diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/mlc-chat-config.json b/mlc-chat-config.json new file mode 100644 index 0000000000000000000000000000000000000000..6151c7d29b918cef87353e6ff3c4cb46bb1a6382 --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,86 @@ +{ + "version": "0.1.0", + "model_type": "gemma2", + "quantization": "q0f32", + "model_config": { + "hidden_size": 2304, + "intermediate_size": 9216, + "attention_bias": false, + "num_attention_heads": 8, + "num_key_value_heads": 4, + "head_dim": 256, + "num_hidden_layers": 26, + "rms_norm_eps": 1e-06, + "vocab_size": 256000, + "hidden_activation": "gelu_pytorch_tanh", + "position_embedding_base": 10000.0, + "context_window_size": 4096, + "prefill_chunk_size": 2048, + "tensor_parallel_shards": 1, + "max_batch_size": 80, + "attn_logit_softcapping": 50.0, + "final_logit_softcapping": 30.0, + "query_pre_attn_scalar": 256, + "sliding_window": 4096 + }, + "vocab_size": 256000, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 2048, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 1.0, + "tokenizer_files": [ + "tokenizer.model", + "tokenizer.json", + "tokenizer_config.json" + ], + "tokenizer_info": { + "token_postproc_method": "byte_fallback", + "prepend_space_in_encode": false, + "strip_space_in_decode": false + }, + "conv_template": { + "name": "gemma_instruction", + "system_template": "{system_message}", + "system_message": "", + "system_prefix_token_ids": [ + 2 + ], + "add_role_after_system_message": true, + "roles": { + "user": "user", + "assistant": "model" + }, + "role_templates": { + "user": "{user_message}", + "assistant": "{assistant_message}", + "tool": "{tool_message}" + }, + "messages": [], + "seps": [ + "\n" + ], + "role_content_sep": "\n", + "role_empty_sep": "\n", + "stop_str": [ + "" + ], + "stop_token_ids": [ + 1, + 107 + ], + "function_string": "", + "use_function_calling": false + }, + "pad_token_id": 0, + "bos_token_id": 2, + "eos_token_id": [ + 1, + 107 + ] +} \ No newline at end of file diff --git a/ndarray-cache-b16.json b/ndarray-cache-b16.json new file mode 100644 index 0000000000000000000000000000000000000000..1e1fac37616486f1503d31231912e21d70f8b151 --- /dev/null +++ b/ndarray-cache-b16.json @@ -0,0 +1,2854 @@ +{ + "metadata": { + "ParamSize": 210, + "ParamBytes": 10457367552.0, + "BitsPerParam": 32.0 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 1179648000, + "records": [ + { + "name": "model.embed_tokens.weight", + "shape": [ + 256000, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 1179648000, + "byteOffset": 0 + } + ], + "md5sum": "62204215d5097751ae26290c6bb95b96" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "c763984f66d00a44b61d9d51bb02cae3" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "3bdc8fa3b17a013ac90cc3f7e8c224f5" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5f67ca7508419bf6966c9e97e8aaf527" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "90430c831dbbf4e397210bc71f7f8d64" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 18874368, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 0 + } + ], + "md5sum": "de11a3b74f47ba1430cea747c85a6329" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 28348416, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 4608 + }, + { + "name": "model.layers.0.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9216 + }, + { + "name": "model.layers.0.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 13824 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 18432 + }, + { + "name": "model.layers.0.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 18892800 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 28329984 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 28334592 + }, + { + "name": "model.layers.1.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 28339200 + }, + { + "name": "model.layers.1.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 28343808 + } + ], + "md5sum": "2802701476a76506baf97b06bba0f746" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "a86ababa0fb0ead8224dbe57698dc227" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "e0e9c4c093911fd7761bc8c88618ca3d" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.10.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.10.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "b3ee22d2770fb9b93347bac59152fdb0" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "104cd3f16f8c0deccdb79139a4d2631b" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "8b2e52123607a5ff981b62fda42f3f42" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.11.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.11.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "fcbcea3d3de6a1b10e491e7a44740f14" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "026c0a4793b398dcc65c7af9ae0f39d5" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7f0f493c428fa02b1851b8ac5d56cbce" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.12.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.12.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5af70b42143c0a2f287bf3cd2548c747" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "9216c08b71172fc715210037e81a0411" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7e8664fb062a5434da3e1d2ee5b9ad9b" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.13.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.13.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "1c5ed6a38c2cadc96100180521a0d678" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "88225258d479cb2800e6a9d7316aae6c" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "8f2fafa637abea77ee1ba268c1575e56" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.14.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.14.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "150300b9bda9b6184ac2b7174ab47322" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "2139b50f9876756a97d4d4def69b4b6d" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c36aa796e244e0883c9235aabff09488" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.15.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.15.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "cd6e2f65f8ce9520f67b6948e061f7f5" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "e50de57dafc9d753b74392d35d92b04f" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7228aa52df7bf064e322299345dbc98e" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.16.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.16.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "773544624d07ead5a304cc9278eacb6c" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "b115593000e031367512ff2a2bef0dab" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "1aeb084857b23899155a47aa17ce1374" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.17.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.17.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "cdc753982202900bf9c850174d7a8525" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "29cc3d52a9e33240234b71c0bdeea9a7" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "d13fb9f509d99fc103a7224473d6bf65" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.18.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.18.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "f7175237b75ad08b569dbcdf61c1ffff" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5fedcaa2e76818925314847463f92706" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "d61ef76e5d20fcf58d3428f857f39ed9" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.19.