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..9ce295eb88f3a9236cfb1dc0c4c7a2e5c83a2f99 --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,84 @@ +{ + "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": 4096, + "tensor_parallel_shards": 1, + "max_batch_size": 128, + "attn_logit_softcapping": 50.0, + "final_logit_softcapping": 30.0, + "query_pre_attn_scalar": 224, + "sliding_window": 4096 + }, + "vocab_size": 256000, + "context_window_size": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 4096, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 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 +} \ No newline at end of file diff --git a/ndarray-cache-b16.json b/ndarray-cache-b16.json new file mode 100644 index 0000000000000000000000000000000000000000..27ae3efad18b5828fe2ad6b1f55a155de2787c43 --- /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": "a3af7a56ca8b021a828ae0c541922426" + }, + { + "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": "491c998ac863be9af01e763845324c08" + }, + { + "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": "39073d97a3ec272a731ee2331653e6d9" + }, + { + "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": "54b6184aeb869659128f2d1b63a1f71e" + }, + { + "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": "a24f9b50a18ef172b4240290fa86035f" + }, + { + "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": "81be37c6285659097108dab7e1167610" + }, + { + "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": "3aca32982f29aff34ee83f2ca4fffc36" + }, + { + "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": "f0c82749a36607fcca1aebe819918988" + }, + { + "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": "d98c81b6ff6c3e625a6d9178f03869b9" + }, + { + "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": "9f15986eb6cf2feb330374aa886f574f" + }, + { + "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": "ba3e941319f5bd84567e7cdff01d562c" + }, + { + "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": "133664ccf5f0a780c3d527c576f83c82" + }, + { + "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": "c80ffba3d542f5244d7b47ee0686fd15" + }, + { + "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": "82da0d1860cde0cb675a3ed2a433854c" + }, + { + "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": "4dbae0a83b35dda0cde8e209e8abc160" + }, + { + "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": "40887d58fb093c33e70f668cf4bf6cee" + }, + { + "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": "3c99c24df6ecc72184bc666fa37713ed" + }, + { + "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": "a03408f01d7845d5dd0fdc96981b9795" + }, + { + "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": "4ca815fde850b6d0caec167e60d28116" + }, + { + "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": "2e41a8aef9bf37abca7872f0bd02441c" + }, + { + "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": "721736733522c0c2d6928724718b8d80" + }, + { + "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": "f94ebe81d257e783b233265f2ed74c31" + }, + { + "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": "90b89a80cfc1602369ee44c5d85f1e03" + }, + { + "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": "f7359bf5843f9300d7b10c1ebf5f1156" + }, + { + "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": "a5d4978c2cb0d3b70036f9fe185d8fd2" + }, + { + "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": "7e12841b8aabd4d6feecb1269dffaf79" + }, + { + "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": "676a40b3e8c491f714185ed2e968b50a" + }, + { + "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": "26c69195a7d9bc01816ca7e652779582" + }, + { + "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": "9e7e3ec3f7a55af727010709324c15db" + }, + { + "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": "54ccc2b6574312de7af096c8c61adaf9" + }, + { + "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": "2c1de3496b09581ed287384f3cbbe1b6" + }, + { + "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": "b88955f08bd540b803f1ccdd03306698" + }, + { + "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": "f3e3014e24bcff20e80b61fa2185999f" + }, + { + "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": "e893e73d14fea8bc08faf7382a6ff46d" + }, + { + "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": "e3a374df504f2f5f4d47394d57d7022b" + }, + { + "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": "696543e0b88e30609403bbbcf50bf083" + }, + { + "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": "a1594005ea5dfa20f1e70fa6b63da8bd" + }, + { + "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": "ae73e2b9420ec8b7686ef1f2a77ad27f" + }, + { + "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": "c342564cc32289df1d3870f7cc00f5b6" + }, + { + "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": "a9ccf3fbd38aa220652a80a8a29e52ed" + }, + { + "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": "8cd76694c761abda3b06b03a36bc07a2" + }, + { + "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": "8c20e62ac573b44910efdf44c9ac91b9" + }, + { + "