Update README.md
Browse files
README.md
CHANGED
@@ -24,9 +24,9 @@ model-index:
|
|
24 |
- name: GSM8k (0-Shot)
|
25 |
type: GSM8k (0-Shot)
|
26 |
value: 31.61%
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
co2_eq_emissions:
|
31 |
emissions: 49600
|
32 |
source: "https://mlco2.github.io/impact#compute"
|
@@ -46,7 +46,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl) & Unsloth.
|
|
46 |
| Model | GSM8k 0-Shot | GSM8k Few-Shot |
|
47 |
|------------------------------------------|------------------|-------------------|
|
48 |
| Mistral-7B-v0.1 | 10 | 41 |
|
49 |
-
| Llama-3.2-3B-Instruct-Thinking | 31.61 |
|
50 |
|
51 |
|
52 |
## Training procedure
|
|
|
24 |
- name: GSM8k (0-Shot)
|
25 |
type: GSM8k (0-Shot)
|
26 |
value: 31.61%
|
27 |
+
- name: GSM8k (Few-Shot)
|
28 |
+
type: GSM8k (Few-Shot)
|
29 |
+
value: 54.51%
|
30 |
co2_eq_emissions:
|
31 |
emissions: 49600
|
32 |
source: "https://mlco2.github.io/impact#compute"
|
|
|
46 |
| Model | GSM8k 0-Shot | GSM8k Few-Shot |
|
47 |
|------------------------------------------|------------------|-------------------|
|
48 |
| Mistral-7B-v0.1 | 10 | 41 |
|
49 |
+
| Llama-3.2-3B-Instruct-Thinking | 31.61 | 54.51 |
|
50 |
|
51 |
|
52 |
## Training procedure
|