/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/TinyLlama-1.1B-Chat-v1.0 --quantization q4f32_1 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC
[2024-06-04 20:07:17] INFO auto_config.py:116: Found model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json
[2024-06-04 20:07:17] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 20:07:17] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (2048)
[2024-06-04 20:07:17] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
[2024-06-04 20:07:17] INFO config.py:107: Overriding max_batch_size from 1 to 80
[2024-06-04 20:07:17] INFO gen_config.py:143: [generation_config.json] Setting bos_token_id: 1
[2024-06-04 20:07:17] INFO gen_config.py:143: [generation_config.json] Setting eos_token_id: 2
[2024-06-04 20:07:17] INFO gen_config.py:143: [generation_config.json] Setting pad_token_id: 0
[2024-06-04 20:07:17] INFO gen_config.py:155: Found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.model. Copying to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/tokenizer.model
[2024-06-04 20:07:17] INFO gen_config.py:155: Found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.json. Copying to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/tokenizer.json
[2024-06-04 20:07:17] INFO gen_config.py:157: Not found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/vocab.json
[2024-06-04 20:07:17] INFO gen_config.py:157: Not found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/merges.txt
[2024-06-04 20:07:17] INFO gen_config.py:157: Not found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/added_tokens.json
[2024-06-04 20:07:17] INFO gen_config.py:155: Found tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer_config.json. Copying to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/tokenizer_config.json
[2024-06-04 20:07:17] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True}
[2024-06-04 20:07:17] INFO gen_config.py:32: [System default] Setting temperature: 1.0
[2024-06-04 20:07:17] INFO gen_config.py:32: [System default] Setting presence_penalty: 0.0
[2024-06-04 20:07:17] INFO gen_config.py:32: [System default] Setting frequency_penalty: 0.0
[2024-06-04 20:07:17] INFO gen_config.py:32: [System default] Setting repetition_penalty: 1.0
[2024-06-04 20:07:17] INFO gen_config.py:32: [System default] Setting top_p: 1.0
[2024-06-04 20:07:17] INFO gen_config.py:223: Dumping configuration file to: /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/mlc-chat-config.json
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/TinyLlama-1.1B-Chat-v1.0 --quantization q4f32_1 --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC
[2024-06-04 20:07:19] INFO auto_config.py:116: Found model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json
[2024-06-04 20:07:20] INFO auto_device.py:79: Found device: cuda:0
[2024-06-04 20:07:21] INFO auto_device.py:88: Not found device: rocm:0
[2024-06-04 20:07:23] INFO auto_device.py:88: Not found device: metal:0
[2024-06-04 20:07:25] INFO auto_device.py:79: Found device: vulkan:0
[2024-06-04 20:07:25] INFO auto_device.py:79: Found device: vulkan:1
[2024-06-04 20:07:25] INFO auto_device.py:79: Found device: vulkan:2
[2024-06-04 20:07:25] INFO auto_device.py:79: Found device: vulkan:3
[2024-06-04 20:07:26] INFO auto_device.py:88: Not found device: opencl:0
[2024-06-04 20:07:26] INFO auto_device.py:35: Using device: cuda:0
[2024-06-04 20:07:26] INFO auto_weight.py:71: Finding weights in: /models/TinyLlama-1.1B-Chat-v1.0
[2024-06-04 20:07:26] INFO auto_weight.py:137: Not found Huggingface PyTorch
[2024-06-04 20:07:27] INFO auto_weight.py:161: Found source weight format: huggingface-safetensor. Source configuration: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json
[2024-06-04 20:07:27] INFO auto_weight.py:107: Using source weight configuration: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json. Use `--source` to override.
[2024-06-04 20:07:27] INFO auto_weight.py:111: Using source weight format: huggingface-safetensor. Use `--source-format` to override.
[2024-06-04 20:07:27] INFO auto_config.py:154: Found model type: llama. Use `--model-type` to override.
[2024-06-04 20:07:27] INFO llama_model.py:52: context_window_size not found in config.json. Falling back to max_position_embeddings (2048)
[2024-06-04 20:07:27] INFO llama_model.py:72: prefill_chunk_size defaults to 2048
Weight conversion with arguments:
  --config          /models/TinyLlama-1.1B-Chat-v1.0/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      llama
  --device          cuda:0
  --source          /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json
  --source-format   huggingface-safetensor
  --output          /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC
Start storing to cache /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC

  0%|          | 0/135 [00:00<?, ?it/s]
                                       
[2024-06-04 20:07:30] INFO huggingface_loader.py:185: Loading HF parameters from: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors

