mkurman commited on
Commit
ea357bc
·
verified ·
1 Parent(s): 9e4549f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ The Marsh Harrier (MSH) is a language model developed by MedIT Solutions using a
25
  The model shows significant improvements over its predecessors across multiple metrics in the Open PL LLM Leaderboard evaluation framework (0-shot), which is part of the SpeakLeash.org open-science initiative.
26
 
27
  Technical Details:
28
- - Base Models: Speakleash Bielik 11B v2.3 Instruct (https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct) and Bielik 11B v2 (https://huggingface.co/speakleash/Bielik-11B-v2)
29
  - Architecture: Compatible with original Bielik architecture
30
  - Parameter Count: 11 billion parameters
31
  - Special Feature: Utilizes MedIT Solutions' proprietary checkpoint merging technology
@@ -55,4 +55,4 @@ MSH-v1 achieves a higher average score of 71.18% compared to Bielik v2.3's 69.33
55
 
56
  All evaluations were conducted using the Open PL LLM Leaderboard framework (0-shot) as part of the SpeakLeash.org open-science initiative.
57
 
58
- Kudos to the **SpeakLeash** project and **ACK Cyfronet AGH** for their extraordinary work.
 
25
  The model shows significant improvements over its predecessors across multiple metrics in the Open PL LLM Leaderboard evaluation framework (0-shot), which is part of the SpeakLeash.org open-science initiative.
26
 
27
  Technical Details:
28
+ - Base Models: [Speakleash Bielik 11B v2.3 Instruct](https://huggingface.co/speakleash/Bielik-11B-v2.3-Instruct) and [Bielik 11B v2](https://huggingface.co/speakleash/Bielik-11B-v2)
29
  - Architecture: Compatible with original Bielik architecture
30
  - Parameter Count: 11 billion parameters
31
  - Special Feature: Utilizes MedIT Solutions' proprietary checkpoint merging technology
 
55
 
56
  All evaluations were conducted using the Open PL LLM Leaderboard framework (0-shot) as part of the SpeakLeash.org open-science initiative.
57
 
58
+ Kudos to the **[SpeakLeash](https://speakleash.org)** project and **[ACK Cyfronet AGH](https://www.cyfronet.pl/)** for their extraordinary work.