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/README.md b/README.md index 7be5fc7f47d5db027d120b8024982df93db95b74..039a186615ab47ae7e86738496ccaad26c563d36 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,11 @@ --- +language: +- en license: mit +base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B +base_model_relation: quantized +library_name: mlc-llm +pipeline_tag: text-generation --- + +4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) for inference with the [Private LLM](http://privatellm.app) app. diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d9e7e08f5c8e277065c653a7c72987d064f55208 --- /dev/null +++ b/config.json @@ -0,0 +1,5 @@ +{ + "quantization_config": { + "bits": 4 + } +} diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..be759405b0787f395616b9f6a04800bd42b12516 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,11583 @@ +{ + "metadata": { + "ParamSize": 805, + "ParamBytes": 36381212672.0, + "BitsPerParam": 3.4891900844756822 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 1024, + 128256 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "3b0091e9675cc30ddb562de5cb1cab5e" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "be56f00c423df3b0695eab97d8f5c83a" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4478a8348569679ca051121053428673" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "56b93512f25b610d2c68c3db50b25f22" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "dce9b5168708d4d7f6bd1ac7489117f4" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 31145984, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 64, + 128256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 0 + }, + { + "name": "model.layers.78.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 16416768 + }, + { + "name": "model.layers.78.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 16433152 + }, + { + "name": "model.layers.78.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 20103168 + }, + { + "name": "model.layers.78.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27443200 + }, + { + "name": "model.layers.79.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27459584 + }, + { + "name": "model.layers.79.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27475968 + } + ], + "md5sum": "f6d4a2a6f5b3f4c56ac1a425748319ac" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.79.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c653a566e9cbac7000648582ba3e79d4" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.79.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9dbd53596bd713459158086e6d0dc6d0" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "3ed7d852262933b734b9bba319aebb07" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f071646732491b3c1fa353ae5bfee3ff" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f1072e72e9569e019627fe0d4f8a99ff" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 29835264, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.79.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.79.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.79.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16416768, + "byteOffset": 9732096 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26148864 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26165248 + } + ], + "md5sum": "f90c8198d41feda54a54f15df0cea400" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "95ea54424c5c7a89f4b8425b0a026ecc" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0888ed7f1121243b2c9f94d94396920f" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8ba60af38072934d423d014d235abbca" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cebe5d43f63630cc878a4d957aab43fd" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d04c603a0303c5b831d7a2bf90ecfc80" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9e1e3c38d32c8dd420201537cad85cd7" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "32f05c224733ec5fdb84a6b454c23d40" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "06a51f0ca8fb8db38b96223c0ba6c96d" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "5bf0386539edca7d59676de280761484" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d3c98fea786141a2f439cb9980594aac" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "06a157e7db7baece876381052459bf3a" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "5183ab98936fccd317217e003c6fc3b2" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0595a21332399b7c5b2c204036e3c333" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "542f7a1fdba0c97a4360dac7fcef7469" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4ba62c64e7b1e0fd72f8bee6571fd965" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8ab88a0ebb486e27d2c1eb3d1008fec7" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "852264770a9bf03b4f20fe2db33292c6" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a430790f2fd7026b49aa0b8086a95242" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "934c7678da36bc800cacf06ad4b0ec4a" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "c6430382eca1fcd18b3b762e46df91b4" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "73c670f32bfc0c4521c6bf2235704b47" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ea9aec136bf042b02bb2208af535bedb" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6dc67927ca7bce03aa61911302c4819b" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "829c3dcd8baab3440f7f3213bd8aec69" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d2db7770f6c414cb9a43c4ae7e8eb41c" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e8153e8e85b753a42f317065f0d179a9" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4893b007a838f28492137b86d152f4a6" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f2659ad43c339b30a5efbaa8e4aa2e59" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fa7a569f9350eec26a7b1327f8353a07" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "37f82b2bd128f144537ccba3850446b2" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 32833536, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 23117824 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 30457856 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 31768576 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 32817152 + } + ], + "md5sum": "51ba6e6d64e65d831c50bd2afbd805a1" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "31d6eee9944daca913d8c76209e639df" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0149f3350dfbbb1527c87ae7c104a5dd" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "65dc6f40cde595f2c4228ed95f420cb4" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6350be185a18cf91a96600b1cd77e1df" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2ed3ae06f60e30f74e9dce709e2fe68b" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6671a01e018565f35fc9ea3f7148da0c" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f7777619655728bb608f7abdf089a4d0" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 28147712, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11042816 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 11059200 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 11075584 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 14745600 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 22085632 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 22102016 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 23412736 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24461312 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24477696 + } + ], + "md5sum": "009efc2ebb07fd43b345ed177e300c14" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7d31837d6957f68075c141ef0e1356a6" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "39b55e353a5680b469eb7a25f902453d" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "91f4f475bc21ae417dc257907d8ed7e1" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e1927e37b645fcd58b8c0b0882f86da5" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1e1207762e36011c4b26caef56a2c919" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2cccdd4ff36a0ad8ebec04a75d084146" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "da78414bab7e35ce985c531b629caf56" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f70d68b84017245d7b69a9fd9b2faffb" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "14e6b7fd97c200d3936a9b666f8644f1" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4e9967bb96cd5e4226a994188ed49961" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "db104906924c9db7ad3234e72f5f1a74" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "011cd7c32db966896f5090f5825b7ef3" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1ff37d82d6ee0b89aba1fa1f95c998c7" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5a6178e087a2b8ed8738adc67543a63a" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9a81d92ce109bc288765de757863a84a" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "efdf5163be0387c193f8ea94426e573d" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cb491ec82e4bfc4209fe971cbe8e34d3" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5c4417c465e28b155946239fe370457f" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "9ef7bc8cfd4dd68031e444fcb82371ae" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4e37404d5366ff289a72ba3c79dfaf58" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9789578c1ebf2e3ea686f86a9e0240e6" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "94d97020058893124908fa5134ec4381" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5ee50d7c6265fb78507839219279a5a6" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "164961fcce10045f3cf1324433c77ae0" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "930a2a55b71cd6b533b31d6aedf0f664" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5026b1b3df1cf1660f74331cbd28c8f6" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8f6400866e8e0ea8c695aa674e0188ee" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "5695dadd02a30fe487b62d83555d9f0d" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cc8f23fdd12598feb8cc825d7d3a1f11" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "431a050ff559042d93b6511507325177" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "73390833fde31e09f118729ebfe6ab98" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f2734a6cd2ba9c5329302764184d0d3a" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1439c4292b98729024cf07a0b1e26c4c" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b096e3e976fd20a5e98fc44a17159132" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "93129b99020392932a0b1a3b3941b081" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "677598e8dfe035a700a542a55136d4e0" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "be79c28b3351d0483973b307986b9adf" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "42da9994f83d506eb216fae7c3001532" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "72418166e8f748918a70a4bb9d69edaf" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "80ed3c6c70748f0f7ba22265542afb0a" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "348d34f16759a62612a8c5f4a78922a4" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fb66d8446a6c39246597241c30f88fe5" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "77d716644efcb4b9d4f4f3ffff4945d3" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "64716031b8186e5155a4a12d8a3b68e0" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "282a0834aa7f467f9829fecba86035bb" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "14ffcf995d9d46e917b5c1eb01a7f8f6" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "75f2cc197f423a2e28d51e10341fde35" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f860cab5545acadd721a3b2010c1ac66" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "2e78343614ed5433dae3420aebb990a6" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4480b9fd23304d5c8488427263a3b228" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9de189f385118b72eb450958ef50ae65" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e7e7fe3f8c9d83741e424a864dddfb89" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "deb60485235a4994591255aaa95981ba" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bee0337ef8f9da7483c6c7ff6c015700" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "46e3d4e233e8956ef149c2c1beee43b5" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ad137a7bc2327fe205fd451cb0e40093" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3c8a6c4cd1a2b0b9008903a58663b846" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "cbe6e8eeea767f283471189912540a58" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "820073a3b296a0f73f76992b0b51e649" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "74063931550fd1584781d85e166af512" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "59379a514ad24897d25418f2d1360fd5" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ade9db29f26824c777acba7805dd42b9" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8621e35e3317402857b5f5322fde94aa" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4c11cfa368426fb3a60b6636b34fe10a" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "ca11fbba1aee1c2dbd9668a06d91bc1a" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "dcaef57a9944b7e6c6352b0038cf16fa" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2a54a2eaa7debea816220a644e7edce3" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "41db23e74eebcc795df0fbd42fcc7a81" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b0548d208dd49259b9971a164c5fafa4" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "14dc965997b9c0cdd82358dc6765e9cc" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8e62a070b0b6d8936e3b9f6587484866" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "58f555999cf2a541561cdc8aba1732e4" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1876766cf0c65a6d76aa3102c4eae54b" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "57234ec1aaf243adc00ccb3b46761b99" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "887ff2ed5fa38d5d5152d59d573d1573" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a184db5ba04fe9410e9d4c1f6c82d125" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 32817152, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 25477120 + } + ], + "md5sum": "fe3e53ab33709462447d0727acc8c1dd" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f10dd3aea4f80110c6ee5a8cd0b9cd14" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6c33918033ef6614d943cc897ae5f061" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1d89268527cdde58ab54adccb8a1b2b5" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5cfeabc2e3e1c10d0055410ecba5f79c" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "13c529d9f9c12592361abca7d961e2d5" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0348047d62218723d2081d0be58006a7" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "21f6477a425174d783c4c6731a7416df" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "93e24a5ec625824875d9d54d3a248228" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "22aed74de5539f45f7b1905a719ce2ee" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3fa3532d8a5ceb3c94e7d2046b966fb5" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 29196288, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 0 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 1310720 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2375680 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2392064 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2408448 + }, + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6078464 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13418496 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 13434880 + }, + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 14745600 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 15794176 + }, + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 15810560 + }, + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 19480576 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26820608 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 26836992 