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.19.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "84a15de2559c5df3e11509196fda3730" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "d5e1b0beb311ea7cae3454052509c21e" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "80617fc9a55f8437fb2c374013b3ffd7" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.2.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.2.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "e50bf9d12b20717933715e74cbeedd6b" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "99a08e5a05761c33a3c57754d1391745" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "5a0ea983928acba60569714fbf50079c" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.20.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.20.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "73942feec2c47358cbf0dfab58d14bd6" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "dbe4a8f46fd21d8bf21625a916637eea" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "27f6c56977a3d53f12f517c33a7ae45d" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.21.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.21.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "59e5c0cb1381e8c78d816b3ec492ec5e" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "d823340637874eaff98864500b40e983" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "5add29e1699e76e24e95bfdfb1d6f466" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.22.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.22.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "712c4ea3c91ee3a0b3cf17b44d2d5fd9" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "94485ce84c951931a96a7dd600be609a" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "4e6767a86c6289ddafefb902fb311890" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.23.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.23.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "af0fff5969b256b9d7391b3907ae4839" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "b4e94b9873512cc6b3535fe2028988f7" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 28311552, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9437184 + } + ], + "md5sum": "942bbbcb26ca333824d079fc5351313b" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5c99e916ea1e05424fad902d8fca3255" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c58faf8bfe09b4135fc2341d827c0f56" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.3.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.3.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5d260f2ade30fb5ad195cee460c3e83f" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "cbd746232d67e9b597ed8ef5b6f0c89b" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "2c7ae43950657786930cd79027138869" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.4.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.4.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "029f24d418ff2b2a502d6e5c49670798" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "61f71048d0529605f7ac20601cc0fdce" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "15c5279bf3da9f6f8d165e2b7d98b768" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.5.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.5.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "175bd30e9196e7eb4cc742e6ff9916e6" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "cb46a0804e54e366b949a6857c2a8f45" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "a8397b6a4bf904a8c9f23e8fde4ef3b4" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.6.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.6.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5d57b4f7c069864b369feea71009a785" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "8d5477556d97018c91402179bc28d25e" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "777c4af18d26abac1975eef88e2bc984" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.7.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.7.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "787dab15288956bb41ead752a08355ad" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "adfd9c0cb3363492b0a80916becbaed1" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c760588decd97f1bf41973802d3c3624" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.8.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.8.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "3ff1d1d3e15343053b4a7ec38b169e55" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "b9f576137fb67786e3a745aa951f64bf" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "cb92beeb40aa2ec7eb1e3c7b8c6f42d6" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.9.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.9.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "b80587270e3afff1e7bbb68d85f58aba" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "52f57bf19dee44be665a7e35807b7530" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5910b60613c521066a125487522f1815" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "688b1a1935ec355712b70083b6b1af9d" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 28348416, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.24.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.24.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9455616 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9460224 + }, + { + "name": "model.layers.25.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9464832 + }, + { + "name": "model.layers.25.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9469440 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 18874368, + "byteOffset": 9474048 + } + ], + "md5sum": "3c384d20a4c9619a47e975a21c8666a0" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 9441792, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.norm.weight", + "shape": [ + 2304 + ], + "dtype": "bfloat16", + "format": "raw", + "nbytes": 4608, + "byteOffset": 9437184 + } + ], + "md5sum": "363eeb447d8c8d38d31c3f544cbfee83" + } + ] +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..0e30d7e564257325ed1bd4ff6ce3f8cf779a9667 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,2854 @@ +{ + "metadata": { + "ParamSize": 210, + "ParamBytes": 10457367552.0, + "BitsPerParam": 32.0 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 1179648000, + "records": [ + { + "name": "model.embed_tokens.weight", + "shape": [ + 256000, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 1179648000, + "byteOffset": 0 + } + ], + "md5sum": "62204215d5097751ae26290c6bb95b96" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "c763984f66d00a44b61d9d51bb02cae3" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "3bdc8fa3b17a013ac90cc3f7e8c224f5" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5f67ca7508419bf6966c9e97e8aaf527" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "90430c831dbbf4e397210bc71f7f8d64" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 18874368, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 0 + } + ], + "md5sum": "de11a3b74f47ba1430cea747c85a6329" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 28348416, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 4608 + }, + { + "name": "model.layers.0.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9216 + }, + { + "name": "model.layers.0.