Blur-7b-v1.22
Blur-7b-v1.22 is a merge of the following models using LazyMergekit:
- s3nh/Sonya-Panda-7B-slerp
- argilla/distilabeled-Marcoro14-7B-slerp
- Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
🧩 Configuration
models:
- model: s3nh/Sonya-Panda-7B-slerp
parameters:
density: [1, 0.7, 0.1] # density gradient
weight: 1.0
- model: argilla/distilabeled-Marcoro14-7B-slerp
parameters:
density: 0.5
weight: [0, 0.3, 0.7, 1] # weight gradient
- model: Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp
parameters:
density: 0.33
weight:
- filter: mlp
value: 0.5
- value: 0
merge_method: ties
base_model: liminerity/Blur-7b-v1.21
parameters:
normalize: true
int8_mask: true
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "liminerity/Blur-7b-v1.22"
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. | 63.35 |
AI2 Reasoning Challenge (25-Shot) | 62.29 |
HellaSwag (10-Shot) | 82.00 |
MMLU (5-Shot) | 58.03 |
TruthfulQA (0-shot) | 68.01 |
Winogrande (5-shot) | 78.61 |
GSM8k (5-shot) | 31.16 |
- Downloads last month
- 58
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for liminerity/Blur-7b-v1.22
Merge model
this model
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard62.290
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.000
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard58.030
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard68.010
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard78.610
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard31.160