sallumallu
commited on
Commit
•
8317b93
1
Parent(s):
43a319b
Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,24 @@ tags: []
|
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
|
|
10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
|
12 |
## Model Details
|
13 |
|
|
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
10 |
+
Base Model meta-llama/Llama-3.2-1B-Instruct results:
|
11 |
|
12 |
+
hf (pretrained=meta-llama/Llama-3.2-1B-Instruct,dtype=float), gen_kwargs: (None), limit: None, num_fewshot: None,
|
13 |
+
batch_size: auto:4 (32,64,64,64,64)
|
14 |
+
|
15 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
16 |
+
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|
17 |
+
|hellaswag| 1|none | 0|acc |↑ |0.4520|± |0.0050|
|
18 |
+
| | |none | 0|acc_norm|↑ |0.6078|± |0.0049|
|
19 |
+
|
20 |
+
Fine Tuned meta-llama/Llama-3.2-1B-Instruct using a small sample of https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k:
|
21 |
+
|
22 |
+
hf (pretrained=./merged_model,dtype=float), gen_kwargs: (None), limit: None, num_fewshot: None, batch_size: auto:4 (32,64,64,64,64)
|
23 |
+
|
24 |
+
| Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
|
25 |
+
|---------|------:|------|-----:|--------|---|-----:|---|-----:|
|
26 |
+
|hellaswag| 1|none | 0|acc |↑ |0.4509|± |0.0050|
|
27 |
+
| | |none | 0|acc_norm|↑ |0.6071|± |0.0049|
|
28 |
|
29 |
## Model Details
|
30 |
|