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 13824 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 18432 + }, + { + "name": "model.layers.0.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 18892800 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 28329984 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 28334592 + }, + { + "name": "model.layers.1.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 28339200 + }, + { + "name": "model.layers.1.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 28343808 + } + ], + "md5sum": "2802701476a76506baf97b06bba0f746" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "a86ababa0fb0ead8224dbe57698dc227" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "e0e9c4c093911fd7761bc8c88618ca3d" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.10.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.10.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "b3ee22d2770fb9b93347bac59152fdb0" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "104cd3f16f8c0deccdb79139a4d2631b" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "8b2e52123607a5ff981b62fda42f3f42" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.11.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.11.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "fcbcea3d3de6a1b10e491e7a44740f14" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "026c0a4793b398dcc65c7af9ae0f39d5" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7f0f493c428fa02b1851b8ac5d56cbce" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.12.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.12.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5af70b42143c0a2f287bf3cd2548c747" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "9216c08b71172fc715210037e81a0411" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7e8664fb062a5434da3e1d2ee5b9ad9b" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.13.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.13.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "1c5ed6a38c2cadc96100180521a0d678" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "88225258d479cb2800e6a9d7316aae6c" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "8f2fafa637abea77ee1ba268c1575e56" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.14.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.14.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "150300b9bda9b6184ac2b7174ab47322" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "2139b50f9876756a97d4d4def69b4b6d" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c36aa796e244e0883c9235aabff09488" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.15.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.15.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "cd6e2f65f8ce9520f67b6948e061f7f5" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "e50de57dafc9d753b74392d35d92b04f" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "7228aa52df7bf064e322299345dbc98e" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.16.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.16.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "773544624d07ead5a304cc9278eacb6c" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "b115593000e031367512ff2a2bef0dab" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "1aeb084857b23899155a47aa17ce1374" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.17.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.17.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "cdc753982202900bf9c850174d7a8525" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "29cc3d52a9e33240234b71c0bdeea9a7" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "d13fb9f509d99fc103a7224473d6bf65" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.18.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.18.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "f7175237b75ad08b569dbcdf61c1ffff" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5fedcaa2e76818925314847463f92706" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "d61ef76e5d20fcf58d3428f857f39ed9" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.19.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.19.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "84a15de2559c5df3e11509196fda3730" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "d5e1b0beb311ea7cae3454052509c21e" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "80617fc9a55f8437fb2c374013b3ffd7" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.2.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.2.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "e50bf9d12b20717933715e74cbeedd6b" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "99a08e5a05761c33a3c57754d1391745" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "5a0ea983928acba60569714fbf50079c" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.20.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.20.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "73942feec2c47358cbf0dfab58d14bd6" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "dbe4a8f46fd21d8bf21625a916637eea" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "27f6c56977a3d53f12f517c33a7ae45d" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.21.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.21.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "59e5c0cb1381e8c78d816b3ec492ec5e" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "d823340637874eaff98864500b40e983" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "5add29e1699e76e24e95bfdfb1d6f466" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.22.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.22.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "712c4ea3c91ee3a0b3cf17b44d2d5fd9" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "94485ce84c951931a96a7dd600be609a" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "4e6767a86c6289ddafefb902fb311890" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.23.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.23.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "af0fff5969b256b9d7391b3907ae4839" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "b4e94b9873512cc6b3535fe2028988f7" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 28311552, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9437184 + } + ], + "md5sum": "942bbbcb26ca333824d079fc5351313b" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5c99e916ea1e05424fad902d8fca3255" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c58faf8bfe09b4135fc2341d827c0f56" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.3.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.3.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5d260f2ade30fb5ad195cee460c3e83f" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "cbd746232d67e9b597ed8ef5b6f0c89b" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "2c7ae43950657786930cd79027138869" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.4.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.4.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "029f24d418ff2b2a502d6e5c49670798" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "61f71048d0529605f7ac20601cc0fdce" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "15c5279bf3da9f6f8d165e2b7d98b768" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.5.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.5.