Hugging Face's logo

riczhou
/
Phi-3-mini-4k-instruct-q4f32_1-MLC

Model card Files Community
Phi-3-mini-4k-instruct-q4f32_1-MLC / logs.txt
riczhou's picture
riczhou
Initial commit
0ef1a5b verified
raw
history blame contribute delete
103 kB
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm gen_config /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83 --quantization q4f32_1 --conv-template phi-3 --output /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC
[2024-05-26 04:14:01] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/config.json
[2024-05-26 04:14:01] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-26 04:14:01] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-26 04:14:01] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
[2024-05-26 04:14:01] INFO config.py:106: Overriding max_batch_size from 1 to 80
[2024-05-26 04:14:01] INFO gen_config.py:255: [generation_config.json] Setting bos_token_id: 1
[2024-05-26 04:14:01] INFO gen_config.py:255: [generation_config.json] Setting eos_token_id: [32000, 32001, 32007]
[2024-05-26 04:14:01] INFO gen_config.py:255: [generation_config.json] Setting pad_token_id: 32000
[2024-05-26 04:14:01] INFO gen_config.py:267: Found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/tokenizer.model. Copying to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/tokenizer.model
[2024-05-26 04:14:01] INFO gen_config.py:267: Found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/tokenizer.json. Copying to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/tokenizer.json
[2024-05-26 04:14:01] INFO gen_config.py:269: Not found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/vocab.json
[2024-05-26 04:14:01] INFO gen_config.py:269: Not found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/merges.txt
[2024-05-26 04:14:01] INFO gen_config.py:267: Found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/added_tokens.json. Copying to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/added_tokens.json
[2024-05-26 04:14:01] INFO gen_config.py:267: Found tokenizer config: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/tokenizer_config.json. Copying to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/tokenizer_config.json
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting temperature: 0.7
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting presence_penalty: 0.0
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting frequency_penalty: 0.0
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting repetition_penalty: 1.0
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting top_p: 0.95
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting mean_gen_len: 128
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting max_gen_len: 512
[2024-05-26 04:14:01] INFO gen_config.py:80: [System default] Setting shift_fill_factor: 0.3
[2024-05-26 04:14:01] INFO gen_config.py:335: Dumping configuration file to: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/mlc-chat-config.json
/home/rickzhou/miniconda3/envs/mlc/bin/python -m mlc_llm convert_weight /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83 --quantization q4f32_1 --source-format auto --output /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC
[2024-05-26 04:14:02] INFO auto_config.py:115: Found model configuration: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/config.json
[2024-05-26 04:14:03] INFO auto_device.py:79: Found device: cuda:0
[2024-05-26 04:14:03] INFO auto_device.py:79: Found device: cuda:1
[2024-05-26 04:14:04] INFO auto_device.py:88: Not found device: rocm:0
[2024-05-26 04:14:05] INFO auto_device.py:88: Not found device: metal:0
[2024-05-26 04:14:06] INFO auto_device.py:79: Found device: vulkan:0
[2024-05-26 04:14:06] INFO auto_device.py:79: Found device: vulkan:1
[2024-05-26 04:14:06] INFO auto_device.py:79: Found device: vulkan:2
[2024-05-26 04:14:07] INFO auto_device.py:88: Not found device: opencl:0
[2024-05-26 04:14:07] INFO auto_device.py:35: Using device: cuda:0
[2024-05-26 04:14:07] INFO auto_weight.py:70: Finding weights in: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83
[2024-05-26 04:14:07] INFO auto_weight.py:136: Not found Huggingface PyTorch
[2024-05-26 04:14:07] INFO auto_weight.py:143: Found source weight format: huggingface-safetensor. Source configuration: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model.safetensors.index.json
[2024-05-26 04:14:07] INFO auto_weight.py:106: Using source weight configuration: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model.safetensors.index.json. Use `--source` to override.
[2024-05-26 04:14:07] INFO auto_weight.py:110: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-05-26 04:14:07] INFO auto_config.py:153: Found model type: phi3. Use `--model-type` to override.
