Fix conflict
Browse files
README.md
CHANGED
@@ -1,8 +1,4 @@
|
|
1 |
---
|
2 |
-
base_model: meta-llama/Llama-3.2-3B-Instruct
|
3 |
-
datasets:
|
4 |
-
- KingNish/reasoning-base-20k
|
5 |
-
- piotr25691/thea-name-overrides
|
6 |
language:
|
7 |
- en
|
8 |
license: llama3.2
|
@@ -14,6 +10,105 @@ tags:
|
|
14 |
- sft
|
15 |
- reasoning
|
16 |
- llama-3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
---
|
18 |
|
19 |
# Model Description
|
|
|
1 |
---
|
|
|
|
|
|
|
|
|
2 |
language:
|
3 |
- en
|
4 |
license: llama3.2
|
|
|
10 |
- sft
|
11 |
- reasoning
|
12 |
- llama-3
|
13 |
+
base_model: meta-llama/Llama-3.2-3B-Instruct
|
14 |
+
datasets:
|
15 |
+
- KingNish/reasoning-base-20k
|
16 |
+
- piotr25691/thea-name-overrides
|
17 |
+
model-index:
|
18 |
+
- name: thea-c-3b-25r
|
19 |
+
results:
|
20 |
+
- task:
|
21 |
+
type: text-generation
|
22 |
+
name: Text Generation
|
23 |
+
dataset:
|
24 |
+
name: IFEval (0-Shot)
|
25 |
+
type: HuggingFaceH4/ifeval
|
26 |
+
args:
|
27 |
+
num_few_shot: 0
|
28 |
+
metrics:
|
29 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
30 |
+
value: 74.02
|
31 |
+
name: strict accuracy
|
32 |
+
source:
|
33 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
34 |
+
name: Open LLM Leaderboard
|
35 |
+
- task:
|
36 |
+
type: text-generation
|
37 |
+
name: Text Generation
|
38 |
+
dataset:
|
39 |
+
name: BBH (3-Shot)
|
40 |
+
type: BBH
|
41 |
+
args:
|
42 |
+
num_few_shot: 3
|
43 |
+
metrics:
|
44 |
+
- type: acc_norm
|
45 |
+
value: 22.77
|
46 |
+
name: normalized accuracy
|
47 |
+
source:
|
48 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
49 |
+
name: Open LLM Leaderboard
|
50 |
+
- task:
|
51 |
+
type: text-generation
|
52 |
+
name: Text Generation
|
53 |
+
dataset:
|
54 |
+
name: MATH Lvl 5 (4-Shot)
|
55 |
+
type: hendrycks/competition_math
|
56 |
+
args:
|
57 |
+
num_few_shot: 4
|
58 |
+
metrics:
|
59 |
+
- type: exact_match
|
60 |
+
value: 13.37
|
61 |
+
name: exact match
|
62 |
+
source:
|
63 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
64 |
+
name: Open LLM Leaderboard
|
65 |
+
- task:
|
66 |
+
type: text-generation
|
67 |
+
name: Text Generation
|
68 |
+
dataset:
|
69 |
+
name: GPQA (0-shot)
|
70 |
+
type: Idavidrein/gpqa
|
71 |
+
args:
|
72 |
+
num_few_shot: 0
|
73 |
+
metrics:
|
74 |
+
- type: acc_norm
|
75 |
+
value: 2.01
|
76 |
+
name: acc_norm
|
77 |
+
source:
|
78 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
79 |
+
name: Open LLM Leaderboard
|
80 |
+
- task:
|
81 |
+
type: text-generation
|
82 |
+
name: Text Generation
|
83 |
+
dataset:
|
84 |
+
name: MuSR (0-shot)
|
85 |
+
type: TAUR-Lab/MuSR
|
86 |
+
args:
|
87 |
+
num_few_shot: 0
|
88 |
+
metrics:
|
89 |
+
- type: acc_norm
|
90 |
+
value: 1.27
|
91 |
+
name: acc_norm
|
92 |
+
source:
|
93 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
94 |
+
name: Open LLM Leaderboard
|
95 |
+
- task:
|
96 |
+
type: text-generation
|
97 |
+
name: Text Generation
|
98 |
+
dataset:
|
99 |
+
name: MMLU-PRO (5-shot)
|
100 |
+
type: TIGER-Lab/MMLU-Pro
|
101 |
+
config: main
|
102 |
+
split: test
|
103 |
+
args:
|
104 |
+
num_few_shot: 5
|
105 |
+
metrics:
|
106 |
+
- type: acc
|
107 |
+
value: 24.2
|
108 |
+
name: accuracy
|
109 |
+
source:
|
110 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=piotr25691/thea-c-3b-25r
|
111 |
+
name: Open LLM Leaderboard
|
112 |
---
|
113 |
|
114 |
# Model Description
|