Hugging Face's logo

nvidia
/
DLER-R1-7B-Research

Safetensors
English
qwen2
Model card Files
xet
Community
1
sliuau commited on
Commit
0cf5f38
·
verified ·
1 Parent(s): d248dc5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ DLER-Qwen-R1-7B is an ultra-efficient 7B open-weight reasoning model designed fo
18
  This model is for research and development only.
19
 
20
  ### Evaluation Results:
21
- | Model | MATH | Length | AIME | Length | AMC | Length | Minerva |Length | Olympiad |Length | Total Avg |
22
  |------------------|----------|------------|--------------------|------------------|--------------------|------------------|--------------------|------------------|--------------------|------------------|-----------------|
23
  | Deepseek-R1-7B | 93.60 | 3999 | 55.40 | 13241 | 82.90 | 7461 | 49.79 | 5199 | 58.21 | 8837 | 7747 |
24
  | **DLER-R1-7B** | **94.21 (+0.61%)** | **1634 (-60%)** | **55.62 (+0.22%)** | **3230 (-76%)** | **84.41 (+1.51%)** | **2512 (-0.67%)** | **53.88 (+4.09%)** | **2058 (-61%)** | **60.48 (+2.27%)** | **2592 (-71%)** | **2405 (-69%)** |
 
18
  This model is for research and development only.
19
 
20
  ### Evaluation Results:
21
+ | Model | MATH | Length | AIME | Length | AMC | Length | Minerva |Length | Olympiad |Length | Total Avg Length |
22
  |------------------|----------|------------|--------------------|------------------|--------------------|------------------|--------------------|------------------|--------------------|------------------|-----------------|
23
  | Deepseek-R1-7B | 93.60 | 3999 | 55.40 | 13241 | 82.90 | 7461 | 49.79 | 5199 | 58.21 | 8837 | 7747 |
24
  | **DLER-R1-7B** | **94.21 (+0.61%)** | **1634 (-60%)** | **55.62 (+0.22%)** | **3230 (-76%)** | **84.41 (+1.51%)** | **2512 (-0.67%)** | **53.88 (+4.09%)** | **2058 (-61%)** | **60.48 (+2.27%)** | **2592 (-71%)** | **2405 (-69%)** |