[2024-05-26 04:14:07] INFO phi3_model.py:53: context_window_size not found in config.json. Falling back to max_position_embeddings (4096)
[2024-05-26 04:14:07] INFO phi3_model.py:68: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
--config /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/config.json
--quantization GroupQuantize(name='q4f32_1', kind='group-quant', group_size=32, quantize_dtype='int4', storage_dtype='uint32', model_dtype='float32', linear_weight_layout='NK', quantize_embedding=True, quantize_final_fc=True, num_elem_per_storage=8, num_storage_per_group=4, max_int_value=7)
--model-type phi3
--device cuda:0
--source /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model.safetensors.index.json
--source-format huggingface-safetensor
--output /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC
Start storing to cache /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC
0%| | 0/195 [00:00<?, ?it/s] [2024-05-26 04:14:10] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model-00002-of-00002.safetensors
0%| | 0/195 [00:00<?, ?it/s] [2024-05-26 04:14:12] INFO group_quantization.py:217: Compiling quantize function for key: ((32064, 3072), float32, cuda, axis=1, output_transpose=False)
0%| | 0/195 [00:01<?, ?it/s] [2024-05-26 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "lm_head.q_weight", shape: (32064, 384), dtype: uint32
0%| | 0/195 [00:02<?, ?it/s] [2024-05-26 04:14:13] INFO huggingface_loader.py:166: [Quantized] Parameter: "lm_head.q_scale", shape: (32064, 96), dtype: float32
0%| | 0/195 [00:02<?, ?it/s]/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:549: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
setattr(self, word, getattr(machar, word).flat[0])
/home/rickzhou/miniconda3/envs/mlc/lib/python3.11/site-packages/numpy/core/getlimits.py:89: UserWarning: The value of the smallest subnormal for <class 'numpy.float32'> type is zero.
return self._float_to_str(self.smallest_subnormal)
1%| | 1/195 [00:02<09:10, 2.84s/it] [2024-05-26 04:14:13] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.ln.weight", shape: (3072,), dtype: float32
1%| | 1/195 [00:02<09:10, 2.84s/it] [2024-05-26 04:14:13] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 8192), float32, cuda, axis=1, output_transpose=False)
1%| | 1/195 [00:02<09:10, 2.84s/it] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
1%| | 1/195 [00:03<09:10, 2.84s/it] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
1%| | 1/195 [00:03<09:10, 2.84s/it] 2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-05-26 04:14:14] INFO group_quantization.py:217: Compiling quantize function for key: ((16384, 3072), float32, cuda, axis=1, output_transpose=False)
2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
2%|▏ | 3/195 [00:03<02:44, 1.17it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
2%|▏ | 3/195 [00:03<02:44, 1.17it/s] 2%|▏ | 4/195 [00:03<02:12, 1.44it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.21.post_attention_layernorm.weight", shape: (3072,), dtype: float32
2%|▏ | 4/195 [00:03<02:12, 1.44it/s] [2024-05-26 04:14:14] INFO group_quantization.py:217: Compiling quantize function for key: ((9216, 3072), float32, cuda, axis=1, output_transpose=False)
2%|▏ | 4/195 [00:03<02:12, 1.44it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
2%|▏ | 4/195 [00:03<02:12, 1.44it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
2%|▏ | 4/195 [00:03<02:12, 1.44it/s] 3%|▎ | 6/195 [00:03<01:23, 2.26it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.ln.weight", shape: (3072,), dtype: float32
3%|▎ | 6/195 [00:03<01:23, 2.26it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
3%|▎ | 6/195 [00:03<01:23, 2.26it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
3%|▎ | 6/195 [00:03<01:23, 2.26it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
3%|▎ | 6/195 [00:03<01:23, 2.26it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
3%|▎ | 6/195 [00:04<01:23, 2.26it/s] 5%|▍ | 9/195 [00:04<00:44, 4.20it/s] [2024-05-26 04:14:14] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.22.post_attention_layernorm.weight", shape: (3072,), dtype: float32
5%|▍ | 9/195 [00:04<00:44, 4.20it/s] [2024-05-26 04:14:14] INFO group_quantization.py:217: Compiling quantize function for key: ((3072, 3072), float32, cuda, axis=1, output_transpose=False)
5%|▍ | 9/195 [00:04<00:44, 4.20it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
5%|▍ | 9/195 [00:04<00:44, 4.20it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
5%|▍ | 9/195 [00:04<00:44, 4.20it/s] 6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.22.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.ln.weight", shape: (3072,), dtype: float32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
6%|▌ | 11/195 [00:04<00:40, 4.53it/s] 8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.23.post_attention_layernorm.weight", shape: (3072,), dtype: float32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.23.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.ln.weight", shape: (3072,), dtype: float32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
8%|▊ | 15/195 [00:04<00:24, 7.25it/s] 10%|█ | 20/195 [00:04<00:14, 11.86it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
10%|█ | 20/195 [00:04<00:14, 11.86it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
10%|█ | 20/195 [00:04<00:14, 11.86it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.24.post_attention_layernorm.weight", shape: (3072,), dtype: float32
10%|█ | 20/195 [00:04<00:14, 11.86it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
10%|█ | 20/195 [00:04<00:14, 11.86it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
10%|█ | 20/195 [00:04<00:14, 11.86it/s] 12%|█▏ | 23/195 [00:04<00:13, 13.04it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
