Quantization made by Richard Erkhov.
NeuralMarcoro14-7B - GGUF
- Model creator: https://huggingface.co/mlabonne/
- Original model: https://huggingface.co/mlabonne/NeuralMarcoro14-7B/
| Name | Quant method | Size |
|---|---|---|
| NeuralMarcoro14-7B.Q2_K.gguf | Q2_K | 2.53GB |
| NeuralMarcoro14-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| NeuralMarcoro14-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| NeuralMarcoro14-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| NeuralMarcoro14-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| NeuralMarcoro14-7B.Q3_K.gguf | Q3_K | 3.28GB |
| NeuralMarcoro14-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| NeuralMarcoro14-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| NeuralMarcoro14-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| NeuralMarcoro14-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| NeuralMarcoro14-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| NeuralMarcoro14-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| NeuralMarcoro14-7B.Q4_K.gguf | Q4_K | 4.07GB |
| NeuralMarcoro14-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| NeuralMarcoro14-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| NeuralMarcoro14-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| NeuralMarcoro14-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| NeuralMarcoro14-7B.Q5_K.gguf | Q5_K | 4.78GB |
| NeuralMarcoro14-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| NeuralMarcoro14-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| NeuralMarcoro14-7B.Q6_K.gguf | Q6_K | 5.53GB |
| NeuralMarcoro14-7B.Q8_0.gguf | Q8_0 | 7.17GB |
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
🏆 Evaluation
Open LLM Leaderboard
Nous
| Model | AGIEval | GPT4ALL | TruthfulQA | Bigbench | Average |
|---|---|---|---|---|---|
| NeuralMarcoro14-7B | 44.59 | 76.17 | 65.94 | 46.9 | 58.4 |
| Marcoro14-7B-slerp | 44.66 | 76.24 | 64.15 | 45.64 | 57.67 |
| Change | -0.07 | -0.07 | +1.79 | +1.26 | +0.73 |
🧩 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"])