from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig

base_model = AutoModelForCausalLM.from_pretrained(
 "Qwen/Qwen2.5-7B",
 quantization_config=BitsAndBytesConfig(
 load_in_4bit=True,
 ),
)
model = PeftModel.from_pretrained(base_model, "OsakanaTeishoku/Qwen2.5-7B-axolotl-sft-v0.1")
tokenizer = AutoTokenizer.from_pretrained("OsakanaTeishoku/Qwen2.5-7B-axolotl-sft-v0.1")

from transformers import TextStreamer

streamer = TextStreamer(
 tokenizer,
 skip_prompt=False, 
 skip_special_tokens=False, 
)

prompt = "あなたは何者ですか"
messages = [
 {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
 {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
 messages,
 tokenize=False,
 add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
 **model_inputs,
 max_new_tokens=512,
 streamer=streamer,
 eos_token_id=tokenizer.eos_token_id,
 pad_token_id=tokenizer.eos_token_id,
)

👁 Built with Axolotl

custom_model_name

This model is a fine-tuned version of Qwen/Qwen2.5-7B on the Aratako/Magpie-Tanuki-8B-annotated-96k dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 2
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 1.0

Training results

Framework versions

• PEFT 0.15.1
• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1

Base model

Qwen/Qwen2.5-7B

(531)

3 items • Updated Apr 19, 2025