12%|█▏ | 23/195 [00:04<00:13, 13.04it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.24.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
12%|█▏ | 23/195 [00:04<00:13, 13.04it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.ln.weight", shape: (3072,), dtype: float32
12%|█▏ | 23/195 [00:04<00:13, 13.04it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
12%|█▏ | 23/195 [00:04<00:13, 13.04it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
12%|█▏ | 23/195 [00:05<00:13, 13.04it/s] 13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] [2024-05-26 04:14:15] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.25.post_attention_layernorm.weight", shape: (3072,), dtype: float32
13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
13%|█▎ | 26/195 [00:05<00:10, 15.50it/s] 15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.25.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.ln.weight", shape: (3072,), dtype: float32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
15%|█▍ | 29/195 [00:05<00:09, 17.45it/s] 17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.26.post_attention_layernorm.weight", shape: (3072,), dtype: float32
17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.26.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
17%|█▋ | 33/195 [00:05<00:08, 18.26it/s] 18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.ln.weight", shape: (3072,), dtype: float32
18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
18%|█▊ | 36/195 [00:05<00:07, 20.35it/s] 20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.27.post_attention_layernorm.weight", shape: (3072,), dtype: float32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.27.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.ln.weight", shape: (3072,), dtype: float32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
20%|██ | 39/195 [00:05<00:07, 19.56it/s] 23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.28.post_attention_layernorm.weight", shape: (3072,), dtype: float32
23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
23%|██▎ | 44/195 [00:05<00:05, 25.50it/s] 24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.28.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.ln.weight", shape: (3072,), dtype: float32
24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
24%|██▍ | 47/195 [00:05<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
24%|██▍ | 47/195 [00:06<00:06, 22.79it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
24%|██▍ | 47/195 [00:06<00:06, 22.79it/s] 26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.29.post_attention_layernorm.weight", shape: (3072,), dtype: float32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:16] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.29.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.ln.weight", shape: (3072,), dtype: float32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
26%|██▌ | 51/195 [00:06<00:06, 21.68it/s] 29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.30.post_attention_layernorm.weight", shape: (3072,), dtype: float32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.30.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
29%|██▊ | 56/195 [00:06<00:05, 27.00it/s] 31%|███ | 60/195 [00:06<00:05, 24.14it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.ln.weight", shape: (3072,), dtype: float32
31%|███ | 60/195 [00:06<00:05, 24.14it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
31%|███ | 60/195 [00:06<00:05, 24.14it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
31%|███ | 60/195 [00:06<00:05, 24.14it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
31%|███ | 60/195 [00:06<00:05, 24.14it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
31%|███ | 60/195 [00:06<00:05, 24.14it/s] 32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.31.post_attention_layernorm.weight", shape: (3072,), dtype: float32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.31.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.norm.weight", shape: (3072,), dtype: float32
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model-00002-of-00002.safetensors
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:17] INFO huggingface_loader.py:184: Loading HF parameters from: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model-00001-of-00002.safetensors
32%|███▏ | 63/195 [00:06<00:05, 22.26it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.embd.q_weight", shape: (32064, 384), dtype: uint32
32%|███▏ | 63/195 [00:07<00:05, 22.26it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.embd.q_scale", shape: (32064, 96), dtype: float32
32%|███▏ | 63/195 [00:07<00:05, 22.26it/s] 35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.ln.weight", shape: (3072,), dtype: float32
35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
35%|███▍ | 68/195 [00:07<00:13, 9.13it/s] 36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.0.post_attention_layernorm.weight", shape: (3072,), dtype: float32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.0.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.ln.weight", shape: (3072,), dtype: float32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
36%|███▋ | 71/195 [00:07<00:11, 10.35it/s] 39%|███▉ | 76/195 [00:07<00:08, 14.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
39%|███▉ | 76/195 [00:08<00:08, 14.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
39%|███▉ | 76/195 [00:08<00:08, 14.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.1.post_attention_layernorm.weight", shape: (3072,), dtype: float32
39%|███▉ | 76/195 [00:08<00:08, 14.35it/s] [2024-05-26 04:14:18] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
39%|███▉ | 76/195 [00:08<00:08, 14.35it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
