Instructions to use liminerity/Blur-7b-v1.22 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liminerity/Blur-7b-v1.22 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="liminerity/Blur-7b-v1.22")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("liminerity/Blur-7b-v1.22")
model = AutoModelForCausalLM.from_pretrained("liminerity/Blur-7b-v1.22")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liminerity/Blur-7b-v1.22 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liminerity/Blur-7b-v1.22"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/Blur-7b-v1.22",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liminerity/Blur-7b-v1.22

SGLang

How to use liminerity/Blur-7b-v1.22 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "liminerity/Blur-7b-v1.22" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/Blur-7b-v1.22",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "liminerity/Blur-7b-v1.22" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liminerity/Blur-7b-v1.22",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liminerity/Blur-7b-v1.22 with Docker Model Runner:
```
docker model run hf.co/liminerity/Blur-7b-v1.22
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Blur-7b-v1.22

Blur-7b-v1.22 is a merge of the following models using LazyMergekit:

🧩 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: 86

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for liminerity/Blur-7b-v1.22

Weyaxi/MetaMath-OpenHermes-2.5-neural-chat-v3-3-Slerp

argilla/distilabeled-Marcoro14-7B-slerp

s3nh/Sonya-Panda-7B-slerp

Merge model

this model

Quantizations

2 models

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

62.290
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

82.000
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

58.030
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

68.010
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

78.610
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

31.160