Beagle14-7B/README.md

license, tags, base_model, model-index

license	tags	base_model	model-index
cc-by-nc-4.0	merge mergekit lazymergekit fblgit/UNA-TheBeagle-7b-v1 argilla/distilabeled-Marcoro14-7B-slerp	fblgit/UNA-TheBeagle-7b-v1 argilla/distilabeled-Marcoro14-7B-slerp	name results Beagle14-7B task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 72.95 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 87.95 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 64.7 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 68.88 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 82.64 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 71.42 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Beagle14-7B Open LLM Leaderboard

Beagle14-7B

Update 01/16/24: Check the DPO fine-tuned version of this model, NeuralBeagle14-7B (probably the best 7B model you can find)! 🎉

Beagle14-7B is a merge of the following models using LazyMergekit:

• fblgit/UNA-TheBeagle-7b-v1
• argilla/distilabeled-Marcoro14-7B-slerp

🏆 Evaluation

The evaluation was performed using LLM AutoEval on Nous suite.

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
Beagle14-7B	44.38	76.53	69.44	47.25	59.4
OpenHermes-2.5-Mistral-7B	42.75	72.99	52.99	40.94	52.42
NeuralHermes-2.5-Mistral-7B	43.67	73.24	55.37	41.76	53.51
Nous-Hermes-2-SOLAR-10.7B	47.79	74.69	55.92	44.84	55.81
Marcoro14-7B-slerp	44.66	76.24	64.15	45.64	57.67
CatMarcoro14-7B-slerp	45.21	75.91	63.81	47.31	58.06

🧩 Configuration

slices:
  - sources:
      - model: fblgit/UNA-TheBeagle-7b-v1
        layer_range: [0, 32]
      - model: argilla/distilabeled-Marcoro14-7B-slerp
        layer_range: [0, 32]
merge_method: slerp
base_model: fblgit/UNA-TheBeagle-7b-v1
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "mlabonne/Beagle14-7B"
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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	74.76
AI2 Reasoning Challenge (25-Shot)	72.95
HellaSwag (10-Shot)	87.95
MMLU (5-Shot)	64.70
TruthfulQA (0-shot)	68.88
Winogrande (5-shot)	82.64
GSM8k (5-shot)	71.42