39%|███▉ | 76/195 [00:08<00:08, 14.35it/s] 41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.1.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.ln.weight", shape: (3072,), dtype: float32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
41%|████ | 79/195 [00:08<00:07, 15.00it/s] 43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.10.post_attention_layernorm.weight", shape: (3072,), dtype: float32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.10.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.ln.weight", shape: (3072,), dtype: float32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
43%|████▎ | 83/195 [00:08<00:06, 16.28it/s] 45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.11.post_attention_layernorm.weight", shape: (3072,), dtype: float32
45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
45%|████▌ | 88/195 [00:08<00:05, 21.24it/s] 47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.11.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.ln.weight", shape: (3072,), dtype: float32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
47%|████▋ | 91/195 [00:08<00:05, 20.24it/s] 49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.12.post_attention_layernorm.weight", shape: (3072,), dtype: float32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.12.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.ln.weight", shape: (3072,), dtype: float32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
49%|████▊ | 95/195 [00:08<00:04, 20.24it/s] 51%|█████▏ | 100/195 [00:08<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
51%|█████▏ | 100/195 [00:08<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.13.post_attention_layernorm.weight", shape: (3072,), dtype: float32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.13.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
51%|█████▏ | 100/195 [00:09<00:03, 25.38it/s] 53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] [2024-05-26 04:14:19] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.ln.weight", shape: (3072,), dtype: float32
53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
53%|█████▎ | 104/195 [00:09<00:03, 23.57it/s] 55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.14.post_attention_layernorm.weight", shape: (3072,), dtype: float32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.14.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.ln.weight", shape: (3072,), dtype: float32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
55%|█████▍ | 107/195 [00:09<00:04, 21.92it/s] 57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.15.post_attention_layernorm.weight", shape: (3072,), dtype: float32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.15.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
57%|█████▋ | 112/195 [00:09<00:03, 27.16it/s] 59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.ln.weight", shape: (3072,), dtype: float32
59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
59%|█████▉ | 116/195 [00:09<00:03, 24.60it/s] 61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.16.post_attention_layernorm.weight", shape: (3072,), dtype: float32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.16.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.ln.weight", shape: (3072,), dtype: float32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
61%|██████ | 119/195 [00:09<00:03, 22.64it/s] 64%|██████▎ | 124/195 [00:09<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
64%|██████▎ | 124/195 [00:09<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
64%|██████▎ | 124/195 [00:09<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.17.post_attention_layernorm.weight", shape: (3072,), dtype: float32
64%|██████▎ | 124/195 [00:09<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
64%|██████▎ | 124/195 [00:09<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
64%|██████▎ | 124/195 [00:10<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
64%|██████▎ | 124/195 [00:10<00:02, 27.92it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.17.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
64%|██████▎ | 124/195 [00:10<00:02, 27.92it/s] 66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.ln.weight", shape: (3072,), dtype: float32
66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] [2024-05-26 04:14:20] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
66%|██████▌ | 128/195 [00:10<00:02, 24.82it/s] 67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.18.post_attention_layernorm.weight", shape: (3072,), dtype: float32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.18.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.ln.weight", shape: (3072,), dtype: float32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
67%|██████▋ | 131/195 [00:10<00:02, 22.93it/s] 70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.19.post_attention_layernorm.weight", shape: (3072,), dtype: float32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.19.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
70%|██████▉ | 136/195 [00:10<00:02, 28.27it/s] 72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.ln.weight", shape: (3072,), dtype: float32
72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
72%|███████▏ | 140/195 [00:10<00:02, 25.30it/s] 73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.2.post_attention_layernorm.weight", shape: (3072,), dtype: float32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.2.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.ln.weight", shape: (3072,), dtype: float32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
73%|███████▎ | 143/195 [00:10<00:02, 23.17it/s] 76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.20.post_attention_layernorm.weight", shape: (3072,), dtype: float32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