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": "09ebddcaaca0ab94453db47df26d3b37" + }, + { + "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": "8313cf6d66b756c4590b67fcb1670bd5" + }, + { + "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": "590a2da4d50cb705ffccac5190c81c3a" + }, + { + "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": "bbe34bca37764c8c1de9ca37b6f4d6fd" + }, + { + "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": "433725444ea45ece6b438f1f4eb1230b" + }, + { + "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": "307ab0846f737090154b6909d89185d9" + }, + { + "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": "1442e2af6d973d018d1c0cc4cd9036e3" + }, + { + "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": "80e399a33f1ea124a251d8c33b21a99a" + }, + { + "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": "a7123b5486f1f11071a442c9f5a674aa" + }, + { + "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": "b350d36ef97afd138743456172cded1a" + }, + { + "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": "3f91c632a3afcc3f848e066fc9fc277d" + }, + { + "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": "91c17d484c0d09522301873050231f44" + }, + { + "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": "4c29b4a171556d71545eea0b7d1b1ab3" + }, + { + "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": "fd7945e3f5b8dff9e065ca090a83f374" + }, + { + "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": "1318190259728d3fa1e9f128e4269a3b" + }, + { + "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": "cf22c371cd3e4f9db93b8867fe14bf7c" + }, + { + "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": "6a725295146c0ba5677e124e2fe0da34" + }, + { + "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": "72c2ba05a0e0942ccd11b67a21f45cfd" + }, + { + "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": "6ec841acc8e17ebfa315bf3985b69956" + }, + { + "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": "2c860adc2f1ad9e44549cbc43a2e9975" + }, + { + "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": "7a5da0311b590481f07a2c6ea22d8dea" + }, + { + "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": "08797b1aa61dbf64a4e4df7a8be2a8b4" + }, + { + "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": "3b527f48312ff17dabb69cc66248a62b" + }, + { + "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": "a1e272ec364e278cb17c52a595a3ab9a" + }, + { + "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": "1aefe1406be82a8a0460a21c1290f891" + }, + { + "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": "e041ef02cae52d0ed220fecb8ebf90c0" + }, + { + "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": "038478141467fd0252ee1f30c0521018" + }, + { + "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": "2b4beed107c3497441069808f3935d4c" + }, + { + "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": "4a3537ab420b63b869d40733dfd14a00" + }, + { + "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": "26f29cb74eaeb8390baeace23314f1f2" + }, + { + "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": "9668ccce68b22ccd35de7c18001e1ddf" + }, + { + "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": "a7ca07fc82c6f615e735761d387319e4" + }, + { + "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": "2176f447c0bfe088191390dacd403c07" + }, + { + "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": "ddc4ab12a1794b40d7a7d2f4f5744d45" + }, + { + "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": "6cb8e7647db51acf325430ce0247514d" + }, + { + "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": "4bb0a856c263aaa8d4224c2dd80f1ba9" + }, + { + "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": "1653aca45ae3049e61516e3eac1dcf5d" + }, + { + "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": "8cb41bb43fc166d2d23be3e590948a66" + } + ] +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..3bd53172c278327a7d590007ed11394c8f00ad08 --- /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": "a3af7a56ca8b021a828ae0c541922426" + }, + { + "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": "491c998ac863be9af01e763845324c08" + }, + { + "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": "39073d97a3ec272a731ee2331653e6d9" + }, + { + "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": "54b6184aeb869659128f2d1b63a1f71e" + }, + { + "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": "a24f9b50a18ef172b4240290fa86035f" + }, + { + "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": "81be37c6285659097108dab7e1167610" + }, + { + "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": "3aca32982f29aff34ee83f2ca4fffc36" + }, + { + "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": "f0c82749a36607fcca1aebe819918988" + }, + { + "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": "d98c81b6ff6c3e625a6d9178f03869b9" + }, + { + "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": "9f15986eb6cf2feb330374aa886f574f" + }, + { + "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": "ba3e941319f5bd84567e7cdff01d562c" + }, + { + "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