tperes commited on
Commit
4302f37
·
verified ·
1 Parent(s): b188a8d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -13,7 +13,10 @@ language:
13
  - en
14
  ---
15
 
16
- # Model: palmyra-mini-thinking-a
 
 
 
17
 
18
  ### Model Description
19
 
@@ -24,7 +27,7 @@ language:
24
  - **Parameters:** 1.7 billion
25
 
26
 
27
- ## Model Background
28
 
29
  The palmyra-mini-thinking-a model demonstrates exceptional performance in advanced mathematical reasoning and competitive programming. Its capabilities are highlighted by an outstanding score of 0.886 on the 'MATH500' benchmark, showcasing a robust ability to solve complex mathematical problems. The strength of the model in quantitative challenges is further confirmed by its score of 0.8287 on 'gsm8k (strict-match)', which demonstrates proficiency in multi-step arithmetic reasoning. Additionally, the model proves its aptitude for high-level problem-solving with a score of 0.8 on 'AMC23'. The model also shows strong potential in the coding domain, achieving a score of 0.5631 on 'Codeforces (pass_rate)' and 0.5481 on 'Olympiadbench (extractive_match)', indicating competence in generating correct solutions for programming challenges.
30
 
@@ -135,7 +138,7 @@ As with any language model, there is a potential for generating biased or inaccu
135
 
136
  To cite this model:
137
  ```
138
- @misc{Palmyra-mini,
139
  author = {Writer Engineering team},
140
  title = {{Palmyra-mini: A powerful LLM designed for math and coding}},
141
  howpublished = {\url{https://dev.writer.com}},
 
13
  - en
14
  ---
15
 
16
+ <div align="center">
17
+ <h1>Palmyra-mini</h1>
18
+
19
+ </div>
20
 
21
  ### Model Description
22
 
 
27
  - **Parameters:** 1.7 billion
28
 
29
 
30
+ ## Model Details
31
 
32
  The palmyra-mini-thinking-a model demonstrates exceptional performance in advanced mathematical reasoning and competitive programming. Its capabilities are highlighted by an outstanding score of 0.886 on the 'MATH500' benchmark, showcasing a robust ability to solve complex mathematical problems. The strength of the model in quantitative challenges is further confirmed by its score of 0.8287 on 'gsm8k (strict-match)', which demonstrates proficiency in multi-step arithmetic reasoning. Additionally, the model proves its aptitude for high-level problem-solving with a score of 0.8 on 'AMC23'. The model also shows strong potential in the coding domain, achieving a score of 0.5631 on 'Codeforces (pass_rate)' and 0.5481 on 'Olympiadbench (extractive_match)', indicating competence in generating correct solutions for programming challenges.
33
 
 
138
 
139
  To cite this model:
140
  ```
141
+ @misc{Palmyra-mini-thinking-a,
142
  author = {Writer Engineering team},
143
  title = {{Palmyra-mini: A powerful LLM designed for math and coding}},
144
  howpublished = {\url{https://dev.writer.com}},