Tom-Qwen-7B-Instruct

A fine-tuned 7B parameter model specialized for step-by-step instruction and conversation.

Model Details

This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct using the Unsloth framework with LoRA (Low-Rank Adaptation) for efficient training.

• Developed by: theprint
• Model type: Causal Language Model (Fine-tuned with LoRA)
• Language: en
• License: apache-2.0
• Base model: Qwen/Qwen2.5-7B-Instruct
• Fine-tuning method: LoRA with rank 128

GGUF Quantized Versions

You can find quantized gguf versions of this model in the /gguf-folder.

Quantized GGUF versions are in the gguf/ directory for use with llama.cpp:

• Tom-Qwen-7B-Instruct-f16.gguf (14531.9 MB) - 16-bit float (original precision, largest file)
• Tom-Qwen-7B-Instruct-q3_k_m.gguf (3632.0 MB) - 3-bit quantization (medium quality)
• Tom-Qwen-7B-Instruct-q4_k_m.gguf (4466.1 MB) - 4-bit quantization (medium, recommended for most use cases)
• Tom-Qwen-7B-Instruct-q5_k_m.gguf (5192.6 MB) - 5-bit quantization (medium, good quality)
• Tom-Qwen-7B-Instruct-q6_k.gguf (5964.5 MB) - 6-bit quantization (high quality)
• Tom-Qwen-7B-Instruct-q8_0.gguf (7723.4 MB) - 8-bit quantization (very high quality)

Intended Use

Conversation, brainstorming, and general instruction following

Training Details

Training Data

Synthesized data set created specifically for this, focused on practical tips and well being.

• Dataset: theprint/Tom-4.2k-alpaca
• Format: alpaca

Training Procedure

• Training epochs: 3
• LoRA rank: 128
• Learning rate: 0.0002
• Batch size: 4
• Framework: Unsloth + transformers + PEFT
• Hardware: NVIDIA RTX 5090

Usage

from unsloth import FastLanguageModel
import torch

# Load model and tokenizer
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name="theprint/Tom-Qwen-7B-Instruct",
    max_seq_length=4096,
    dtype=None,
    load_in_4bit=True,
)

# Enable inference mode
FastLanguageModel.for_inference(model)

# Example usage
inputs = tokenizer(["Your prompt here"], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Alternative Usage (Standard Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "theprint/Tom-Qwen-7B-Instruct",
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("theprint/Tom-Qwen-7B-Instruct")

# Example usage
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Your question here"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True)
outputs = model.generate(inputs, max_new_tokens=256, temperature=0.7, do_sample=True)
response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
print(response)

Using with llama.cpp

# Download a quantized version (q4_k_m recommended for most use cases)
wget https://huggingface.co/theprint/Tom-Qwen-7B-Instruct/resolve/main/gguf/Tom-Qwen-7B-Instruct-q4_k_m.gguf

# Run with llama.cpp
./llama.cpp/main -m Tom-Qwen-7B-Instruct-q4_k_m.gguf -p "Your prompt here" -n 256

Limitations

May hallucinate or provide incorrect information. Not suitable for critical decision making.

Citation

If you use this model, please cite:

@misc{tom_qwen_7b_instruct,
  title={Tom-Qwen-7B-Instruct: Fine-tuned Qwen/Qwen2.5-7B-Instruct},
  author={theprint},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/theprint/Tom-Qwen-7B-Instruct}
}

Acknowledgments

• Base model: Qwen/Qwen2.5-7B-Instruct
• Training dataset: theprint/Tom-4.2k-alpaca
• Fine-tuning framework: Unsloth
• Quantization: llama.cpp