Total runs:
7.4K
Run Growth:
0
Growth Rate:
0.00%
Sponsored by
PostMcpAi
Finnish-NLP / Ahma-2-4B-Instruct
Model's Last Updated: November 25 2025
text-generation
Introduction of Ahma-2-4B-Instruct
Model Details of Ahma-2-4B-Instruct
- Base Model: Gemma-3-4b-pt
- Language: Finnish (fi)
-
Training Methodology:
- Step 1: Continued Pretraining (CP) Mix of English, Finnish and Code-switching data
- Step 2: Supervised Fine-Tuning (SFT) Mostly Finnish
- Step 3: Direct Preference Optimization (DPO) Mostly Finnish
Running this model
More info coming later
Pretraining
More info coming later
Finetuning
More info coming later
Evaluation results
MTBench Finnish
This Ahma-Gemma-3-4B-Instruct-v1.0 model was primarily evaluated using MTBench Finnish by LumiOpen
Single-turn results:
| Benchmark | Ahma 3B base (instruct prompt format) | Ahma 7B Instruct (instruct prompt format) | Ahma-Gemma-3-4B-Instruct-v1.0 |
|---|---|---|---|
| Coding | 1.00 | 1.00 | 4.2 |
| Extraction | 1.30 | 3.00 | 7.3 |
| Humanities | 6.20 | 8.00 | 8.9 |
| Math | 3.20 | 2.90 | 6.1 |
| Reasoning | 4.60 | 5.70 | 4.8 |
| Roleplay | 6.50 | 7.20 | 7.7 |
| STEM | 5.95 | 7.30 | 9.9 |
| Writing | 9.00 | 8.80 | 9.2 |
| Overall Average | 4.72 | 5.50 | 7.26 |
Multi-turn results:
| Benchmark | Ahma 3B Instruct (instruct prompt format) | Ahma 7B Instruct (instruct prompt format) | Ahma-Gemma-3-4B-Instruct-v1.0 | Poro 34B Chat | Poro-2-8B-Instruct |
|---|---|---|---|---|---|
| Coding | 1.00 | 1.05 | 4.35 | 3.70 | ? |
| Extraction | 1.15 | 2.65 | 6.55 | 6.37 | ? |
| Humanities | 6.20 | 7.85 | 6.55 | 9.25 | ? |
| Math | 2.70 | 2.40 | 4.80 | 1.20 | ? |
| Reasoning | 3.50 | 4.50 | 4.40 | 4.35 | ? |
| Roleplay | 6.40 | 6.60 | 7.26 | 7.35 | ? |
| STEM | 4.78 | 5.40 | 8.80 | 7.80 | ? |
| Writing | 6.65 | 6.25 | 7.6 | 8.50 | ? |
| Overall Average | 4.05 | 4.59 | 6.57 | 6.06 | 6.75 |
As we can see, the Ahma-Gemma-3-4B-Instruct-v1.0 model improves upon our previous model generation. We have already started to work on the datasets and methods to improve this model/scale to bigger models
Acknowledgements
This project would not have been possible without compute generously provided by Google through the TPU Research Cloud .
