ - type: acc_norm
73
+ value: 3.13
74
+ name: acc_norm
75
+ source:
76
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
77
+ name: Open LLM Leaderboard
78
+ - task:
79
+ type: text-generation
80
+ name: Text Generation
81
+ dataset:
82
+ name: MuSR (0-shot)
83
+ type: TAUR-Lab/MuSR
84
+ args:
85
+ num_few_shot: 0
86
+ metrics:
87
+ - type: acc_norm
88
+ value: 1.42
89
+ name: acc_norm
90
+ source:
91
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
92
+ name: Open LLM Leaderboard
93
+ - task:
94
+ type: text-generation
95
+ name: Text Generation
96
+ dataset:
97
+ name: MMLU-PRO (5-shot)
98
+ type: TIGER-Lab/MMLU-Pro
99
+ config: main
100
+ split: test
101
+ args:
102
+ num_few_shot: 5
103
+ metrics:
104
+ - type: acc
105
+ value: 6.17
106
+ name: accuracy
107
+ source:
108
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=FlofloB/83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit
109
+ name: Open LLM Leaderboard
110
  ---
111
 
112
  # Uploaded model
 
117
 
118
  This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
119
 
120
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
121
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
122
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FlofloB__83k_continued_pretraining_Qwen2.5-0.5B-Instruct_Unsloth_merged_16bit)
123
+
124
+ | Metric |Value|
125
+ |-------------------|----:|
126
+ |Avg. | 7.92|
127
+ |IFEval (0-Shot) |28.69|
128
+ |BBH (3-Shot) | 8.13|
129
+ |MATH Lvl 5 (4-Shot)| 0.00|
130
+ |GPQA (0-shot) | 3.13|
131
+ |MuSR (0-shot) | 1.42|
132
+ |MMLU-PRO (5-shot) | 6.17|
133
+