Qwen2.5-3B Finetune (Merged)

This is a full merged checkpoint of the fine-tuned Qwen2.5-3B-Instruct model.

Model Details

• Base Model: Qwen/Qwen2.5-3B-Instruct
• Architecture: Qwen2ForCausalLM (36 hidden layers, 16 attention heads, 2 key-value heads)
• Parameters: ~3.09B parameters
• Precision: bfloat16
• Context Length: 32,768 (rope base 1,000,000)

Quick Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "gradients-io-tournaments/qwen2.5-3b-finetune-upwork1"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
]

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=256)
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)
print(response)