| /opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC | |
| [2024-06-04 20:08:25] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json | |
| [2024-06-04 20:08:25] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. | |
| [2024-06-04 20:08:25] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048) | |
| [2024-06-04 20:08:25] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 | |
| [2024-06-04 20:08:25] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80 | |
| [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 1 | |
| [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: 2 | |
| [2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.model. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.model[0m | |
| [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.json[0m | |
| [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/vocab.json | |
| [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/merges.txt | |
| [2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/added_tokens.json | |
| [2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer_config.json[0m | |
| [2024-06-04 20:08:25] 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 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtop_p[0m: 1.0 | |
| [2024-06-04 20:08:25] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/mlc-chat-config.json[0m | |
| /opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC | |
| [2024-06-04 20:08:27] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json | |
| [2024-06-04 20:08:28] INFO auto_device.py:79: [92mFound[0m device: cuda:0 | |
| [2024-06-04 20:08:30] INFO auto_device.py:88: [91mNot found[0m device: rocm:0 | |
| [2024-06-04 20:08:31] INFO auto_device.py:88: [91mNot found[0m device: metal:0 | |
| [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:0 | |
| [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:1 | |
| [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:2 | |
| [2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:3 | |
| [2024-06-04 20:08:34] INFO auto_device.py:88: [91mNot found[0m device: opencl:0 | |
| [2024-06-04 20:08:34] INFO auto_device.py:35: Using device: [1mcuda:0[0m | |
| [2024-06-04 20:08:34] INFO auto_weight.py:71: Finding weights in: /models/TinyLlama-1.1B-Chat-v1.0 | |
| [2024-06-04 20:08:34] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch | |
| [2024-06-04 20:08:34] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json | |
| [2024-06-04 20:08:34] INFO auto_weight.py:107: Using source weight configuration: [1m/models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json[0m. Use `--source` to override. | |
| [2024-06-04 20:08:34] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override. | |
| [2024-06-04 20:08:34] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override. | |
| [2024-06-04 20:08:34] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048) | |
| [2024-06-04 20:08:34] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048 | |
| [1mWeight conversion with arguments:[0m | |
| [1m--config[0m /models/TinyLlama-1.1B-Chat-v1.0/config.json | |
| [1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16') | |
| [1m--model-type[0m llama | |
| [1m--device[0m cuda:0 | |
| [1m--source[0m /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json | |
| [1m--source-format[0m huggingface-safetensor | |
| [1m--output[0m /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC | |
| Start storing to cache /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC | |
| 0%| | 0/135 [00:00<?, ?it/s] [2024-06-04 20:08:36] 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 20:08:39] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mlm_head.weight[0m", shape: (32000, 2048), dtype: float16 | |
| 0%| | 0/135 [00:03<?, ?it/s] 1%| | 1/135 [00:04<09:19, 4.17s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.embed_tokens.weight[0m", shape: (32000, 2048), dtype: float16 | |
| 1%| | 1/135 [00:04<09:19, 4.17s/it] 1%|▏ | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 1%|▏ | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:40] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 1%|▏ | 2/135 [00:04<04:37, 2.09s/it] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 1%|▏ | 2/135 [00:04<04:37, 2.09s/it] 4%|▎ | 5/135 [00:05<01:27, 1.48it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 4%|▎ | 5/135 [00:05<01:27, 1.48it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 4%|▎ | 5/135 [00:05<01:27, 1.48it/s] 5%|▌ | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.0.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 5%|▌ | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 5%|▌ | 7/135 [00:05<00:54, 2.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 5%|▌ | 7/135 [00:05<00:54, 2.36it/s] 7%|▋ | 10/135 [00:05<00:30, 4.08it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 7%|▋ | 10/135 [00:05<00:30, 4.08it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 7%|▋ | 10/135 [00:05<00:30, 4.08it/s] 9%|▉ | 12/135 [00:05<00:24, 4.93it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 9%|▉ | 12/135 [00:05<00:24, 4.93it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.1.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 9%|▉ | 12/135 [00:05<00:24, 4.93it/s] 10%|█ | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 10%|█ | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 10%|█ | 14/135 [00:05<00:19, 6.36it/s] [2024-06-04 20:08:41] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 10%|█ | 14/135 [00:05<00:19, 6.36it/s] 13%|█▎ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 13%|█▎ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 13%|█▎ | 17/135 [00:05<00:15, 7.70it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.10.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 13%|█▎ | 17/135 [00:06<00:15, 7.70it/s] 15%|█▍ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 15%|█▍ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 15%|█▍ | 20/135 [00:06<00:11, 10.40it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 15%|█▍ | 20/135 [00:06<00:11, 10.40it/s] 17%|█▋ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 17%|█▋ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 17%|█▋ | 23/135 [00:06<00:11, 10.16it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.11.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 17%|█▋ | 23/135 [00:06<00:11, 10.16it/s] 19%|█▉ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 19%|█▉ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 19%|█▉ | 26/135 [00:06<00:08, 12.86it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 19%|█▉ | 26/135 [00:06<00:08, 12.86it/s] 21%|██▏ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 21%|██▏ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 21%|██▏ | 29/135 [00:06<00:08, 12.28it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.12.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 21%|██▏ | 29/135 [00:06<00:08, 12.28it/s] 24%|██▎ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:42] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 24%|██▎ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 24%|██▎ | 32/135 [00:06<00:06, 14.78it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 24%|██▎ | 32/135 [00:07<00:06, 14.78it/s] 26%|██▌ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 26%|██▌ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 26%|██▌ | 35/135 [00:07<00:07, 12.60it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.13.