You can deploy this model and start earning money today!

Quardo/
TR-Qwen2-7B-003-241201

Name: TR-Qwen2-7B-003-241201
Availability: InStock

Quardo/wikipedia-turkish-qa

Qwen/Qwen2-7B-Instruct

finetune

Views

No views yet

TR-Qwen2-7B-003-241201

The third generation of TR-Qwen2, fine-tuned with the largest token count so far.

7B-001: Fine-tuned on 12 million tokens.
1.5B-002: Fine-tuned on 2 million tokens.
7B-003 (this version): Fine-tuned on 103 million tokens, or effectively 25.75 million tokens across 4 epochs (compared to just 1 epoch for the earlier versions).

The model has been fine-tuned with this system prompt only: Yardımsever bir yapay zeka asistanısın. Still the fine-tuning service is the same: Together.ai

Note: This version may perform poorly with mathematical tasks, as its fine-tuning is based on Wikipedia-based data. Expect stronger cultural understanding instead (unlike 002) with actual capabilities to talk normally (unlike 001).

Note 2: This version of the model expects questions, not converstions like "Hello" ("merhaba"), to use it fully it would be better to ask it questions like "What is the capital of Turkey?" ("Türkiye'nin başkenti neresidir?")

Generated responses: (Q8_0 were used, temp: .1, top-p: .05, with system prompt, on TR-Qwen2 space)

Bir haftada kaç saat vardır?

Bir hafta 168 saatlikdır.

Işık hızı saniyede kaç kilometredir?

300,000 km/s

Türkiye’nin başkenti neresidir ve hangi yılda başkent ilan edilmiştir?

Ankara, 1923 yılında başkent ilan edilmiştir.

Bir metrik ton kaç kilogramdır?

1000 kg'dır.

Dünyanın en yüksek dağı hangisidir ve yüksekliği ne kadardır?

Everest Dağı, 8.848 metre yüksekliğindedir.

Quardo/TR-Qwen2-7B-003-241201

TR-Qwen2-7B-003-241201

Generated responses: (Q8_0 were used, temp: .1, top-p: .05, with system prompt, on TR-Qwen2 space)

Quardo/
TR-Qwen2-7B-003-241201