  0%|          | 0/135 [00:00<?, ?it/s]
                                       
[2024-06-04 20:07:32] INFO group_quantization.py:217: Compiling quantize function for key: ((32000, 2048), float32, cuda, axis=1, output_transpose=False)

  0%|          | 0/135 [00:02<?, ?it/s]
                                       
[2024-06-04 20:07:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_weight", shape: (32000, 256), dtype: uint32

  0%|          | 0/135 [00:03<?, ?it/s]
                                       
[2024-06-04 20:07:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "lm_head.q_scale", shape: (32000, 64), dtype: float32

  0%|          | 0/135 [00:03<?, ?it/s]
  1%|          | 1/135 [00:03<07:24,  3.32s/it]
                                               
[2024-06-04 20:07:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_weight", shape: (32000, 256), dtype: uint32

  1%|          | 1/135 [00:03<07:24,  3.32s/it]
                                               
[2024-06-04 20:07:33] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.embed_tokens.q_scale", shape: (32000, 64), dtype: float32

  1%|          | 1/135 [00:03<07:24,  3.32s/it]
  1%|▏         | 2/135 [00:03<03:13,  1.46s/it]
                                               
[2024-06-04 20:07:33] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.input_layernorm.weight", shape: (2048,), dtype: float32

  1%|▏         | 2/135 [00:03<03:13,  1.46s/it]
                                               
[2024-06-04 20:07:33] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 5632), float32, cuda, axis=1, output_transpose=False)

  1%|▏         | 2/135 [00:03<03:13,  1.46s/it]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

  1%|▏         | 2/135 [00:03<03:13,  1.46s/it]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

  1%|▏         | 2/135 [00:03<03:13,  1.46s/it]
  3%|▎         | 4/135 [00:03<01:29,  1.47it/s]
                                               
[2024-06-04 20:07:34] INFO group_quantization.py:217: Compiling quantize function for key: ((11264, 2048), float32, cuda, axis=1, output_transpose=False)

  3%|▎         | 4/135 [00:03<01:29,  1.47it/s]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

  3%|▎         | 4/135 [00:04<01:29,  1.47it/s]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

  3%|▎         | 4/135 [00:04<01:29,  1.47it/s]
  4%|▎         | 5/135 [00:04<01:22,  1.57it/s]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.0.post_attention_layernorm.weight", shape: (2048,), dtype: float32

  4%|▎         | 5/135 [00:04<01:22,  1.57it/s]
                                               
[2024-06-04 20:07:34] INFO group_quantization.py:217: Compiling quantize function for key: ((2560, 2048), float32, cuda, axis=1, output_transpose=False)

  4%|▎         | 5/135 [00:04<01:22,  1.57it/s]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

  4%|▎         | 5/135 [00:04<01:22,  1.57it/s]
                                               
[2024-06-04 20:07:34] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

  4%|▎         | 5/135 [00:04<01:22,  1.57it/s]
  5%|▌         | 7/135 [00:04<00:56,  2.28it/s]
                                               
[2024-06-04 20:07:34] INFO group_quantization.py:217: Compiling quantize function for key: ((2048, 2048), float32, cuda, axis=1, output_transpose=False)

  5%|▌         | 7/135 [00:04<00:56,  2.28it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

  5%|▌         | 7/135 [00:05<00:56,  2.28it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.0.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

  5%|▌         | 7/135 [00:05<00:56,  2.28it/s]
  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.input_layernorm.weight", shape: (2048,), dtype: float32

  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
                                               
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

  6%|▌         | 8/135 [00:05<00:55,  2.30it/s]
  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.1.post_attention_layernorm.weight", shape: (2048,), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.1.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.input_layernorm.weight", shape: (2048,), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

