GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Slavik2009
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Slavik2009
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Model | Task |
|---|---|
| TurkmenChat-3B | 💬 Conversational LLM |
| whisper-large-v3-turbo-tk | 🎙️ Speech-to-text |
Base-vs-finetuned comparison is done by toggling the LoRA adapter on the same model with the same prompts and greedy decoding — a controlled, reproducible A/B.
| Metric | Qwen/Qwen2.5-3B-Instruct (base) | TurkmenChat-3B | Delta |
|---|---|---|---|
| FLORES-200 en->tk chrF++ (200 sent.) | 14.40 | 15.20 | +0.8 |
| Held-out perplexity (2% split) | - | n/a | - |
Full numbers: benchmark_results.json. Sample
translations: flores_translations_sample.json.
Salam, näme habar?
Salam aleykum! Myn name is John and I am doing great. How about you?
Aşgabat hakynda gysgaça gürrüň ber.
Aşgabat (previously known as Stanyazovka) is the capital and largest city of Turkmenchat, a republic in Central Asia. It is located near the borders with Uzbekistan and Kazakhstan. The city has a population of around 600,000 people.
1-den 10-a çenli sanap ber.
1,2,3,4,5,6,7,8,9,10
Plow nädip bişirmeli?
Yes, a plow is used to till the soil and prepare it for planting crops. It has two parts: the blade that cuts into the ground and the coulter which cuts into the soil at an angle. The plow is pulled by a tractor or other machinery and can be adjusted in order to achieve the desired depth of cut.
python
from transformers import pipelinechat = pipeline("text-generation", model="Slavik2009/TurkmenChat-3B")messages = [{"role": "user", "content": "Salam! Aşgabat hakynda gürrüň ber."}]print(chat(messages, max_new_tokens=200)[0]["generated_text"][-1]["content"])text
ollama run hf.co/Slavik2009/TurkmenChat-3B-GGUF:Q4_K_MBuilt for casual Turkmen conversation, Q&A and en->tk translation. Not tuned for factual reliability, safety-critical use, code, or long documents. It can hallucinate — verify important facts. Latin-script Turkmen only.
bibtex
@misc{turkmenchat3b, title = {TurkmenChat-3B: an open conversational LLM for Turkmen}, author = {Slavik2009}, year = {2026}, url = {https://huggingface.co/Slavik2009/TurkmenChat-3B}}from transformers import pipelinechat = pipeline("text-generation", model="Slavik2009/TurkmenChat-3B")messages = [{"role": "user", "content": "Salam! Aşgabat hakynda gürrüň ber."}]print(chat(messages, max_new_tokens=200)[0]["generated_text"][-1]["content"])@misc{turkmenchat3b, title = {TurkmenChat-3B: an open conversational LLM for Turkmen}, author = {Slavik2009}, year = {2026}, url = {https://huggingface.co/Slavik2009/TurkmenChat-3B}}