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "175bd30e9196e7eb4cc742e6ff9916e6" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "cb46a0804e54e366b949a6857c2a8f45" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "a8397b6a4bf904a8c9f23e8fde4ef3b4" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.6.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.6.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "5d57b4f7c069864b369feea71009a785" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "8d5477556d97018c91402179bc28d25e" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "777c4af18d26abac1975eef88e2bc984" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.7.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.7.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "787dab15288956bb41ead752a08355ad" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "adfd9c0cb3363492b0a80916becbaed1" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "c760588decd97f1bf41973802d3c3624" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.8.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.8.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "3ff1d1d3e15343053b4a7ec38b169e55" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "b9f576137fb67786e3a745aa951f64bf" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "cb92beeb40aa2ec7eb1e3c7b8c6f42d6" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 28329984, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.9.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.9.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9455616 + } + ], + "md5sum": "b80587270e3afff1e7bbb68d85f58aba" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "52f57bf19dee44be665a7e35807b7530" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 42467328, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.weight", + "shape": [ + 2304, + 9216 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 42467328, + "byteOffset": 0 + } + ], + "md5sum": "5910b60613c521066a125487522f1815" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 84934656, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.weight", + "shape": [ + 18432, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 84934656, + "byteOffset": 0 + } + ], + "md5sum": "688b1a1935ec355712b70083b6b1af9d" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 28348416, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9441792 + }, + { + "name": "model.layers.24.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9446400 + }, + { + "name": "model.layers.24.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9451008 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9455616 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9460224 + }, + { + "name": "model.layers.25.post_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9464832 + }, + { + "name": "model.layers.25.pre_feedforward_layernorm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9469440 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.weight", + "shape": [ + 4096, + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 18874368, + "byteOffset": 9474048 + } + ], + "md5sum": "3c384d20a4c9619a47e975a21c8666a0" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 9441792, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.weight", + "shape": [ + 2304, + 2048 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 9437184, + "byteOffset": 0 + }, + { + "name": "model.norm.weight", + "shape": [ + 2304 + ], + "dtype": "float32", + "format": "f32-to-bf16", + "nbytes": 4608, + "byteOffset": 9437184 + } + ], + "md5sum": "363eeb447d8c8d38d31c3f544cbfee83" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..8be6f65ddb02be298e022315c4bad2cca43a58ed --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:257b431bf2f375f6a2ea6dea7bff6793bdbdc1647cbe363aaa31da079f516690 +size 1179648000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..435e42bf719a80cd4d094d03de7b61667deb3ea6 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1e03ec1d791e1a51d6e6a3168a771680cdb2e7b4c950a929f1c9d8e96b634f1 +size 42467328 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..af287421e1406a76e796908a6758f060270275c0 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49857f49ab9d6faa3369fcf893ff257b3eb609c0ccd7de0eacd8582687da2b96 +size 42467328 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..32ef334f67e5e298a9c1b5d8de897bd7a82c4695 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e3cc3119b952034bf1319e29e1ab927e77c894990e0af40a7186844bf5e3d9 +size 84934656 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..787e032d7483cf4950f2563adc775c5e2f310dd3 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e672ab09b744b6af4e68782ebb5df832d4ce3d30b9e43e29d9bbad90030c5846 +size 28329984 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..c6cf0fe0e40945339393b8e59f2cc6295031df4e --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13214c4d1bc511012135439ab3f095db8e81cdb5b4953f333b50423316e7d00a +size 42467328 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c24cee75de69134348b29be220177bd0ed08a9f --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc922e4e48d8f7323753f06a8cf65ad521ffda958cb46c3854e5d95b9ab90c0 +size 84934656 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..78538562e9bb73474fa6c11fc32f3895137dcc0f --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b340d8103aebd6631d35bd254e369fd5c4d4b4d0ecc1f7ef6bbed9aa9110dd2 +size 28329984 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..52dc9531fdeb43234387ee505a25c0553328a013 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b58258aca81141b5acfba999aba7b3d3e711d13aa61bf83590266f8be719085 +size 42467328 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..fb458d51377de0d9150cbd0b24f29f69a9c601c1 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68fb9036c3dd084a2cc0d326346a0f9ebe2d0ffc7badeedd664345ba9c238f6c +size 84934656 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..6264afc9a86460daa458a52adf82f0c8ee946bc2 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c3d3a6680925400a928ade33c3c46dc0b9cac5f51d228ed58b1b858f798438 +size 28329984 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..5fde34f92ec705bf04f53384af810ffdef703689 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4172db4fa3345d5031140a8ea1ebc5ac37ecd2b57e1d5fa711ddff232eb2153e +size 42467328 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..87c6672b1c34954c66ad564505d7294655c7d30b --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd20eeb68a86ba52044e8a7e274c54d82ecb505e9e91cf362929d6ad6e87d74 +size 84934656 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..35b4de3871dd89379fd8f10d307122081c7eae93 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f190c8806be79621cfc99c5400c97cee55e213524622d0a3dda1d6fa458e2649 +size 84934656 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cd9a8513e5bc515d12825851e408d4a96598451 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a9f196842f554705f2a68041cb7e2be41e95a51a76e045d9d8e979c0a3b24f +size 28329984 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..72d8e8e06e6d3f66caa78926b0ec107894959e6d --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367fdd71e717d410689392d000b85e90f7206bf527994ba463578414c9d6a60e +size 42467328 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..896449c7149681863589e2da1c84fad3ab735a49 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d061fc9dc74caad174c44238d19856742a7edbcb27a5158ec943ee4882b990b +size 84934656 