Views
No views yet
### Maelekezo:
{query}
### Jibu:
<Leave new line for model to respond> 1# Load model directly
2from transformers import AutoTokenizer, AutoModelForCausalLM
3
4tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2")
5model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2", device_map="auto")
6query = "Nipe maagizo ya kutengeneza mkate wa mandizi"
7text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200, do_sample=True, repetition_penalty=1.1)
8output = text_gen(f"### Maelekezo:\n{query}\n### Jibu:\n")
9print(output[0]['generated_text'])
10
11
12"""
13 Maagizo ya kutengeneza mkate wa mandazi:
141. Preheat tanuri hadi 375°F (190°C).
152. Paka sufuria ya uso na siagi au jotoa sufuria.
163. Katika bakuli la chumvi, ongeza viungo vifuatavyo: unga, sukari ya kahawa, chumvi, mdalasini, na unga wa kakao.
17Koroga mchanganyiko pamoja na mbegu za kikombe 1 1/2 za mtindi wenye jamii na hatua ya maji nyepesi.
184. Kando ya uwanja, changanya zaini ya yai 2
19"""| Metric | Value |
|---|---|
| Avg. | 54.25 |
| AI2 Reasoning Challenge (25-Shot) | 55.20 |
| HellaSwag (10-Shot) | 78.22 |
| MMLU (5-Shot) | 50.30 |
| TruthfulQA (0-shot) | 57.08 |
| Winogrande (5-shot) | 73.24 |
| GSM8k (5-shot) | 11.45 |