mlabonne_-_NeuralMarcoro14-7B-4bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NeuralMarcoro14-7B - bnb 4bits

• Model creator: https://huggingface.co/mlabonne/
• Original model: https://huggingface.co/mlabonne/NeuralMarcoro14-7B/

Original model description:

license: cc-by-nc-4.0 tags:

• mlabonne/Marcoro14-7B-slerp
• dpo
• rlhf
• merge
• mergekit
• lazymergekit datasets:
• mlabonne/chatml_dpo_pairs base_model: mlabonne/Marcoro14-7B-slerp model-index:
• name: NeuralMarcoro14-7B results:
  • task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics:
    • type: acc_norm value: 71.42 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics:
    • type: acc_norm value: 87.59 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics:
    • type: acc value: 64.84 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics:
    • type: mc2 value: 65.64 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics:
    • type: acc value: 81.22 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard
  • task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics:
    • type: acc value: 70.74 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralMarcoro14-7B name: Open LLM Leaderboard

---

NeuralMarcoro14-7B

This is a DPO fine-tuned version of mlabonne/Marcoro14-7B-slerp using the chatml_dpo_pairs preference dataset. It improves the performance of the model on Nous benchmark suite and the Open LLM Benchmark.

It is currently the best-performing 7B LLM on the Open LLM Leaderboard (08/01/24).

You can try it out in this Space (GGUF Q4_K_M).

⚡ Quantized models

• GGUF: https://huggingface.co/mlabonne/NeuralMarcoro14-7B-GGUF

🏆 Evaluation

Open LLM Leaderboard

Nous

🧩 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

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/NeuralMarcoro14-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])