": "133664ccf5f0a780c3d527c576f83c82" + }, + { + "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": "c80ffba3d542f5244d7b47ee0686fd15" + }, + { + "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": "82da0d1860cde0cb675a3ed2a433854c" + }, + { + "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": "4dbae0a83b35dda0cde8e209e8abc160" + }, + { + "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": "40887d58fb093c33e70f668cf4bf6cee" + }, + { + "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": "3c99c24df6ecc72184bc666fa37713ed" + }, + { + "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": "a03408f01d7845d5dd0fdc96981b9795" + }, + { + "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": "4ca815fde850b6d0caec167e60d28116" + }, + { + "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": "2e41a8aef9bf37abca7872f0bd02441c" + }, + { + "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": "721736733522c0c2d6928724718b8d80" + }, + { + "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": "f94ebe81d257e783b233265f2ed74c31" + }, + { + "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": "90b89a80cfc1602369ee44c5d85f1e03" + }, + { + "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": "f7359bf5843f9300d7b10c1ebf5f1156" + }, + { + "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": "a5d4978c2cb0d3b70036f9fe185d8fd2" + }, + { + "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": "7e12841b8aabd4d6feecb1269dffaf79" + }, + { + "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": "676a40b3e8c491f714185ed2e968b50a" + }, + { + "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": "26c69195a7d9bc01816ca7e652779582" + }, + { + "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": "9e7e3ec3f7a55af727010709324c15db" + }, + { + "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": "54ccc2b6574312de7af096c8c61adaf9" + }, + { + "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": "2c1de3496b09581ed287384f3cbbe1b6" + }, + { + "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": "b88955f08bd540b803f1ccdd03306698" + }, + { + "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": "f3e3014e24bcff20e80b61fa2185999f" + }, + { + "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": "e893e73d14fea8bc08faf7382a6ff46d" + }, + { + "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": "e3a374df504f2f5f4d47394d57d7022b" + }, + { + "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": "696543e0b88e30609403bbbcf50bf083" + }, + { + "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": "a1594005ea5dfa20f1e70fa6b63da8bd" + }, + { + "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": "ae73e2b9420ec8b7686ef1f2a77ad27f" + }, + { + "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": "c342564cc32289df1d3870f7cc00f5b6" + }, + { + "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": "a9ccf3fbd38aa220652a80a8a29e52ed" + }, + { + "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": "8cd76694c761abda3b06b03a36bc07a2" + }, + { + "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": "8c20e62ac573b44910efdf44c9ac91b9" + }, + { + "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": "09ebddcaaca0ab94453db47df26d3b37" + }, + { + "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": "8313cf6d66b756c4590b67fcb1670bd5" + }, + { + "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": "590a2da4d50cb705ffccac5190c81c3a" + }, + { + "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": "bbe34bca37764c8c1de9ca37b6f4d6fd" + }, + { + "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": "433725444ea45ece6b438f1f4eb1230b" + }, + { + "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": "307ab0846f737090154b6909d89185d9" + }, + { + "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": "1442e2af6d973d018d1c0cc4cd9036e3" + }, + { + "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": "80e399a33f1ea124a251d8c33b21a99a" + }, + { + "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": "a7123b5486f1f11071a442c9f5a674aa" + }, + { + "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": "b350d36ef97afd138743456172cded1a" + }, + { + "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": "3f91c632a3afcc3f848e066fc9fc277d" + }, + { + "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": "91c17d484c0d09522301873050231f44" + }, + { + "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": "4c29b4a171556d71545eea0b7d1b1ab3" + }, + { + "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": "fd7945e3f5b8dff9e065ca090a83f374" + }, + { + "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": "1318190259728d3fa1e9f128e4269a3b" + }, + { + "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": "cf22c371cd3e4f9db93b8867fe14bf7c" + }, + { + "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": "6a725295146c0ba5677e124e2fe0da34" + }, + { + "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": "72c2ba05a0e0942ccd11b67a21f45cfd" + }, + { + "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": "6ec841acc8e17ebfa315bf3985b69956" + }, + { + "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": "2c860adc2f1ad9e44549cbc43