Instructions to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant with Transformers:

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

pipe = pipeline("text-generation", model="GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant")
model = AutoModelForCausalLM.from_pretrained("GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant

SGLang

How to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant 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/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant with Docker Model Runner:
```
docker model run hf.co/GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant
```

Qwen-1.5-4B-layer-mix-bpw-3.0-double-quant / quant_strategy.json

NicoNico6

update

0cc8fe2 about 2 years ago

Raw

History Blame Contribute Delete

86.1 kB

	{
	"measurement": {
	"model.layers.0": {
	"accuracy": 0.9535447359085083,
	"total_bits": 296346912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_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
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.1": {
	"accuracy": 0.9570767879486084,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_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
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.2": {
	"accuracy": 0.9590513706207275,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.3": {
	"accuracy": 0.9570000171661377,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_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
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.4": {
	"accuracy": 0.9529976844787598,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.5": {
	"accuracy": 0.9522297382354736,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.6": {
	"accuracy": 0.9527850151062012,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.7": {
	"accuracy": 0.967296838760376,
	"total_bits": 308013792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_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
	}
	},
	"model.layers.8": {
	"accuracy": 0.9617153406143188,
	"total_bits": 296346912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_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
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.9": {
	"accuracy": 0.9558558464050293,
	"total_bits": 296346912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_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
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.10": {
	"accuracy": 0.961064338684082,
	"total_bits": 308013792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_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
	}
	},
	"model.layers.11": {
	"accuracy": 0.9479024410247803,
	"total_bits": 319680672,
	"o_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
	},
	"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
	},
	"gate_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
	}
	},
	"model.layers.12": {
	"accuracy": 0.9536442756652832,
	"total_bits": 198380032,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.13": {
	"accuracy": 0.9531874656677246,
	"total_bits": 198380032,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.14": {
	"accuracy": 0.9519779682159424,
	"total_bits": 198380032,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.15": {
	"accuracy": 0.9532725811004639,
	"total_bits": 198380032,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.16": {
	"accuracy": 0.956120491027832,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.17": {
	"accuracy": 0.9555456638336182,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.18": {
	"accuracy": 0.9539203643798828,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.19": {
	"accuracy": 0.9534120559692383,
	"total_bits": 244989792,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"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
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.20": {
	"accuracy": 0.9578115940093994,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.21": {
	"accuracy": 0.9579923152923584,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.22": {
	"accuracy": 0.9582035541534424,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.23": {
	"accuracy": 0.9552838802337646,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.24": {
	"accuracy": 0.9604921340942383,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.25": {
	"accuracy": 0.9500429630279541,
	"total_bits": 319680672,
	"o_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
	},
	"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
	},
	"gate_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
	}
	},
	"model.layers.26": {
	"accuracy": 0.9604992866516113,
	"total_bits": 190155456,
	"o_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.27": {
	"accuracy": 0.9601393938064575,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.28": {
	"accuracy": 0.9593974351882935,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.29": {
	"accuracy": 0.9595791101455688,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.30": {
	"accuracy": 0.9596754312515259,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.31": {
	"accuracy": 0.959135890007019,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.32": {
	"accuracy": 0.9589416980743408,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.33": {
	"accuracy": 0.9597592353820801,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.34": {
	"accuracy": 0.95875084400177,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.35": {
	"accuracy": 0.9580636024475098,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.36": {
	"accuracy": 0.9574229717254639,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.37": {
	"accuracy": 0.9579139947891235,
	"total_bits": 181780736,
	"o_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"down_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"2": 8
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.38": {
	"accuracy": 0.959316611289978,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	},
	"model.layers.39": {
	"accuracy": 0.9586589336395264,
	"total_bits": 264834912,
	"o_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
	},
	"q_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"k_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"v_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"gate_proj": {
	"group_size": {
	"2": 16
	},
	"bits": [
	2
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	},
	"up_proj": {
	"group_size": {
	"4": 128
	},
	"bits": [
	4
	],
	"bits_prop": [
	1
	],
	"scale_bits": 4
	}
	}
	}
	}