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..653eea91734680d862fa2f5038d88ae228f70ddd --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a250b8a52b322d7cc363dc48680ec139b7c748d7285bec9fbc687fbb7da67513 +size 28329984 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..67e14ad63f43c21b4b7292f35996898d628e805f --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb59c8d9f42dcb97fb9aeeb8324c2ca37bf99fe8b6f806239083715bd5cf345 +size 42467328 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..536d7b90566c9a12686f11e7f6db70217c9eae41 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98edd1dc79178e3101dd6bf9a6c66aa0e444b6548e04b2136cc2faf75801495 +size 84934656 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..3aa2ba101014247e7b36caee9fb8bb449d601bd1 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94ae68c7566e2d3ff59c1c844fed04b7f298d1a094cf04fa2fb0a4d5169685e7 +size 28329984 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..59054377ede3428b3345d0c0e5bb77f493b92dbe --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4be582ad38c57277b8dd4de7894030e60d82ce3968518deec64edfb333936973 +size 42467328 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..337ff941dbf506a065cf4aae62c10ea08ee012ba --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03aa31db52de34830ebf4b84dd5a9723f21a446a7d9544f792676172c5fd430 +size 84934656 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..6dbebac3d3db83beb336370891be188e8e254dae --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a30cf6096b0fa6ee2391865108f214331eb7c11495cd8ee9c4620e4bd0f5c893 +size 42467328 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..efd9a9e30fe1720f86e21db5f37845c5110cc96a --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9fa4a8ba882789b8a7a2671e6e69f3f595292eb684f575105e55de84437b0bd +size 28329984 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc79fafe3173d96d6c861bb16799730bce65a577 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e368db0c003c98ee5a2b48ab854662264adc3ba7e12d747f3d619cc88f9e156a +size 42467328 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..124c2a85f556240f748d285b4fcf06a949d55210 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d90b37f1d65f364b41d9fe66286e5cc23b401af176bdabb050ba8f8749dcfcd +size 84934656 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..50b10b50b69bde4569f7f84eb77b1ffc555ca3eb --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c19298ebb9467ddddfdbd867703a08807d55021d18dd3f83bba65cb4fe2993a +size 28329984 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..90504ee9b8221f2951550b480e1bb3bb74c0a695 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1596119cceeae1905200c6b39cc4780fdb61951cfb2f051b05b24cc2a2843dc2 +size 42467328 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..3dba14d35a034554a2c0751221570d8f49861208 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b6c9d3774164aa55d6d32cd9beab3c3f02ba10044258c0f3638bce643d36538 +size 84934656 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d2ebe93dce05170768d9bf19226a9a8ea963c62 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca61d257110b2d8f182deb9e973d84eaa763baf2671b0a4d4ff9feaa27a0431e +size 28329984 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..2d444d71e78932293ba3cbc26a1f560e29073a46 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249a669035a3ac758125f80f2d37962f321c4c9bf4caf37f8c6f7cbbc93cfee2 +size 42467328 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..058499fd0bad411f985222ec4a9feac19f0e61ee --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770b970cb4b74f9517a435bfba16346df0e1cc21231bcf89c9dc9c15bd2e723b +size 84934656 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..eaab88202a76fed615da70d20fcdbfe828e1b6e4 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bece480ba78db7bb987a68a73731c25084cbcc1eeff739805eeeb4125f1d071 +size 28329984 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..faa1e19283c92c2dc3d7c5879784c9654f5c5adb --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f70ceaa6250ee2f07e3e6a37f8a0ca5127b39ed587a03166082a2714552d352 +size 84934656 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..28c948636340055e29e24eea26971b71d9a65cf1 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b6016ff8b2d425597487d5a1feaf6ff1436f9a889ef885fe432658777e0c92 +size 42467328 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..ee371c882003681c5ee1b7c2b441bc4553157e5d --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6201676bd18ff933f4fbce3b96397be475e0ef0903268e3cfab43265108d729d +size 84934656 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a44843e1e9993b84097eb6be447eab0b50423bf --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7fa9cd74804827fe24ed468ddb072e2d168e91f33de2b00703c99cdadff83b +size 28329984 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..beceecb2e581331d5d84c4d781479b3c9396e8ff --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb14e9287f11cc6abb01e3952a81929d6fe4a8e9248a1e905f6bface20d10c6 +size 42467328 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..5ae3b0cf696f0c175406b8c2ba9ca83b69739644 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40563a86e1a34c3819cc9472afcd6024e990205d9bbe01e613f7be1e90181ea7 +size 84934656 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..78c56eae8d7bfb8ac4670403cd1efdba46dc3c04 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4b147243c5505dffb299bb6f20f5437551d716d7316a70e695f48f90567502 +size 28329984 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea7bbcf665d60a0dd79bf332cd4b3be31753c3cf --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a1af9cb04a5728d5ca9057bcf70abeef7a70a5de78d5cd5da5eb3ba33b92f4 +size 42467328 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb5f6d8319bb18c913bb571fbe3f20815763bd57 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f95e81272a9cf7bc8f716c3248cd195189886e8e8d7c3976b38e767c6a011bc3 +size 84934656 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3e77aa7dbcf5e88b18b5bbd28c40e967a96a522 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02c0b3fb511cb3e0344bb7b08ede0af957ac5d2e98017819a338194df66d9c47 +size 28329984 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6240a057efe1c3f28ad7978a4f1ae740c7e5a92 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97d38ae27a089e7e1526f6dfd33a6cc20814ef9246f6b60fc51e4e06bf352d2 +size 42467328 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..36b6ca6d8951968be44a1dd05828783999ad21f4 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78f22811bf5a302bb837e8f733606c5131242d2ccfca20f14d64e5b903ff57ea +size 18874368 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1ae3d356344adca1c30508bf8c9220687033ecc --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409be182ccb94cd395de439c6a6d989df14cdce4583611f8f6b345fbe7772d60 +size 84934656 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..0481cdaa5ee71edf6274dc67cea3575a0bd975e3 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3aa684f06a1da9bcf6b0af054cbbc00c50559af127ae945288012c04eee9fe4 +size 28329984 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..0af71404fe28c7ad15c459faca50e91ef02ceb26 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aabef0acd02ca2f1e1af3687ed091859322a771fee88d2643914d785cad3ffda +size 84934656 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..d68b21bc7a2f69b70309d22d0c79a90272d1423e --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f388d2fbe2a51f7be66af4740d6710e6bb18236fb017efb22dac3a9c3fe0b8 +size 28311552 