a2e9975" + }, + { + "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": "7a5da0311b590481f07a2c6ea22d8dea" + }, + { + "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": "08797b1aa61dbf64a4e4df7a8be2a8b4" + }, + { + "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": "3b527f48312ff17dabb69cc66248a62b" + }, + { + "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": "a1e272ec364e278cb17c52a595a3ab9a" + }, + { + "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": "1aefe1406be82a8a0460a21c1290f891" + }, + { + "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": "e041ef02cae52d0ed220fecb8ebf90c0" + }, + { + "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": "038478141467fd0252ee1f30c0521018" + }, + { + "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": "2b4beed107c3497441069808f3935d4c" + }, + { + "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": "4a3537ab420b63b869d40733dfd14a00" + }, + { + "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": "26f29cb74eaeb8390baeace23314f1f2" + }, + { + "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": "9668ccce68b22ccd35de7c18001e1ddf" + }, + { + "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": "a7ca07fc82c6f615e735761d387319e4" + }, + { + "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": "2176f447c0bfe088191390dacd403c07" + }, + { + "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": "ddc4ab12a1794b40d7a7d2f4f5744d45" + }, + { + "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": "6cb8e7647db51acf325430ce0247514d" + }, + { + "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": "4bb0a856c263aaa8d4224c2dd80f1ba9" + }, + { + "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": "1653aca45ae3049e61516e3eac1dcf5d" + }, + { + "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": "8cb41bb43fc166d2d23be3e590948a66" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..8777c3f2a50880f5665a93f9ff41b10828ab379e --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f1377e5cce7254337905779614a72b5aab95123e9a7b393430e1b64d3a7953 +size 1179648000 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..f801a9d043afffcf79f6661811eebf0b2f89222e --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d0ad02ad75ad34d39073017c1cb0acda622c805a015b9f50f0e7c4ffc73bb6 +size 42467328 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..3680d8e49f77d5693bf88d783770e3371fb06e8b --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:991fb1a2f20bfcc83dd3c78b5e5623eecd285c1dc35babec354c1d391abdd652 +size 42467328 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..687838efac4af87e306edfa3bf31fc9197298ab8 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef6ca7c2257dc9c634ed38b8593a6c7ac948e08fa03fc91b22e78d924b47f4a0 +size 84934656 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..40ec766de4bcdab759e3f480a5b98682fa8cbe57 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9122ddcd43ed5a3ff1877749c50272ccace8be39cced42f8ded6798f8523959e +size 28329984 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..548344c8a72b906be49b6e79a1f1282d2c868093 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c55f64834d00e69e2558faaf3c4b30d00203b3ef82ad14dace571754203fb0c5 +size 42467328 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..3ad6177c2c7bdf8e562f50e239d7647acc1cc8e2 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90eab78c7d5e3a04b52e3d7276f5b5fa75f8a0921d2855dab3846a61ff56ef1b +size 84934656 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..6cbb266562e729590385df72cb563ac664133e4a --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfae3aff2ab10f2b5e577a6e47d17b920c3aeae50dbd0eafb1841c7af234a3b0 +size 28329984 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..29d2b913a2c9b4f17da48023845499c8c0c16b6c --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:337cc0271f1331744c3a51ba0c71d614db24066fc8db07fc50c3485dcfa5b2bf +size 42467328 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..4341770e91332a53a15c2a9eb5ebbf11568ff711 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a5f3aa1d917c4a7fe2e22cf194db6b30455db511e261c820ab2de6035371f0 +size 84934656 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..897880a18c8c2424199616e089f2e49463e3782a --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e35e228979e6cde8d9696a7892282e710ffe3fcb2b68faca19b5eaa38b919656 +size 28329984 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb613b34e6dbc9256839b843ab332268b313eee6 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29e3ccf6873b95f12cde7841c9303f82d53477153486f587561f3d91bdc03aa0 +size 42467328 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..815aa1154069b997e8da7eeb8a35b00fe10f8fce --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9016cd639442ccf7f2d6f09a9fc9e854d0df29c0a909ed12c37176fb3f93437 +size 84934656 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..27d01a35ddbe14ab1d3490ccc37a6ea5d65d6994 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1f0a5846ad3625e91fd10b1eb0b838afb8a238c1e004cebebd1f11b6b0e1d8 +size 84934656 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..7081802e0db8e1110768a470624f68521095c1e7 