anakin87 commited on
Commit
e5e5316
1 Parent(s): ef6ab66

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -1
README.md CHANGED
@@ -10,10 +10,22 @@ license: llama3
10
  language:
11
  - it
12
  ---
13
- # merge
14
 
15
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  ## Merge Details
18
  ### Merge Method
19
 
 
10
  language:
11
  - it
12
  ---
13
+ # Llama-3-8b-ita-slerp
14
 
15
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
16
 
17
+ I tried to merge two of the best Italian LLMs using Mergekit. The results are acceptable, but I could not improve on the best existing model.
18
+
19
+ ## Evaluation
20
+
21
+ For a detailed comparison of model performance, check out the [Leaderboard for Italian Language Models](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard).
22
+
23
+ Here's a breakdown of the performance metrics:
24
+
25
+ | Metric | hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average |
26
+ |:----------------------------|:----------------------|:----------------|:---------------------|:--------|
27
+ | **Accuracy Normalized** | 0.6879 | 0.5714 | 0.5732 | 0.6109 |
28
+
29
  ## Merge Details
30
  ### Merge Method
31