Instructions to use GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0 with Transformers:

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

pipe = pipeline("text-generation", model="GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0")
model = AutoModelForCausalLM.from_pretrained("GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0

SGLang

How to use GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0 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 "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0" \
    --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": "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0",
		"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 "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0" \
        --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": "GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0 with Docker Model Runner:
```
docker model run hf.co/GreenBitAI/01-Yi-34B-layer-mix-bpw-3.0
```

01-Yi-34B-layer-mix-bpw-3.0 / quant_strategy.json

NicoNico6

update

91dbbea over 2 years ago

Raw

History Blame Contribute Delete

129 kB

	{
	"measurement": {
	"model.layers.0": {
	"accuracy": 0.9728512763977051,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.1": {
	"accuracy": 0.9760153293609619,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.2": {
	"accuracy": 0.9462802410125732,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.3": {
	"accuracy": 0.9944927841424942,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.4": {
	"accuracy": 0.993605300784111,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.5": {
	"accuracy": 0.9932107627391815,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.6": {
	"accuracy": 0.9913060367107391,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.7": {
	"accuracy": 0.9906440675258636,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.8": {
	"accuracy": 0.9870590567588806,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.9": {
	"accuracy": 0.9886279404163361,
	"total_bits": 1179493632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.10": {
	"accuracy": 0.985314667224884,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.11": {
	"accuracy": 0.9837721586227417,
	"total_bits": 1179493632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.12": {
	"accuracy": 0.9826334714889526,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.13": {
	"accuracy": 0.9785091876983643,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.14": {
	"accuracy": 0.978158712387085,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.15": {
	"accuracy": 0.9814843535423279,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.16": {
	"accuracy": 0.9805989265441895,
	"total_bits": 1179493632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.17": {
	"accuracy": 0.9753129482269287,
	"total_bits": 1165045632,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.18": {
	"accuracy": 0.976073145866394,
	"total_bits": 1266197760,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.19": {
	"accuracy": 0.9731930494308472,
	"total_bits": 1266197760,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.20": {
	"accuracy": 0.9715620279312134,
	"total_bits": 1454051712,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.21": {
	"accuracy": 0.9717429876327515,
	"total_bits": 1266197760,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.22": {
	"accuracy": 0.9711763858795166,
	"total_bits": 1555203840,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.23": {
	"accuracy": 0.9721603393554688,
	"total_bits": 1454051712,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.24": {
	"accuracy": 0.9733863472938538,
	"total_bits": 1555203840,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.25": {
	"accuracy": 0.9728134870529175,
	"total_bits": 1656355968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.26": {
	"accuracy": 0.9726482033729553,
	"total_bits": 1656355968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.27": {
	"accuracy": 0.9706771373748779,
	"total_bits": 1656355968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.28": {
	"accuracy": 0.9735845327377319,
	"total_bits": 1670803968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.29": {
	"accuracy": 0.972029447555542,
	"total_bits": 1670803968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.30": {
	"accuracy": 0.9713331460952759,
	"total_bits": 1670803968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.31": {
	"accuracy": 0.9692908525466919,
	"total_bits": 1670803968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.32": {
	"accuracy": 0.9678269624710083,
	"total_bits": 1670803968,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.33": {
	"accuracy": 0.9791433811187744,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.34": {
	"accuracy": 0.978040874004364,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.35": {
	"accuracy": 0.9855986833572388,
	"total_bits": 2248826112,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.36": {
	"accuracy": 0.9850517511367798,
	"total_bits": 2248826112,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.37": {
	"accuracy": 0.9835020303726196,
	"total_bits": 2248826112,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.38": {
	"accuracy": 0.9753072261810303,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.39": {
	"accuracy": 0.9759111404418945,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.40": {
	"accuracy": 0.9762191772460938,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.41": {
	"accuracy": 0.976518988609314,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.42": {
	"accuracy": 0.9794609546661377,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.43": {
	"accuracy": 0.9793961048126221,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.44": {
	"accuracy": 0.9801192283630371,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.45": {
	"accuracy": 0.9815818071365356,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.46": {
	"accuracy": 0.9830822944641113,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.47": {
	"accuracy": 0.9841325879096985,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.48": {
	"accuracy": 0.9849817156791687,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.49": {
	"accuracy": 0.9844100475311279,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.50": {
	"accuracy": 0.9858189225196838,
	"total_bits": 2147673984,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.51": {
	"accuracy": 0.970251202583313,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.52": {
	"accuracy": 0.9718092679977417,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.53": {
	"accuracy": 0.9726873636245728,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.54": {
	"accuracy": 0.9737123250961304,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.55": {
	"accuracy": 0.9734394550323486,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.56": {
	"accuracy": 0.9729830026626587,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.57": {
	"accuracy": 0.9715316295623779,
	"total_bits": 1844214912,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.58": {
	"accuracy": 0.9705996513366699,
	"total_bits": 1945367040,
	"q_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.59": {
	"accuracy": 0.9778633117675781,
	"total_bits": 1454051712,
	"q_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"o_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 64
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	}
	}
	}