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b017b9cba42aa805f161811847f19282832581f6f76da143891f127202d1aeb8 +size 28329984 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..8492ead1c66ffa6b92c0d853a72ac94f5ecd943a --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa17780d7c79f3dd196a17a12776f57826261aae7d579b1839a8043a3a295f47 +size 42467328 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbbc0c7360093c8c379b76a221daa0b53ea4b819 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55260315994abf06f20662cf31bc9732b86d243b5d7285d45dfb399e0e4d9c35 +size 84934656 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..aaa896881c41822b451db6ed1e1511e002403b65 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce3584db9200359c7e8e9cb4f53b8417a79394218bb38fba002e26d60261461 +size 28329984 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..7e979545404b44b4253ccc71764a98aa89696337 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f43e6c5c6daa41e91cc1f6635621c8fcd4d5beb181885d115b7e06359b611a46 +size 42467328 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..bac78ae710e15b62cc8509a2b06a46e671b8d8f6 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66705908d6ca78db83c1eed715a9704d39f7205cc7b1518ee450a3cfc9a2cbfa +size 84934656 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..5106edd7efbd1bcd3f12b30ec2279798b2bb4fcb --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce3fe0a2f2efd3de4b5d9949335c6c82f9734ed0f9db383abc8187b82790241 +size 28329984 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..2d19980571e4449b249e8b6109f94f2c7fb76c1d --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43fc46945070179a0ca6396c61a0279e470634a1cb9f6a1538c7ab357b3c950f +size 42467328 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..9dd514bf9c2ef460f8ae7ffc6edb0c020cd5982a --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ab0d7b766d7af9218c5fa19834fab40d154ed26204e319a7b742ae304bba19b +size 84934656 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6564922b06ec18020693072dcd76f4c44f73851 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85aebbab7370d9cdcb86391c4498496830c4a69a120fadbba6375cb6ed965c63 +size 42467328 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..b4a27231917da83c319ae8234486b7de6e9f390f --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ee7325dce31638190cf543ffe6fbd895a403b608509c01f28996c7031762f7 +size 28329984 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..19fa389f12303085d193598ad042d6cfa454f9d2 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32ab8058836593b1e269bff259f928199f1594e08548049a1cfe624a2054906f +size 42467328 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa22a691d5dffedaa3267fc4a478463ce6f37265 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5237fcfe53e1c533b56f1eeb8528526759be5d1219cda0165e710619c6c9d2 +size 84934656 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..48c45d76742b5e0bacc30c4fa6d57d6045e010e6 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d88da52e25d678f1838a8de956536ae20538605b7926cb5fa691f5f9281fdd2 +size 28329984 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..f800985ddb7b5e9450f40753604e28a1ab06224c --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf45bea29c4aede7b6b2e73d66d647a2a569e8d1c013c138b86ab792fe1bf49 +size 42467328 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..195e8d1ff0d2b814cf9545782999bb9ce22d4223 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ff4f744f60857e4b7a74ebe47cafc870b58bd88f843ed9a8ad6aa1a09c3ee0 +size 84934656 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d94dad1d8048c94dece3ff5c05a3d52d9c7da06 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0212e0624de85dde31a36c852eaed261f42cd5073a00f7a0b1c83be2efb3825 +size 28329984 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c597f7315b688b9c7922dd265c8d9d83fe07d57 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cfdf9a6defda04449d97eae278dc63bd88b8dd6fbe3a57d9fa9b13c501fe09 +size 42467328 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9e3ddc477b50f30efaa972c6add7bc0c3e27b87 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43f3fc08106619f36756e8080b0cc450a1fb4278074e9de1fd5bd7cfe5853cb3 +size 84934656 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d32fb484c3169662a57003970adc61f19498705 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d11362773c0116ffd1e2301729ee1aa85712b22f17404c58a479b46cd271f5 +size 28329984 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..597d2583e028a821b752d0b156b437eb4dc0d40c --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecdab7ab76bbdcc47e29f25d5054fdfe0ac696a4ec160184ec887706e3003831 +size 84934656 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..1de4c16a1723b1d37dfc51c5354d7e828737380d --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347fb1876cc56516451bad31ec1ec662e8f9602f9c602a90d7493abc3ca59872 +size 42467328 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..9a17dd2ac2772618baea726965aaa52bff1bf0cc --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2792619a84a3a0c8dfc30d643cfd436ba09df8648c152ed1be466921ab06a01 +size 84934656 