Darewin-7B / README.md
mlabonne's picture
Adding Evaluation Results (#1)
556081c verified
---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
base_model:
- Intel/neural-chat-7b-v3-3
- openaccess-ai-collective/DPOpenHermes-7B-v2
- fblgit/una-cybertron-7b-v2-bf16
- openchat/openchat-3.5-0106
- OpenPipe/mistral-ft-optimized-1227
- mlabonne/NeuralHermes-2.5-Mistral-7B
model-index:
- name: Darewin-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: 68.6
name: normalized accuracy
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-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: 86.22
name: normalized accuracy
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-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: 65.21
name: accuracy
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-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: 60.38
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-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: 79.79
name: accuracy
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-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: 71.04
name: accuracy
source:
url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/Darewin-7B
name: Open LLM Leaderboard
---
# Darewin-7B
Darewin-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Intel/neural-chat-7b-v3-3](https://huggingface.co./Intel/neural-chat-7b-v3-3)
* [openaccess-ai-collective/DPOpenHermes-7B-v2](https://huggingface.co./openaccess-ai-collective/DPOpenHermes-7B-v2)
* [fblgit/una-cybertron-7b-v2-bf16](https://huggingface.co./fblgit/una-cybertron-7b-v2-bf16)
* [openchat/openchat-3.5-0106](https://huggingface.co./openchat/openchat-3.5-0106)
* [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co./OpenPipe/mistral-ft-optimized-1227)
* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co./mlabonne/NeuralHermes-2.5-Mistral-7B)
## 🧩 Configuration
```yaml
models:
- model: mistralai/Mistral-7B-v0.1
# No parameters necessary for base model
- model: Intel/neural-chat-7b-v3-3
parameters:
density: 0.6
weight: 0.2
- model: openaccess-ai-collective/DPOpenHermes-7B-v2
parameters:
density: 0.6
weight: 0.1
- model: fblgit/una-cybertron-7b-v2-bf16
parameters:
density: 0.6
weight: 0.2
- model: openchat/openchat-3.5-0106
parameters:
density: 0.6
weight: 0.15
- model: OpenPipe/mistral-ft-optimized-1227
parameters:
density: 0.6
weight: 0.25
- model: mlabonne/NeuralHermes-2.5-Mistral-7B
parameters:
density: 0.6
weight: 0.1
merge_method: dare_ties
base_model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: true
dtype: bfloat16
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "mlabonne/Darewin-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](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co./datasets/open-llm-leaderboard/details_mlabonne__Darewin-7B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |71.87|
|AI2 Reasoning Challenge (25-Shot)|68.60|
|HellaSwag (10-Shot) |86.22|
|MMLU (5-Shot) |65.21|
|TruthfulQA (0-shot) |60.38|
|Winogrande (5-shot) |79.79|
|GSM8k (5-shot) |71.04|