metadata

language:
  - en
license: apache-2.0
tags:
  - mistral
  - instruct
  - finetune
  - chatml
  - gpt4
  - synthetic data
  - distillation
  - dpo
  - rlhf
datasets:
  - Intel/orca_dpo_pairs
base_model: teknium/OpenHermes-2.5-Mistral-7B

Credits: Maxime Labonne https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac

(With minor alterations)

NeuralHermes 2.5 - Mistral 7B

NeuralHermes is based on the teknium/OpenHermes-2.5-Mistral-7B model that has been further fine-tuned with Direct Preference Optimization (DPO) using the Intel/orca_dpo_pairs dataset. .

Usage

You can run this model using the following code:

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=2 # Changed from 4
gradient_accumulation_steps=4
gradient_checkpointing=True
learning_rate=2e-5 # Changed from 5e-5
lr_scheduler_type="cosine"
max_steps=250 # Changed from 200
optim="paged_adamw_32bit"
warmup_steps=100

DPOTrainer:

beta=0.1
max_prompt_length=1024
max_length=1536