---
library_name: transformers
tags:
- dpo
- mistral
- finetune
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
language:
- en
---

# NeuralHermes 2.5 - Mistral 7B

NeuralHermes-2.5 was created by fine-tuning OpenHermes-2.5 using a RLHF-like technique: Direct Preference Optimization (DPO) using the `Intel/orca_dpo_pairs` dataset.

## Usage

You can also run this model using the following code:

```python
import transformers
from transformers import AutoTokenizer

# Format prompt
message = [
    {"role": "system", "content": "You are a helpful assistant chatbot."},
    {"role": "user", "content": "What is a Large Language Model?"}
]
tokenizer = AutoTokenizer.from_pretrained(new_model)
prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)

# Create pipeline
pipeline = transformers.pipeline(
    "text-generation",
    model=new_model,
    tokenizer=tokenizer
)

# Generate text
sequences = pipeline(
    prompt,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    num_return_sequences=1,
    max_length=200,
)
print(sequences[0]['generated_text'])
```

## Training hyperparameters

**LoRA**:
* r=16
* lora_alpha=16
* lora_dropout=0.05
* bias="none"
* task_type="CAUSAL_LM"
* target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']

**Training arguments**:
* per_device_train_batch_size=4
* gradient_accumulation_steps=4
* gradient_checkpointing=True
* learning_rate=5e-5
* lr_scheduler_type="cosine"
* max_steps=200
* optim="paged_adamw_32bit"
* warmup_steps=100

**DPOTrainer**:
* beta=0.1
* max_prompt_length=1024
* max_length=1536