---
license: apache-2.0
library_name: transformers
base_model:
- nbeerbower/flammen15-mistral-7B
datasets:
- jondurbin/gutenberg-dpo-v0.1
model-index:
- name: flammen15-gutenberg-DPO-v1-7B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 47.98
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 32.67
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 6.72
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 4.59
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 12.53
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 24.29
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=flammenai/flammen15-gutenberg-DPO-v1-7B
      name: Open LLM Leaderboard
---

![image/png](https://huggingface.co/nbeerbower/flammen13X-mistral-7B/resolve/main/flammen13x.png)

# flammen15-gutenberg-DPO-v1-7B

A Mistral 7B LLM built from merging pretrained models and finetuning on [Jon Durbin](https://huggingface.co/jondurbin)'s [Gutenberg DPO set](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1). Flammen specializes in exceptional character roleplay, creative writing, and general intelligence

### Method

Finetuned using an A100 on Google Colab. (plz give more gpu)

[Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne)

### Configuration

LoRA, model, and training settings:

```python
# LoRA configuration
peft_config = LoraConfig(
    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']
)

# Model to fine-tune
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    load_in_4bit=True
)
model.config.use_cache = False

# Reference model
ref_model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    load_in_4bit=True
)

# Training arguments
training_args = TrainingArguments(
    per_device_train_batch_size=2,
    gradient_accumulation_steps=2,
    gradient_checkpointing=True,
    learning_rate=2e-5,
    lr_scheduler_type="cosine",
    max_steps=200,
    save_strategy="no",
    logging_steps=1,
    output_dir=new_model,
    optim="paged_adamw_32bit",
    warmup_steps=100,
    bf16=True,
    report_to="wandb",
)

# Create DPO trainer
dpo_trainer = DPOTrainer(
    model,
    ref_model,
    args=training_args,
    train_dataset=dataset,
    tokenizer=tokenizer,
    peft_config=peft_config,
    beta=0.1,
    max_prompt_length=1024,
    max_length=1536,
    force_use_ref_model=True
)

# Fine-tune model with DPO
dpo_trainer.train()
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_flammenai__flammen15-gutenberg-DPO-v1-7B)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |21.46|
|IFEval (0-Shot)    |47.98|
|BBH (3-Shot)       |32.67|
|MATH Lvl 5 (4-Shot)| 6.72|
|GPQA (0-shot)      | 4.59|
|MuSR (0-shot)      |12.53|
|MMLU-PRO (5-shot)  |24.29|