GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ErkaMarka
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ErkaMarka
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen 2.5 7B fine-tuned on Mongolian news data for chatbot
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load tokenizertokenizer = AutoTokenizer.from_pretrained("ErkaMarka/mongolian-qwen-7b-chatbot") # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-7B-Instruct", torch_dtype=torch.float16, device_map="auto") # Resize embeddings for new tokensbase_model.resize_token_embeddings(len(tokenizer)) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "ErkaMarka/mongolian-qwen-7b-chatbot") # Generatemessages = [{"role": "user", "content": "Монгол улсын нийслэл хот юу вэ?"}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=150)print(tokenizer.decode(outputs[0], skip_special_tokens=True))Evaluated on 100 Mongolian Q&A pairs using BLEU score.
Apache 2.0
text
@misc{mongolian_qwen_7b_chatbot}, author = {Your Name}, title = {mongolian-qwen-7b-chatbot}, year = {2024}, publisher = {Hugging Face}, url = {https://huggingface.co/ErkaMarka/mongolian-qwen-7b-chatbot}}from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load tokenizertokenizer = AutoTokenizer.from_pretrained("ErkaMarka/mongolian-qwen-7b-chatbot") # Load base modelbase_model = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-7B-Instruct", torch_dtype=torch.float16, device_map="auto") # Resize embeddings for new tokensbase_model.resize_token_embeddings(len(tokenizer)) # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "ErkaMarka/mongolian-qwen-7b-chatbot") # Generatemessages = [{"role": "user", "content": "Монгол улсын нийслэл хот юу вэ?"}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=150)print(tokenizer.decode(outputs[0], skip_special_tokens=True))@misc{mongolian_qwen_7b_chatbot}, author = {Your Name}, title = {mongolian-qwen-7b-chatbot}, year = {2024}, publisher = {Hugging Face}, url = {https://huggingface.co/ErkaMarka/mongolian-qwen-7b-chatbot}}