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b29c63009b089174d0247cfa712b1160f1bc312 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61713f0c22de5801676af39424f78fc46df743352684d0615c1e95854208c89 +size 42467328 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..807f61a1d426915aa6712a345a9e9b93fe02a7e9 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c53962c94dc86f8395a59d94909ae90f74c7d35e50356d70c3c415f1d7e16a +size 84934656 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5b879ed097d64a19b92e7ec674c2fec28492004 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853d55987aa25b32e011d0daf9a17d8fec927ce7801b8699ff0dd4ecd56b0a8a +size 28329984 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..dd73eee7ac59978339372d0263ea1beedb17ade5 --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f62bb0030a262c0861854527a1f49e18c16fc21881934b19bd6eddbd8e6094d5 +size 42467328 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..83b818412fb2052796d28e1f7e2afa4b912364c4 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10029c2698fe8ea72a72268f67078936c05de60d8d94d43babf2b9cb14210335 +size 84934656 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..789c12d1f03fe00d7d4093d6bfaf4358914ff29b --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb348089e1a330667caeb261f53f4cbb6bfa731a8be2065346e02c1aa5c19078 +size 28329984 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..dbb00f0aba97ddc2fa21ac61025f4245e8adc2b1 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9f4ab4826968bc824be1efa473e2faa21621bd268cf0fb48f5b48768f9512e +size 28348416 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..1682c5f50f588103ceaa62d19ca9c02e1e1c55c0 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3df07ee036f9a09b0cce54fa7711a38496f2024b38b1372291ec84a2cae350f +size 42467328 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..7aac584da1f24f105929f2453c162ab0c283d937 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd387e542633ce0d51a88eaf423b464f87b48fae324982406aaa3430bc6af24 +size 84934656 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d236c18ba3a4d4134dc79192776aeef4423e55f --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:675683df009d8a0fb9fc46018e32a509032ce45b5694ac7d194f23e09f0abd0c +size 28329984 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..7456025031d12563508862ce421064dc84ea2ca0 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e016eda6855b18d857dfc708ff6242ef37a9eea49bd405cb233a307774cce7 +size 42467328 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..86cb14d363e3cb35cd0b2b2320dc3971ec87cd4d --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c6e3f1571f80c7630d0175b2eff1600120a99bf68680d9eac7990c58add0cf0 +size 84934656 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..9a57419d7e112356074dd173ad38250394f5f944 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e701524463dacd7966f1fb4621d6d561ea7a1f041eb71343f673774f0836c31e +size 28329984 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7d9e21fadc71d24cef0a6b8c7143e79cf6ef43a --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476b1572cbd8a46da5f2745f1a4193fb5c28b631325edf86f4af9700d46e0fc9 +size 42467328 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e8213186c424a8a22635b0e9813848dd74fe7ba --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f7529ac4e868d13b130940518e7553e2878465fe04cab72ddc85772068dd1f +size 84934656 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d6adaaf9b5e433e588a47b9ef069628ce6dc5d5 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea5630fe37ee8672369516eb1790608c0ebe45d61ed065ffc0b87d1356a79be5 +size 28329984 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..18d0ba11ec7364b67b09adf3451ab865f56d4163 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce81ff8c797a7775f387665a9f4485ee745afcb8ac01a1ea7c93f5862186bd5f +size 42467328 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..4be9945ca8430b313e11aa6b7ec9b7921656d574 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e328234ebb2c4f7192b66dedae2d9cf51f2c0837299a788cb9925902832cdad5 +size 42467328 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..941964375db3daf8ef249f2f31c11242185abde1 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab5a6ab81f83ce4c077520f767c38c9a0d91f4741bc953209a91384c69bda70 +size 84934656 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e1e6ad9cacc43c6f07d8ecc6f3f55c0501f937d --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913902fea4a8a0f7ff452f82eae72befd1d52aa8a814ffeb43a949c1c94ca858 +size 28329984 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a61cf90817cd17c46e2c7ba99d7ed0964291074 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8950068d47937665886f4e5fcc6bede04712531ffe668bc4fca9fa50ea71ad72 +size 42467328 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..a50faaadd3ad071cf8f12803011c9db76cd88afb --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8286145da4cb9b3d1f49eb2146bef71bc27e2b12004ac590a172ddaeed5f7add +size 84934656 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..afd4c9663877eb598a7b794a2e0cb4b80ed893fa --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a74bb4ee1d025d03f465d8c81b76cec09259c2a2383f1eaa3612e816212fe4 +size 28329984 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..a787cac01174e06c804d2e983f978f91c1df6b11 --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35039556c7ecc9ac7b37c331f05d89bd911c25436a77abeab75ca893f81f5049 +size 42467328 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..10d025a9c2fa29c76e7026897dead04a8339bab0 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f602e7444172da53dca7d0d5543b8f67132d0930ef9f120b0746e04666efdf +size 42467328 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d5350188328d63f9057a97288ff39a1dd5b422a --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0de820f00c80ef23403008a9cb6d47e276539e16fc7a16a5bac213889ce78399 +size 84934656 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2feaa2f6b5ce650757256288df5359d41e8ab50 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4369911613d31958e27e42ae5c5b7c98e9e7c1781c8c62443d1d9dd197020472 +size 28348416 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d2e225fb3da32c6ea09b638cbf3bb25cd065b6d --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76d6b83b28f72479eb747661b040386bee74aa52e1435a8f74bcf7d02c8b88e7 +size 9441792 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..17caeef28b474768c735535fe5a7d74e055af82e --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be48d191c675ce38885659d842577b986e5a12dc22c2c419622113cc9e93fad3 +size 84934656 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..71542bf18f4b3cd507ef277908a6227eab7fd85b --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d91a22386acf5be16bff153c649e35fa46b98c04a686877dd4dfd31e55b238 +size 28329984 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..af0eac5c0056f83b8f3fcdb79165f8847111c305 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922 +size 17525357 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..796efe9ab515c15e146ce7588e6d7b9b8134dbf8 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2 +size 4241003 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..87df8b34caa7086990087d64a0ceeb4d047cd714 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2009 