Kybalion-1B-DPO

A 1B-parameter instruct model aligned on top of devwoo/Kybalion-1B (Llama 3.2 1B + CPT + SFT) using Direct Preference Optimization (DPO). The LoRA adapter has been merged into the base weights so this is a standalone instruct model — no PEFT adapter required at inference.

⚠️ Experimental / educational model. Training used conservative hyperparameters, so quality improvements over the base Kybalion-1B are modest. See Limitations for an honest assessment.

Model Details

Item	Value
Base	devwoo/Kybalion-1B (built on Llama 3.2 1B)
Parameters	1.24 B
Precision	BF16
Context length	2048
Tokenizer	Llama 3.2 standard
Chat template	Llama 3.2 (system / user / assistant + `<
Alignment method	DPO (Direct Preference Optimization)
Adapter	LoRA r=16, α=32, all linear → merged
Training framework	HuggingFace trl + peft

Training Recipe

DPO recipe following Chapter 6 (Direct Alignment Algorithms) of Nathan Lambert's RLHF book, with Zephyr hyperparameters.

Item	Value
Dataset	argilla/ultrafeedback-binarized-preferences-cleaned (~60K pairs)
β (KL strength)	0.1
Learning rate	5e-7 (cosine, 10% warmup)
Effective batch size	32 (per-device 8 × grad accum 4)
Epochs	1
Max length	1024 (prompt 512)
Loss type	sigmoid (vanilla DPO)
LoRA targets	q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Optimizer	AdamW
Hardware	NVIDIA A100 40GB (Colab Pro+)
Reference model	Implicit via PEFT adapter toggle (no extra memory)

After training, the LoRA adapter was merged into base weights with merge_and_unload().

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "devwoo/Kybalion-1B-DPO"

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

messages = [
    {"role": "user", "content": "Explain quantum entanglement in simple terms."},
]
input_text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer(input_text, return_tensors="pt").to(model.device)

out = model.generate(
    **inputs,
    max_new_tokens=400,
    temperature=0.7,
    top_p=0.9,
    do_sample=True,
    repetition_penalty=1.15,
    eos_token_id=[tokenizer.eos_token_id, 128009],   # explicitly include <|eot_id|>
    pad_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

💡 Always pass eos_token_id=[..., 128009] at generation time. Llama 3.2's <|eot_id|> token must be registered as a stop token, otherwise the model leaks assistant tokens mid-response and may loop indefinitely.

Limitations & Known Issues

This model has several known limitations. Please read before any production use.

1. Conservative training — limited alignment shift

• lr=5e-7 is the value Zephyr used for full fine-tuning. With LoRA, this is generally too low (typical LoRA DPO uses 5e-6 to 5e-4).
• Trained for only 1 epoch.
• → The output distribution likely did not move far from the base Kybalion-1B.

2. Qualitative evaluation on 10 prompts

We compared base vs. trained responses on 10 prompts (helpfulness / reasoning / coding / advice / creative) using identical sampling (T=0.7, top_p=0.9):

Outcome	Count
Clear trained win	2/10 (instruction following — prompts 5, 7)
Clear base win	3/10 (arithmetic reasoning, factual accuracy)
Tie / both fail	5/10
New factual errors introduced by trained model	2 (sky blue → "aerosols"; Senso-ji → wrongly placed in Kamakura)

→ DPO did not produce the expected uplift.

3. Stop-token leakage and repetition at generation time

• Leaving only the default eos_token_id makes the model ignore <|eot_id|> and keep generating.
• Tokens like assistant, student from the chat template leak into the middle of the response.
• Always pass eos_token_id=[tokenizer.eos_token_id, 128009] and use repetition_penalty >= 1.15.

4. Base-model capability ceiling

• 1B parameters — limited arithmetic and logical reasoning.
• English instruction following is weaker than 7B+ models.
• Korean output quality depends on the baseline Kybalion training distribution; this DPO pass used English UltraFeedback only.

Evaluation

• Automated benchmarks: not run.
• Qualitative: 10-prompt base vs. trained comparison — see Limitations §2.

For proper evaluation, the Tulu 3 eval suite or LM Evaluation Harness are recommended.

Reproduction

A single Colab notebook reproducing this model is available separately (BF16, LoRA r=16, A100 40GB, ~3–5h). For a stronger run, we recommend:

Change	Effect
lr=5e-6 (10×)	Lets DPO actually move the policy
num_epochs=3	Absorbs more of the signal
β=0.05	Loosens the KL constraint slightly
repetition_penalty=1.15 (inference)	Cuts repetition
eos_token_id=[128001, 128009] (inference)	Proper stop-token handling

Citation

@misc{kybalion-1b-dpo,
  title  = {Kybalion-1B-DPO: DPO-aligned Kybalion-1B},
  author = {devwoo},
  year   = {2026},
  url    = {https://huggingface.co/devwoo/Kybalion-1B-DPO},
  note   = {DPO recipe following Tunstall et al. (Zephyr) and Rafailov et al. (DPO)},
}

References:

• Rafailov et al., 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model.
• Tunstall et al., 2023. Zephyr: Direct Distillation of LM Alignment.
• Lambert, 2025. Reinforcement Learning from Human Feedback (book).
• Ouyang et al., 2022. Training Language Models to Follow Instructions with Human Feedback (InstructGPT).

License

Inherited from base: Llama 3.2 Community License.