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..fce662bbbe781690aea1814c65a0fe5cfd19b68f --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c172415743ff3b759de776fbabab0df4e459688fb570e39330a9eb413ab87a +size 28329984 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c670b510ddced6ee804dfbcb1ef0d4f7b10a2ab --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd2ab88da5966083654045171dfa5c56b30a04ad08e77f4133870a718bad80f +size 42467328 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ef3ce82a7d1027880c49eacfb2a4d509a4e5474 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d846cc929f13d9cb2f9fde5255cb74b6e3473523610fecd2d52b3788841b32c3 +size 84934656 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..909174d1c51b0a4e8e79983b622098faf4299612 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3bb7540b89b56d689bca1508669af170e41fca6314b75e473eba4024636231 +size 28329984 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c327b1badbd32ebca089c037f6fa381df1b3ab2 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109ab251a13aab27395701726165dfb74df51c4e54cc44c3b219efd3d26a7209 +size 42467328 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..730b9ba4073b39b0a3bcd091be4616cbf20486a9 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeac6615d5d5ecc6e4d8fd24cbbae4855a49228c436309054e2b29dfce803005 +size 84934656 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..27c1f7f9e761f3b9a51198189229a076927eea0e --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633bf3238d6664b91dd8e410cecbeaae0e93b11fcc6ee52abaadebd10efa7e1a +size 28329984 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..e85af12c4d61505f9ce0e50323fa356e4192b1e9 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8569a5da472e67e8ff54beb3b93938e2ef209d4e545b12bb81b17c3ac0ef43c8 +size 42467328 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..f0369727abb537e84b2d8fdd488ea9f74d22087c --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684ea856327ee2f95e9c966ca6eeaea853cc3e6c1bdedbd0539962def1e0e25a +size 18874368 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..a9d69421b91b0987d14b0a5418dfa61d9f7fb2ed --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3a5e4e840fe7b127e0a16e5dfd4521010dc4f2286ee18819828d22ab68e83d +size 84934656 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9d91377b3a1057413f00fc8ec23e19de489501b --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f3157ebc16ff2c0820a16f04f52785bdf16d734a4cc1a1b1143ab5610f36a72 +size 28329984 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e789e88baea4490bb425a9b1e84239f3f876f89 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e83cb8659da34b3f90e8b8eb9a51cb4fff7728e6525483d489c3ad35288d507 +size 84934656 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..07e22bdceec50ca8d3731d74430f18d9ed9eceb2 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b829ced42827cb8f43654a4d85614de06017178ee4d2fe7ea39a6d457c0eee +size 28311552 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..5cde2df4b8e0a30cd59682e0f722e9056821b83a --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:000bdfe071a95e44d96df525f4cc2ee7d72f821ac95c93aeeebcb89db854f297 +size 42467328 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..dc3b1e54fc72505c4eb824e089fec9bd237458f2 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210ae3cdfc7fcb7849dc436e3bf7f91937556803bfd56f865c2132739bb1772d +size 84934656 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..7cbc22259e426b976679e2dee06888110d812f1a --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb462d90c7e9de3ac34b12b097152ee3a8dd194de903e167bd32bbfdbe08e0b5 +size 28329984 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb344fd4f981105431cec0ec5a8be2bf4c5f54bf --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0696c68af3c3228a5b1bcddc14b8a76a4f069633d3f794227d094651485916 +size 42467328 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..4901eee4a6dc29ec93960773194bb1c51c6a465a --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:966470261cc24fe5e69ce2dfa080ec7bd7507644d5b74b2557335ae0e46a1eb7 +size 84934656 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..0faffec51838b412db1e7f0fa877073575132c50 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2e67dc574cdd8843db8c89039c026a694a92f03ec519e7c9bca3744d9425ebb +size 28329984 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..d02a2d8ed42bcfa5a2865274905d5d902f0323a0 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a0b8dab411659b71c769fa8b28458457c2185bfe6bf9161dee01dd074b9d6db +size 28348416 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..93d4269724906c8e0aa61c0a1f4aed5e13fef109 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:234a82d1a5b44a09ec562ea26db74cbf5e0ee4861b696f28d2f7acc1d1d938aa +size 42467328 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..661ddb2a68a5a7ce0774c7e1be1dfe9c141e9884 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:651a68e8a7ad77553b68a959675dc3718c3f29f3b7428c8e44e1a802dacf2a34 +size 84934656 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2b3db14f6161efbc4ad16fd0dde92660d18c7bd --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7418a5fd9aa3625e3c17df7a92d492425271c715efe9ea46cad31e2cac1d5a +size 28329984 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa93efacfded70fed7714d8bb71eae59ab1c32bf --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760cc2310e0d3b436e710fec8950400cddf9b84038c88fd0c61d41d2ca789a9b +size 42467328 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b4ce607daa37a1d832908759991a06190f205a6 --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8be62b07b821573854d0f321dbf52378e4797d5ab99d56234444a483437c6e0c +size 84934656 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..080a1acc58eb1afb53fb80c43dec2419b0556983 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e300c9e1c09a9bf705ca5f6f3a7782e694831f3f40c17c98751f2502b7398d3c +size 28329984 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..e3770bd8ea9e86a7bdd0e7a0a47254b7c21ca2bf --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db86a089737323c5f66e45efd2c72855b8b5be2099b84d9290e1c1426f69ed5 +size 42467328 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..89859db6b556b7adc318b03abecb740b225e8bae --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58d2e0f1c158e9c18bf3f2ff3df555929292cfd0981fc57e5f4585d9ed7844c +size 84934656 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..048a206fb20e3bf56dd221ad30583e8e389d6062 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98e839b490ae320ee090b5d0b47bca53659aaac8daa1b94e8f03572f5717b73 +size 28329984 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e815d280bbc6e45ead64f3688ffa89ca747e562 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8f3e294ebc6605a2e4caaffe5696779a5bbef4e284db95fc26f042801587446 +size 42467328 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..1cc75a85121f89c7d0a4f3b8f16e2eed36f80570 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2826f7fcfe233d1287b6f801efadc491a6707101e2578bdacd0e7abb5701725b +size 42467328 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..b9bc7c1d55b7dc4016b293e7f00cb935fd91e765 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a8a131f9ab064fc0ea2852103b58a327d64e30e90ec7ee9bc4acadeaf9ddd88 +size 84934656 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..54c939dfe828de6909f6df8a91dfa65d903dd0ea --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9c9892c123e50a9295ed49e33699a6e9f6850666059bcc5efde74cf56128153 +size 28329984 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b146ee4046ac9f84cbce388583808244fb8e297 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b407f0363ff2a3b06ba62f4b039dc119a73e37cc4c32136c1cd4ed6fa05769 +size 42467328 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..e93efc8c8fb14eea1a046c4d83f55fd1b9dcfc6f --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2af2d643c75f076e95ee4a8cec1f53df2b60f9aa809529cbad1b88338f7d80 +size 84934656 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..627e726b31c57e9cd9c22420cb4e4167fe30a932 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9b773c1bb2acbb09a9ac198558c2b6c5c0e5abbcf7e459d240289906e1d4fa +size 28329984 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..245019312ea22e33d863e558c61941938c9055af --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be87509549f8845ae93a98e6180baeac08e82759fa3f58f9635d019585640733 +size 42467328 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d0af442e31b396cad4d73eec32e130f5088409c --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71b053caeb7f1a8fa79dfed284966230ac008f82c8a63ba1e1b84a2dcbcc287 +size 42467328 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..57bceaadf55da9d6789dbb43ada58763d220ee50 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc310a55c95deaab6748a71b29f3d70905807a615a72fb6e23f505228b2bbb3 +size 84934656 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbd284b94bda7bf7eeeb4195d9003a59bab02085 --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380dcd5298d2df6bdeee6c01ae492533a2100f2b9dcc9527d671aac52a427a6a +size 28348416 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c6dc503769cf5fbeedd57da0b1fda950d0ef6b7 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a3d05ea00dcf0ac875374bccb069f19d64c921e3154f0a826dbcd1be6ed1bd +size 9441792 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..efe731a9b5a1e77d5cb49de8fa0a7fbecded5601 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cbc0870ba3cead566a707251adfd9010a8503992878f0ae68c247c970aea1a +size 84934656 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..3206525936b68eca688a760c6ae468736be5f8c8 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f06e2f2b5d847c976cf7d790000f8d573b2e74571af7805e07b804189892498 +size 28329984 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..a2c7967c7e04b774515e26c390eb67891ce487db --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa178a85ecd933ead78169c82e42ff18f5d1e3e5b4432bfaff18342e0bb9993 +size 17525369 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000000000000000000000000000000000000..0fb99fadba40bda6e559565d903f62cfde63b88a --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef +size 4241111 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3602bc076168f7106dc145ffc77e37ce873110a1 --- /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 +}