  8%|▊         | 11/135 [00:05<00:28,  4.32it/s]
 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.10.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.10.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.input_layernorm.weight", shape: (2048,), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 13%|█▎        | 17/135 [00:05<00:12,  9.39it/s]
 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.11.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.11.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.input_layernorm.weight", shape: (2048,), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 17%|█▋        | 23/135 [00:05<00:07, 15.03it/s]
 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.12.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.12.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.input_layernorm.weight", shape: (2048,), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:35] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 21%|██▏       | 29/135 [00:05<00:05, 20.91it/s]
 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.13.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.13.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.input_layernorm.weight", shape: (2048,), dtype: float32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 26%|██▌       | 35/135 [00:05<00:03, 26.60it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 26%|██▌       | 35/135 [00:06<00:03, 26.60it/s]
 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.14.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.14.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.input_layernorm.weight", shape: (2048,), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 30%|███       | 41/135 [00:06<00:02, 31.80it/s]
 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.15.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.15.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.input_layernorm.weight", shape: (2048,), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 35%|███▍      | 47/135 [00:06<00:02, 36.29it/s]
 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.16.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.16.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.input_layernorm.weight", shape: (2048,), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 39%|███▉      | 53/135 [00:06<00:02, 40.11it/s]
 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.17.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.17.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.input_layernorm.weight", shape: (2048,), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 44%|████▎     | 59/135 [00:06<00:01, 42.90it/s]
 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.18.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.18.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.input_layernorm.weight", shape: (2048,), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 48%|████▊     | 65/135 [00:06<00:01, 45.23it/s]
 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.19.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.19.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.input_layernorm.weight", shape: (2048,), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 53%|█████▎    | 71/135 [00:06<00:01, 46.99it/s]
 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.2.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.2.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.input_layernorm.weight", shape: (2048,), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 57%|█████▋    | 77/135 [00:06<00:01, 48.15it/s]
 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.20.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.20.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.input_layernorm.weight", shape: (2048,), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:36] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 61%|██████▏   | 83/135 [00:06<00:01, 48.95it/s]
 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.21.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.21.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.input_layernorm.weight", shape: (2048,), dtype: float32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 66%|██████▌   | 89/135 [00:06<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 66%|██████▌   | 89/135 [00:07<00:00, 49.41it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 66%|██████▌   | 89/135 [00:07<00:00, 49.41it/s]
 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.3.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.3.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.input_layernorm.weight", shape: (2048,), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
                                                
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 70%|███████   | 95/135 [00:07<00:00, 49.77it/s]
 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.4.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.4.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.input_layernorm.weight", shape: (2048,), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 75%|███████▍  | 101/135 [00:07<00:00, 50.25it/s]
 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.5.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.5.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.input_layernorm.weight", shape: (2048,), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 79%|███████▉  | 107/135 [00:07<00:00, 50.64it/s]
 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.6.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.6.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.input_layernorm.weight", shape: (2048,), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 84%|████████▎ | 113/135 [00:07<00:00, 50.97it/s]
 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.7.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.7.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.input_layernorm.weight", shape: (2048,), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 88%|████████▊ | 119/135 [00:07<00:00, 51.27it/s]
 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.8.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.8.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.input_layernorm.weight", shape: (2048,), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_weight", shape: (2048, 704), dtype: uint32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.down_proj.q_scale", shape: (2048, 176), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_weight", shape: (11264, 256), dtype: uint32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.mlp.gate_up_proj.q_scale", shape: (11264, 64), dtype: float32

 93%|█████████▎| 125/135 [00:07<00:00, 50.68it/s]
 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.layers.9.post_attention_layernorm.weight", shape: (2048,), dtype: float32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_weight", shape: (2560, 256), dtype: uint32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.qkv_proj.q_scale", shape: (2560, 64), dtype: float32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_weight", shape: (2048, 256), dtype: uint32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:167: [Quantized] Parameter: "model.layers.9.self_attn.o_proj.q_scale", shape: (2048, 64), dtype: float32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
                                                 
[2024-06-04 20:07:37] INFO huggingface_loader.py:175: [Not quantized] Parameter: "model.norm.weight", shape: (2048,), dtype: float32

 97%|█████████▋| 131/135 [00:07<00:00, 50.69it/s]
100%|██████████| 135/135 [00:07<00:00, 17.29it/s]
[2024-06-04 20:07:37] INFO huggingface_loader.py:197: Unloading HF weight file: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors
[2024-06-04 20:07:38] INFO stats.py:77: Time usage: HF loading: 2.395 sec; Pre-quantization mapping: 0.820 sec; Quantization: 2.709 sec
[2024-06-04 20:07:38] INFO stats.py:91: RAM usage: Peak RAM: 4.098 GB. Total bytes loaded from disk: 4.098 GB
[2024-06-04 20:07:38] INFO convert_weight.py:155: Parameter size after quantization: 0.641 GB
[2024-06-04 20:07:38] INFO convert_weight.py:160: Total parameters: 1,100,048,384
[2024-06-04 20:07:38] INFO convert_weight.py:161: Bits per parameter: 5.002
[2024-06-04 20:07:38] INFO convert_weight.py:166: Saved to directory: /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC

All finished, 24 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/ndarray-cache.json
Also saved a bf16 record to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q4f32_1-MLC/ndarray-cache-b16.json