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 26%|██▌ | 35/135 [00:07<00:07, 12.60it/s] 28%|██▊ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 28%|██▊ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 28%|██▊ | 38/135 [00:07<00:06, 15.07it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 28%|██▊ | 38/135 [00:07<00:06, 15.07it/s] 30%|███ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 30%|███ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 30%|███ | 41/135 [00:07<00:07, 13.33it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.14.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 30%|███ | 41/135 [00:07<00:07, 13.33it/s] 33%|███▎ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 33%|███▎ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 33%|███▎ | 44/135 [00:07<00:05, 15.58it/s] [2024-06-04 20:08:43] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 33%|███▎ | 44/135 [00:07<00:05, 15.58it/s] 35%|███▍ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 35%|███▍ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 35%|███▍ | 47/135 [00:08<00:06, 13.02it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.15.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 35%|███▍ | 47/135 [00:08<00:06, 13.02it/s] 37%|███▋ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 37%|███▋ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 37%|███▋ | 50/135 [00:08<00:05, 15.39it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 37%|███▋ | 50/135 [00:08<00:05, 15.39it/s] 39%|███▉ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 39%|███▉ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 39%|███▉ | 53/135 [00:08<00:05, 13.68it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.16.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 39%|███▉ | 53/135 [00:08<00:05, 13.68it/s] 41%|████▏ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 41%|████▏ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 41%|████▏ | 56/135 [00:08<00:04, 15.94it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 41%|████▏ | 56/135 [00:08<00:04, 15.94it/s] 44%|████▎ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 44%|████▎ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 44%|████▎ | 59/135 [00:08<00:05, 13.32it/s] [2024-06-04 20:08:44] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.17.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 44%|████▎ | 59/135 [00:08<00:05, 13.32it/s] 46%|████▌ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 46%|████▌ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 46%|████▌ | 62/135 [00:08<00:04, 15.85it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 46%|████▌ | 62/135 [00:09<00:04, 15.85it/s] 48%|████▊ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 48%|████▊ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 48%|████▊ | 65/135 [00:09<00:05, 13.89it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.18.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 48%|████▊ | 65/135 [00:09<00:05, 13.89it/s] 50%|█████ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 50%|█████ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 50%|█████ | 68/135 [00:09<00:04, 16.19it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 50%|█████ | 68/135 [00:09<00:04, 16.19it/s] 53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.19.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s] 55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:45] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s] 57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.2.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s] 59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s] 61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.20.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s] 64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s] 66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:46] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.21.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s] 68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 68%|██████▊ | 92/135 [00:11<00:02, 16.18it/s] 70%|███████ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 70%|███████ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 70%|███████ | 95/135 [00:11<00:02, 13.39it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.3.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 70%|███████ | 95/135 [00:11<00:02, 13.39it/s] 73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s] 75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.4.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s] 77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:47] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s] 79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.5.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s] 81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s] 84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.6.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s] 86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s] 88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:48] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.7.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s] 90%|█████████ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 90%|█████████ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 90%|█████████ | 122/135 [00:12<00:00, 16.30it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 90%|█████████ | 122/135 [00:13<00:00, 16.30it/s] 93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.8.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s] 95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.input_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.down_proj.weight[0m", shape: (2048, 5632), dtype: float16 | |
| 95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.mlp.gate_up_proj.weight[0m", shape: (11264, 2048), dtype: float16 | |
| 95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s] 97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.post_attention_layernorm.weight[0m", shape: (2048,), dtype: float16 | |
| 97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.qkv_proj.weight[0m", shape: (2560, 2048), dtype: float16 | |
| 97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.layers.9.self_attn.o_proj.weight[0m", shape: (2048, 2048), dtype: float16 | |
| 97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s] 99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s] [2024-06-04 20:08:49] INFO huggingface_loader.py:175: [Not quantized] Parameter: "[1mmodel.norm.weight[0m", shape: (2048,), dtype: float16 | |
| 99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s] 100%|██████████| 135/135 [00:13<00:00, 9.82it/s] | |
| [2024-06-04 20:08:49] INFO huggingface_loader.py:197: Unloading HF weight file: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors | |
| [2024-06-04 20:08:50] INFO stats.py:77: [92mTime usage[0m: HF loading: 3.678 sec; Pre-quantization mapping: 4.070 sec; Quantization: 0.000 sec | |
| [2024-06-04 20:08:50] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 4.098 GB. Total bytes loaded from disk: 4.098 GB | |
| [2024-06-04 20:08:50] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 2.049 GB | |
| [2024-06-04 20:08:50] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,100,048,384 | |
| [2024-06-04 20:08:50] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000 | |
| [2024-06-04 20:08:50] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC[0m | |
| All finished, 58 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/ndarray-cache.json | |