Datacrunch/Verda for sponsoring us some compute for Finetuning: HF Org ( https://huggingface.co/datacrunch ) Website: ( https://verda.com/ )
Team Members
-
Aapo Tanskanen,
Hugging Face profile
,
LinkedIn profile
- Initial parts in pretraining in our continued pretraining journey
-
Rasmus Toivanen,
Hugging Face profile
,
LinkedIn profile
- Pretraining this model, post-training this model, gathering datasets, running evaluations
Other notable supporters on this journey
- Ari Kouhia, Hugging Face profile for helpful comments on our WA group and helping in synthetic data generation
- Heikki Saxén, Hugging Face profile for helpful comments on our WA group and also for finetuning DentalQA models on top of this model
- Mikko Hällfors, Hugging Face profile for helpful comments on our WA group and helping in synthetic data generation
Feel free to contact us for more details 🤗
Runs of Finnish-NLP Ahma-2-4B-Instruct on huggingface.co
108
Total runs
0
24-hour runs
0
3-day runs
-9
7-day runs
-67
30-day runs
More Information About Ahma-2-4B-Instruct huggingface.co Model
Url of Ahma-2-4B-Instruct
Ahma-2-4B-Instruct huggingface.co Url
Provider of Ahma-2-4B-Instruct huggingface.co
Other API from Finnish-NLP
Updated:April 08 2025
Total runs:
5.6K
Run Growth:
0
Growth Rate:
0.00%
Total runs:
1.1K
Run Growth:
1.0K
Growth Rate:
96.32%
Total runs:
987
Run Growth:
-1.4K
Growth Rate:
-142.35%
Total runs:
813
Run Growth:
779
Growth Rate:
96.17%
Total runs:
796
Run Growth:
767
Growth Rate:
96.97%
Total runs:
490
Run Growth:
430
Growth Rate:
88.48%
Total runs:
482
Run Growth:
-62
Growth Rate:
-12.86%
Total runs:
381
Run Growth:
351
Growth Rate:
93.10%
Total runs:
270
Run Growth:
0
Growth Rate:
0.00%
Total runs:
246
Run Growth:
143
Growth Rate:
58.13%
Total runs:
96
Run Growth:
0
Growth Rate:
0.00%
Total runs:
82
Run Growth:
60
Growth Rate:
73.17%
Total runs:
61
Run Growth:
52
Growth Rate:
85.25%
Total runs:
49
Run Growth:
24
Growth Rate:
54.55%
Total runs:
48
Run Growth:
26
Growth Rate:
54.17%
Total runs:
47
Run Growth:
0
Growth Rate:
0.00%
Total runs:
44
Run Growth:
14
Growth Rate:
35.90%
Total runs:
33
Run Growth:
14
Growth Rate:
42.42%
Total runs:
31
Run Growth:
4
Growth Rate:
12.90%
Total runs:
29
Run Growth:
-105
Growth Rate:
-362.07%
Total runs:
28
Run Growth:
0
Growth Rate:
0.00%
Total runs:
27
Run Growth:
0
Growth Rate:
0.00%
Total runs:
27
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
26
Run Growth:
0
Growth Rate:
0.00%
Total runs:
23
Run Growth:
20
Growth Rate:
86.96%
Total runs:
21
Run Growth:
9
Growth Rate:
42.86%
Total runs:
20
Run Growth:
0
Growth Rate:
0.00%
Total runs:
20
Run Growth:
7
Growth Rate:
35.00%
Total runs:
19
Run Growth:
0
Growth Rate:
0.00%
Total runs:
19
Run Growth:
-23
Growth Rate:
-121.05%
Total runs:
18
Run Growth:
0
Growth Rate:
0.00%
Total runs:
16
Run Growth:
0
Growth Rate:
0.00%
Total runs:
16
Run Growth:
10
Growth Rate:
62.50%
Total runs:
15
Run Growth:
0
Growth Rate:
0.00%
Total runs:
15
Run Growth:
0
Growth Rate:
0.00%
Total runs:
15
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12
Run Growth:
0
Growth Rate:
0.00%
Total runs:
12
Run Growth:
4
Growth Rate:
33.33%
Total runs:
11
Run Growth:
5
Growth Rate:
45.45%
Total runs:
10
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10
Run Growth:
0
Growth Rate:
0.00%
Total runs:
10
Run Growth:
5
Growth Rate:
50.00%
Total runs:
9
Run Growth:
0
Growth Rate:
0.00%
Total runs:
6
Run Growth:
-2
Growth Rate:
-33.33%
Total runs:
5
Run Growth:
0
Growth Rate:
0.00%
Total runs:
5
Run Growth:
0
Growth Rate:
0.00%
Total runs:
3
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%