README.md

---
language:
- en
base_model: Qwen/Qwen3-8B
library_name: transformers
pipeline_tag: text-generation
tags:
- axolotl
- reasoning
- math
- commonsense
- primeintellect
license: apache-2.0
datasets:
- NousResearch/Hermes-3-Dataset
- QuixiAI/dolphin
model-index:
- name: Delphermes-8B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag
      type: hellaswag
    metrics:
    - type: accuracy
      value: 0.88
      name: Accuracy
  - task:
      type: text-generation
      name: Mathematical Reasoning
    dataset:
      name: GSM8K
      type: gsm8k
    metrics:
    - type: accuracy
      value: 0.89
      name: Accuracy
  - task:
      type: text-generation
      name: Theory of Mind
    dataset:
      name: TheoryPlay
      type: theoryplay
    metrics:
    - type: accuracy
      value: 0.8
      name: Accuracy
---

# Delphermes-8B

This is a merged LoRA model based on Qwen/Qwen3-8B, SFT on Hermes3 + Dolphin Dataset. The model demonstrates strong performance across reasoning, mathematical problem-solving, and commonsense understanding tasks.

## Model Details

- **Base Model**: Qwen/Qwen3-8B
- **Language**: English (en)
- **Library**: transformers
- **Training Method**: LoRA fine-tuning with Axolotl
- **Infrastructure**: 8xB200 Cluster from PrimeIntellect
- **Training Framework**: DeepSpeed Zero2

## Performance

| Benchmark | Score | Description |
|-----------|-------|-------------|
| **HellaSwag** | 88% | Commonsense reasoning and natural language inference |
| **GSM8K** | 89% | Grade school math word problems |
| **TheoryPlay** | 80% | Theory of mind and social reasoning tasks |


## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "justinj92/Delphermes-8B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# Example usage for reasoning tasks
text = "Sarah believes that her keys are in her purse, but they are actually on the kitchen table. Where will Sarah look for her keys?"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(
    **inputs, 
    max_length=200,
    temperature=0.1,
    do_sample=True,
    pad_token_id=tokenizer.eos_token_id
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```

### Chat Format

This model supports the Hermes chat format:

```python
def format_chat(messages):
    formatted = ""
    for message in messages:
        role = message["role"]
        content = message["content"]
        if role == "system":
            formatted += f"<|im_start|>system\n{content}<|im_end|>\n"
        elif role == "user":
            formatted += f"<|im_start|>user\n{content}<|im_end|>\n"
        elif role == "assistant":
            formatted += f"<|im_start|>assistant\n{content}<|im_end|>\n"
    formatted += "<|im_start|>assistant\n"
    return formatted

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Solve this math problem: A store has 45 apples. If they sell 1/3 of them in the morning and 1/5 of the remaining apples in the afternoon, how many apples are left?"}
]

prompt = format_chat(messages)
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=300, temperature=0.1)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
```

## Training Details

- **Training Framework**: Axolotl with DeepSpeed Zero2 optimization
- **Hardware**: 8x NVIDIA B200 GPUs (PrimeIntellect cluster)
- **Base Model**: Qwen/Qwen3-8B
- **Training Method**: Low-Rank Adaptation (LoRA)
- **Dataset**: NousResearch/Hermes-3-Dataset + QuixiAI/dolphin
- **Training Duration**: 28 hours
- **Learning Rate**: 0.0004
- **Batch Size**: 8
- **Sequence Length**: 4096

## Evaluation Methodology

All evaluations were conducted using:
- **HellaSwag**: Standard validation set with 4-way multiple choice accuracy
- **GSM8K**: Test set with exact match accuracy on final numerical answers
- **TheoryPlay**: Validation set with accuracy on theory of mind reasoning tasks

## Limitations

- The model may still struggle with very complex mathematical proofs
- Performance on non-English languages may be limited
- May occasionally generate inconsistent responses in edge cases
- Training data cutoff affects knowledge of recent events

## Ethical Considerations

This model has been trained on curated datasets and should be used responsibly. Users should:
- Verify important information from the model
- Be aware of potential biases in training data
- Use appropriate content filtering for production applications

## Citation

```bibtex
@misc{Delphermes-8B,
  title={Delphermes-8B: A Fine-tuned Language Model for Reasoning Tasks},
  author={[Your Name]},
  year={2025},
  url={https://huggingface.co/justinj92/Delphermes-8B}
}
```

## License

This model is released under the Apache 2.0 license.