language:
- en
license: apache-2.0
datasets:
- Intel/orca_dpo_pairs
model-index:
- name: mistral-7b-dpo-v6
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: 72.53
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
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: 88.1
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
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: 64.68
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
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: 68.24
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
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: 82.56
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
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: 70.89
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mncai/mistral-7b-dpo-v6
name: Open LLM Leaderboard
Model Card for mncai/mistral-7b-dpo-v6
Introduction of MindsAndCompany
We create various AI models and develop solutions that can be applied to businesses. And as for generative AI, we are developing products like Code Assistant, TOD Chatbot, LLMOps, and are in the process of developing Enterprise AGI (Artificial General Intelligence).
Model Summary
based mistral-7b, dpo tuned.
Detail
first step ties merge.
models:
- model: AIDC-ai-business/Marcoroni-7B-v3
# no parameters necessary for base model
- model: GreenNode/GreenNodeLM-7B-v1olet # psmathur/orca_mini_v3_13b
parameters:
density: [1, 0.7, 0.1] # density gradient
weight: 1.0
- model: viethq188/LeoScorpius-7B-Chat-DPO
parameters:
density: 0.5
weight: [0, 0.3, 0.7, 1] # weight gradient
- model: mncai/mistral-7b-dpo-v5
parameters:
density: 0.33
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: ties
base_model: AIDC-ai-business/Marcoroni-7B-v3
parameters:
normalize: true
int8_mask: true
dtype: float16
second step dpo.
# Training arguments
training_args = TrainingArguments(
per_device_train_batch_size=5,
gradient_accumulation_steps=4,
gradient_checkpointing=True,
learning_rate=5e-6,
lr_scheduler_type="cosine",
max_steps=1000,
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=2048,
)
# Fine-tune model with DPO
dpo_trainer.train()
How to Use
Here give some examples of how to use our model.
from transformers import AutoConfig, AutoModel, AutoTokenizer
import transformers
import torch
hf_model = 'mncai/mistral-7b-dpo-v6'
message = "<|user|>\n๋ ๊ฐ์ ๊ตฌ๊ฐ ์๋๋ฐ ๊ฐ๊ฐ ์ง๋ฆ์ด 1, 2์ผ๋ ๊ตฌ์ ๋ถํผ๋ ๋ช๋ฐฐ ์ฐจ์ด๊ฐ ๋์ง? ์ค๋ช
๋ ๊ฐ์ด ํด์ค.\n<|assistant|>\n"
sequences = pipeline(
message,
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=2048,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
Warnings
Currently, the leaderboard is overfitted. It is inevitable because, unlike Kaggle, where there's private scoring followed by the end of the competition, here the scores are continuously open. Even among my models, some received lower scores in internal data evaluations. mncai/agiin-13.6B-v0.1 > mncai/agiin-11.1B-v0.1 > mncai/mistral-7b-dpo-v6. However, on the leaderboard, mncai/mistral-7b-dpo-v6 has the highest score. When choosing a model to use on the open LLM leaderboard, it would be best to evaluate with your own private dataset that is not publicly available.
Detect-Pretrain-Code-Contamination Result Share
use https://github.com/Mihaiii/detect-pretrain-code-contamination
DATASET=truthful_qa python src/run.py --target_model mncai/mistral-7b-dpo-v6 --data $DATASET --output_dir out/$DATASET --ratio_gen 0.4
result < 0.1, %: 0.76
Contact
If you have any questions, please raise an issue or contact us at [email protected]
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.50 |
| AI2 Reasoning Challenge (25-Shot) | 72.53 |
| HellaSwag (10-Shot) | 88.10 |
| MMLU (5-Shot) | 64.68 |
| TruthfulQA (0-shot) | 68.24 |
| Winogrande (5-shot) | 82.56 |
| GSM8k (5-shot) | 70.89 |