Quantization made by Richard Erkhov.
NeuralDaredevil-7B - GGUF
- Model creator: https://huggingface.co/mlabonne/
- Original model: https://huggingface.co/mlabonne/NeuralDaredevil-7B/
Name | Quant method | Size |
---|---|---|
NeuralDaredevil-7B.Q2_K.gguf | Q2_K | 2.53GB |
NeuralDaredevil-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
NeuralDaredevil-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
NeuralDaredevil-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
NeuralDaredevil-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
NeuralDaredevil-7B.Q3_K.gguf | Q3_K | 3.28GB |
NeuralDaredevil-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
NeuralDaredevil-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
NeuralDaredevil-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
NeuralDaredevil-7B.Q4_0.gguf | Q4_0 | 3.83GB |
NeuralDaredevil-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
NeuralDaredevil-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
NeuralDaredevil-7B.Q4_K.gguf | Q4_K | 4.07GB |
NeuralDaredevil-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
NeuralDaredevil-7B.Q4_1.gguf | Q4_1 | 4.24GB |
NeuralDaredevil-7B.Q5_0.gguf | Q5_0 | 4.65GB |
NeuralDaredevil-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
NeuralDaredevil-7B.Q5_K.gguf | Q5_K | 4.78GB |
NeuralDaredevil-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
NeuralDaredevil-7B.Q5_1.gguf | Q5_1 | 5.07GB |
NeuralDaredevil-7B.Q6_K.gguf | Q6_K | 5.53GB |
Original model description:
license: cc-by-nc-4.0 tags: - merge - mergekit - lazymergekit - dpo - rlhf - mlabonne/example base_model: mlabonne/Daredevil-7B model-index: - name: NeuralDaredevil-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: 69.88 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-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: 87.62 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-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: 65.12 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-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: 66.85 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-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: 82.08 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-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: 73.16 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/NeuralDaredevil-7B name: Open LLM Leaderboard
NeuralDaredevil-7B
NeuralDaredevil-7B is a DPO fine-tune of mlabonne/Daredevil-7B using the argilla/distilabel-intel-orca-dpo-pairs preference dataset and my DPO notebook from this article.
Thanks Argilla for providing the dataset and the training recipe here. πͺ
π Evaluation
Nous
The evaluation was performed using LLM AutoEval on Nous suite.
Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
---|---|---|---|---|---|
mlabonne/NeuralDaredevil-7B π | 59.39 | 45.23 | 76.2 | 67.61 | 48.52 |
mlabonne/Beagle14-7B π | 59.4 | 44.38 | 76.53 | 69.44 | 47.25 |
argilla/distilabeled-Marcoro14-7B-slerp π | 58.93 | 45.38 | 76.48 | 65.68 | 48.18 |
mlabonne/NeuralMarcoro14-7B π | 58.4 | 44.59 | 76.17 | 65.94 | 46.9 |
openchat/openchat-3.5-0106 π | 53.71 | 44.17 | 73.72 | 52.53 | 44.4 |
teknium/OpenHermes-2.5-Mistral-7B π | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |
You can find the complete benchmark on YALL - Yet Another LLM Leaderboard.
Open LLM Leaderboard
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 74.12 |
AI2 Reasoning Challenge (25-Shot) | 69.88 |
HellaSwag (10-Shot) | 87.62 |
MMLU (5-Shot) | 65.12 |
TruthfulQA (0-shot) | 66.85 |
Winogrande (5-shot) | 82.08 |
GSM8k (5-shot) | 73.16 |
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/NeuralDaredevil-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"])