76%|███████▌ | 148/195 [00:10<00:01, 28.34it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.20.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
76%|███████▌ | 148/195 [00:11<00:01, 28.34it/s] 78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.21.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.ln.weight", shape: (3072,), dtype: float32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:21] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
78%|███████▊ | 152/195 [00:11<00:01, 25.31it/s] 80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.3.post_attention_layernorm.weight", shape: (3072,), dtype: float32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.3.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.ln.weight", shape: (3072,), dtype: float32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
80%|████████ | 156/195 [00:11<00:01, 23.80it/s] 83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.4.post_attention_layernorm.weight", shape: (3072,), dtype: float32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.4.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
83%|████████▎ | 161/195 [00:11<00:01, 28.73it/s] 85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.ln.weight", shape: (3072,), dtype: float32
85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
85%|████████▍ | 165/195 [00:11<00:01, 25.62it/s] 86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.5.post_attention_layernorm.weight", shape: (3072,), dtype: float32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.5.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.ln.weight", shape: (3072,), dtype: float32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
86%|████████▌ | 168/195 [00:11<00:01, 23.43it/s] 89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.6.post_attention_layernorm.weight", shape: (3072,), dtype: float32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.6.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
89%|████████▊ | 173/195 [00:11<00:00, 28.55it/s] 91%|█████████ | 177/195 [00:11<00:00, 25.52it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.ln.weight", shape: (3072,), dtype: float32
91%|█████████ | 177/195 [00:11<00:00, 25.52it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
91%|█████████ | 177/195 [00:11<00:00, 25.52it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
91%|█████████ | 177/195 [00:12<00:00, 25.52it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
91%|█████████ | 177/195 [00:12<00:00, 25.52it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
91%|█████████ | 177/195 [00:12<00:00, 25.52it/s] 92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:22] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.7.post_attention_layernorm.weight", shape: (3072,), dtype: float32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.7.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.ln.weight", shape: (3072,), dtype: float32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
92%|█████████▏| 180/195 [00:12<00:00, 23.33it/s] 95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.8.post_attention_layernorm.weight", shape: (3072,), dtype: float32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.8.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
95%|█████████▍| 185/195 [00:12<00:00, 28.60it/s] 97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.ln.weight", shape: (3072,), dtype: float32
97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_weight", shape: (3072, 1024), dtype: uint32
97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.down_proj.q_scale", shape: (3072, 256), dtype: float32
97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_weight", shape: (16384, 384), dtype: uint32
97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mlp.gate_up_proj.q_scale", shape: (16384, 96), dtype: float32
97%|█████████▋| 189/195 [00:12<00:00, 25.63it/s] 98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:174: [Not quantized] Parameter: "transformer.h.9.post_attention_layernorm.weight", shape: (3072,), dtype: float32
98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_weight", shape: (3072, 384), dtype: uint32
98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.out_proj.q_scale", shape: (3072, 96), dtype: float32
98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_weight", shape: (9216, 384), dtype: uint32
98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] [2024-05-26 04:14:23] INFO huggingface_loader.py:166: [Quantized] Parameter: "transformer.h.9.mixer.qkv_proj.q_scale", shape: (9216, 96), dtype: float32
98%|█████████▊| 192/195 [00:12<00:00, 23.45it/s] 100%|██████████| 195/195 [00:12<00:00, 15.39it/s]
[2024-05-26 04:14:23] INFO huggingface_loader.py:196: Unloading HF weight file: /ssd1/rickzhou/models/hf/models--microsoft--Phi-3-mini-4k-instruct/snapshots/5fa34190089f0ee40f9cce3cafc396b89b2e5e83/model-00001-of-00002.safetensors
[2024-05-26 04:14:23] INFO stats.py:76: Time usage: HF loading: 2.551 sec; Pre-quantization mapping: 1.725 sec; Quantization: 2.476 sec
[2024-05-26 04:14:23] INFO stats.py:90: RAM usage: Peak RAM: 9.262 GB. Total bytes loaded from disk: 14.235 GB
[2024-05-26 04:14:24] INFO convert_weight.py:155: Parameter size after quantization: 2.225 GB
[2024-05-26 04:14:24] INFO convert_weight.py:160: Total parameters: 3,821,079,552
[2024-05-26 04:14:24] INFO convert_weight.py:161: Bits per parameter: 5.001
[2024-05-26 04:14:24] INFO convert_weight.py:166: Saved to directory: /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC
All finished, 83 total shards committed, record saved to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /ssd1/rickzhou/models/Phi-3-mini-4k-instruct-q4f32_1-MLC/ndarray-cache-b16.json