Instructions to use GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-alpaca 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-alpaca 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-alpaca")
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-alpaca")
model = AutoModelForCausalLM.from_pretrained("GreenBitAI/Qwen-1.5-4B-layer-mix-bpw-3.0-alpaca")
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-alpaca 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-alpaca"
# 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-alpaca",
		"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-alpaca

SGLang

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

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

NicoNico6

update

93d94eb about 2 years ago

Raw

History Blame Contribute Delete

86.2 kB

	{
	"measurement": {
	"model.layers.0": {
	"accuracy": 0.9096698760986328,
	"total_bits": 271943712,
	"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.1": {
	"accuracy": 0.9286572933197021,
	"total_bits": 224206752,
	"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.2": {
	"accuracy": 0.9440598487854004,
	"total_bits": 259042272,
	"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.3": {
	"accuracy": 0.9462785720825195,
	"total_bits": 259042272,
	"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.4": {
	"accuracy": 0.9482824802398682,
	"total_bits": 259042272,
	"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.5": {
	"accuracy": 0.9288809299468994,
	"total_bits": 224206752,
	"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.6": {
	"accuracy": 0.9409534931182861,
	"total_bits": 259042272,
	"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.7": {
	"accuracy": 0.97636878490448,
	"total_bits": 319680672,
	"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.8": {
	"accuracy": 0.9747415781021118,
	"total_bits": 319680672,
	"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.9": {
	"accuracy": 0.9734252691268921,
	"total_bits": 319680672,
	"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.10": {
	"accuracy": 0.9705219268798828,
	"total_bits": 319680672,
	"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.11": {
	"accuracy": 0.9314451217651367,
	"total_bits": 259042272,
	"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.12": {
	"accuracy": 0.9396202564239502,
	"total_bits": 224206752,
	"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.13": {
	"accuracy": 0.9343719482421875,
	"total_bits": 224206752,
	"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.14": {
	"accuracy": 0.9370849132537842,
	"total_bits": 224206752,
	"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.15": {
	"accuracy": 0.9369666576385498,
	"total_bits": 224206752,
	"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.16": {
	"accuracy": 0.9315023422241211,
	"total_bits": 224206752,
	"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.17": {
	"accuracy": 0.9309182167053223,
	"total_bits": 224206752,
	"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.18": {
	"accuracy": 0.9522058963775635,
	"total_bits": 271943712,
	"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.19": {
	"accuracy": 0.9481220245361328,
	"total_bits": 259042272,
	"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.20": {
	"accuracy": 0.9506392478942871,
	"total_bits": 271943712,
	"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.21": {
	"accuracy": 0.9442451000213623,
	"total_bits": 259042272,
	"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.22": {
	"accuracy": 0.9434452056884766,
	"total_bits": 259042272,
	"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.23": {
	"accuracy": 0.9384822845458984,
	"total_bits": 259042272,
	"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.24": {
	"accuracy": 0.9454813003540039,
	"total_bits": 259042272,
	"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.25": {
	"accuracy": 0.9371838569641113,
	"total_bits": 259042272,
	"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.26": {
	"accuracy": 0.9395887851715088,
	"total_bits": 176471424,
	"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.27": {
	"accuracy": 0.9384074211120605,
	"total_bits": 176471424,
	"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.28": {
	"accuracy": 0.938711404800415,
	"total_bits": 176471424,
	"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.29": {
	"accuracy": 0.938201904296875,
	"total_bits": 176471424,
	"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.30": {
	"accuracy": 0.9373049736022949,
	"total_bits": 176471424,
	"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.31": {
	"accuracy": 0.9390568733215332,
	"total_bits": 189372864,
	"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.32": {
	"accuracy": 0.9377017021179199,
	"total_bits": 189372864,
	"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.33": {
	"accuracy": 0.9383924007415771,
	"total_bits": 189372864,
	"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.34": {
	"accuracy": 0.9503309726715088,
	"total_bits": 211305312,
	"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.35": {
	"accuracy": 0.9464483261108398,
	"total_bits": 211305312,
	"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.36": {
	"accuracy": 0.9353611469268799,
	"total_bits": 189372864,
	"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.37": {
	"accuracy": 0.9354612827301025,
	"total_bits": 189372864,
	"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.38": {
	"accuracy": 0.9497716426849365,
	"total_bits": 259042272,
	"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.39": {
	"accuracy": 0.9486417770385742,
	"total_bits": 259042272,
	"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
	}
	}
	}
	}