metadata
tags:
- merge
- mergekit
- lazymergekit
- mistralai/Mistral-7B-Instruct-v0.2
- teknium/OpenHermes-2.5-Mistral-7B
base_model:
- mistralai/Mistral-7B-Instruct-v0.2
- teknium/OpenHermes-2.5-Mistral-7B
license: apache-2.0
Nero-7B-slerp
Nero-7B-slerp is a merge of the following models using mergekit:
π Performance
Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
---|---|---|---|---|---|
teodortita/Nero-7B-slerp | 41.73 | 73.37 | 58.66 | 43.03 | 54.2 |
mistralai/Mistral-7B-Instruct-v0.2 | 38.68 | 71.64 | 66.85 | 42.28 | 54.86 |
teknium/OpenHermes-2.5-Mistral-7B | 42.82 | 73.04 | 53.02 | 40.99 | 52.47 |
Observe the metrics in bold to see the benchmarks where this merged model overtakes the base models in performance.
𧩠Configuration
slices:
- sources:
- model: mistralai/Mistral-7B-Instruct-v0.2
layer_range: [0, 32]
- model: teknium/OpenHermes-2.5-Mistral-7B
layer_range: [0, 32]
merge_method: slerp
base_model: mistralai/Mistral-7B-Instruct-v0.2
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
π» Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "teodortita/Nero-7B-slerp"
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"])