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "3": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "4": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "5": { + "content": "<2mass>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "6": { + "content": "[@BOS@]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "7": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "8": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "9": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "10": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "11": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "12": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "13": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "14": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "15": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "16": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "17": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "18": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "19": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "20": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "21": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "22": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "23": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "24": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "25": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "26": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "27": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "28": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "29": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "30": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "31": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "32": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "33": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "34": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "35": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "36": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "37": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "38": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "39": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "40": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "41": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "42": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "43": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "44": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "45": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "46": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "47": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "48": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "49": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "50": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "51": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "52": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "53": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "54": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "55": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "56": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "57": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "58": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "59": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "60": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "61": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "62": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "63": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "64": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "65": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "66": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "67": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "68": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "69": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "70": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "71": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "72": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "73": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "74": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "75": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "76": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "77": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "78": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "79": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "80": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "81": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "82": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "83": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "84": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "85": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "86": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "87": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "88": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "89": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "90": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "91": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "92": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "93": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "94": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "95": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "96": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "97": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "98": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "99": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "100": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "101": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "102": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "103": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "104": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "105": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "106": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "107": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "108": { + "content": "\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "109": { + "content": "\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "110": { + "content": "\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "111": { + "content": "\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "112": { + "content": "\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "113": { + "content": "\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "114": { + "content": "\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "115": { + "content": "\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "116": { + "content": "\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "117": { + "content": "\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "118": { + "content": "\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "119": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "120": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "121": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "122": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "123": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "124": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "125": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "126": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "127": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "129": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "130": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "131": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "132": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "133": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "134": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "135": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "136": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "137": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "138": { + "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "139": { + "content": "▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "140": { + "content": "▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "141": { + "content": "▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "142": { + "content": "▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "143": { + "content": "▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "144": { + "content": "▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "145": { + "content": "▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "146": { + "content": "▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "147": { + "content": "▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "148": { + "content": "▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "149": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "150": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "152": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "153": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "154": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "155": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "156": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "157": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "158": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "159": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "160": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "161": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "162": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "163": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "164": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "165": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "166": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "167": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "168": { + "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "169": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "170": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "172": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "173": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "174": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "175": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "171": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "176": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "177": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "178": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "179": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "180": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "181": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "182": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "183": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "184": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "185": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "186": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "187": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "188": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "189": { + "content": "

", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "190": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "191": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "192": { + "content": "
", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "193": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "194": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "195": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "196": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "197": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "198": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "199": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "200": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "201": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "202": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "203": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "204": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "205": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "206": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "207": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "208": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "209": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "210": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "211": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "212": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "213": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "214": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "215": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "216": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255968": { + "content": "[toxicity=0]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255969": { + "content": "\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255970": { + "content": "\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255971": { + "content": "\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255972": { + "content": "\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255973": { + "content": "\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255974": { + "content": "\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255975": { + "content": "\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255976": { + "content": "\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255977": { + "content": "\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255978": { + "content": "\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255979": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255980": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255981": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255982": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255983": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255984": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255985": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255986": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255987": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255988": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255989": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255990": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255991": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255992": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255993": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255994": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255995": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255996": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255997": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255998": { + "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "255999": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + '\n' + message['content'] | trim + '\n' }}{% endfor %}{% if add_generation_prompt %}{{'model\n'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}