GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
The-JDdev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
The-JDdev
Model Tree
Qwen/Qwen2.5-0.5B
Input Modalities
Output Modalities
Supported Functionality
The training data was generated from the Bengali book "ক্লড এআই মাস্টারি" (Claude AI Mastery) using template-based generation covering:
Only assistant tokens are trained (labels set). System and user tokens are masked with -100 to focus learning on response generation rather than prompt memorization.
The assistant is trained to be friendly, patient, and example-driven — inspired by Claude's teaching style. The system prompt instructs:
"তুমি একজন বন্ধুত্বপূর্ণ বাংলা অ্যাসিস্ট্যান্ট। Claude AI বিষয়ে সহজ ভাষায় উদাহরণসহ উত্তর দাও।"
(You are a friendly Bengali assistant. Answer about Claude AI in simple language with examples.)
python
from transformers import AutoTokenizer, AutoModelForCausalLMimport torch model = AutoModelForCausalLM.from_pretrained( "The-JDdev/Qwen2.5-0.5B-Bengali-Claude-Assistant", dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained( "The-JDdev/Qwen2.5-0.5B-Bengali-Claude-Assistant", trust_remote_code=True,) messages = [ {"role": "system", "content": "তুমি একজন বন্ধুত্বপূর্ণ বাংলা অ্যাসিস্ট্যান্ট। Claude AI বিষয়ে সহজ ভাষায় উদাহরণসহ উত্তর দাও।"}, {"role": "user", "content": "Claude কী?"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt")outputs = model.generate( **inputs, max_new_tokens=200, do_sample=True, temperature=0.6, top_p=0.85, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id,)response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(response)See training_metadata.json for full training hyperparameters and statistics.
model.safetensors — Full merged model (bf16, 943MB)adapter_model.safetensors — LoRA adapter only (35MB) — use this with the base model for faster loadingadapter_config.json — LoRA configurationtokenizer.json — Tokenizertraining_metadata.json — Training hyperparametersApache 2.0 (inherited from Qwen2.5)
from transformers import AutoTokenizer, AutoModelForCausalLMimport torch model = AutoModelForCausalLM.from_pretrained( "The-JDdev/Qwen2.5-0.5B-Bengali-Claude-Assistant", dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained( "The-JDdev/Qwen2.5-0.5B-Bengali-Claude-Assistant", trust_remote_code=True,) messages = [ {"role": "system", "content": "তুমি একজন বন্ধুত্বপূর্ণ বাংলা অ্যাসিস্ট্যান্ট। Claude AI বিষয়ে সহজ ভাষায় উদাহরণসহ উত্তর দাও।"}, {"role": "user", "content": "Claude কী?"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt")outputs = model.generate( **inputs, max_new_tokens=200, do_sample=True, temperature=0.6, top_p=0.85, repetition_penalty=1.2, pad_token_id=tokenizer.eos_token_id,)response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(response)