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 28147712 + } + ], + "md5sum": "3bb9ca7f459745574946a93e2e513c45" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2ce831f614f04896be708cb03032ee40" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0d862bfbb37aa4cea12e0dd4fe9fd313" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2e08b146f5f788b588c7bcd0e4cd88e2" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "182973e3cd3b763cfc4c0291b520282e" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "25c9e180f5ef120857c370240db90156" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "243ad6aa08b6573f3e1379588a294639" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "527868f48a66bece3d5d6470799eab4e" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "615c19403eae0ec9a55ac90848cb7a76" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a5c8ba457d2b961b4a94c71651801776" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 30490624, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9715712 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13402112 + }, + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 13418496 + }, + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 17088512 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 24444928 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 25755648 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 26804224 + }, + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 26820608 + } + ], + "md5sum": "4a51dc1c2ee39bb9669c4e1261ed46b6" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "69e20a9a0d9c53061a72b73d12fe3831" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "46b54148e38c1ece24b789c928021b16" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "abb1f80c7c01237cfe819bc18302569e" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7e8c77dac7f8dd41685aedac58eef383" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2c31caf801dbaee28d92238dedf771bb" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "64928d45083774a5af2e176b07290c08" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f9c7624248dbac6c1fcb58aea5528d47" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "34d05c67b3091498883eefd6c67fbdcd" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 12075008 + }, + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 12091392 + }, + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 15761408 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "30ccd877b4796fd264698fc8c7169fb4" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b7fd1eff91aea059e79496764482a61d" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "632df46c64efe7e51aaa41d7daba0d79" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "5089efd3781793492aab08101aa07c10" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c29809ab709bd74cb8d454b2cece92ee" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "34d71d974d30dda83e7772ee5471597b" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ddb37e3db949b258fb9e3e6572780a27" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d1d9d8dca48b60cdb85731784544ee83" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "01aa5a99364b8d5894964d8fe36234a6" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "273fb95dea3e4848307148cf5044c20d" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 28114944, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24428544 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 24444928 + } + ], + "md5sum": "3f0e6f834f88ccf775e27be94295645f" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c8b79b1e66187668bed099be7099d1cb" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "777491fb5bfb16036ae91b5a4ebef130" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9be97d51d5fb7d2fe3829569a2ad924b" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0f55e3e98a33b33db3838e90f32816cf" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4ea7d81e1f6e740ecb15021183e938c2" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c25ce33d3ac4d0ffd7fdc8c7ecfde824" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8dcd987154baf55a748396c54480bdaa" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "19e1ee9456987e4cda2c6ba5c007f2c8" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "1407d5ae777a9c246d516da850da6f7a" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8ae6907a8cf89121f68693e3b5a63f21" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ba1d0d9b0c9dc38631524cc42dd0a8c4" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4affed2de7a8c92cb837cf08b442bdfb" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8289ea17d79f7fcedf2fb68b63119f46" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "19fdd42368ea9ffe0b5e5ba09c54bc81" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "99e7e7c5be722517dd0c57302c309c4d" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5603632441671b36c9a63c59d70e46e1" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1969fc27cdfb4c93b505287317ae6137" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b6720568cf479fc9e0d12ae2aba56935" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "07afda7e70c193ae54fb045890bc5a4a" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "6c311af7d5ce5c42338345e86f454940" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.42.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0f2390981da40ee17ad0c304c54c39f5" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "42c1cd65568ccef72b282794346f1072" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ebf3e71800f609d13e4f19c8fdd45ec4" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c772735c1425e1160f5443f186e3f98c" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "030644a9dad18b623364715ff9fa11d6" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f4bcea1e59f974535406c66afd538930" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1a4b45782b1bf9fb3113fe8e28fffd45" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9f880021cce2fb846475d1e7a656035e" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.42.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.43.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "6f91bcf618e72719d41e352fc32f252d" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.44.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3609ef8a95160047e47d62550461a2a3" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "279b7be92755bb281989f28fab742047" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2262d7408b546fd6d5141ab4faf22c65" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.45.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d6e255341b24ddc9d1759ad76b4c42a6" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "21d35a869de8054f852a661010da9612" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9b5255888c6d7effa017ab90900e005d" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e084b24048946b16667976b99bdee058" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8afac5754347eae8def7807680b077ca" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.44.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.45.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "663223a10337d35a8e019c5c40d5fde4" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0eafe3652c9e1f354037d5b5d7f25184" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5be97b9b9d4b18872e959afae821079f" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d15f2eeee7ae5bfcaceb65e952ab51ea" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f92ef9197e16a08ba008fe9c5129798b" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.47.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "79fb7c7e64e8c5b9cd6c888af8ad381a" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d5d6c9cc2c6e719200178f8f21eb9be3" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.48.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9c471cd81096f026b544ffca8b075dd8" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d1223f3172803f705f9c9cfbe82485b9" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "65b929a8e516cbc1511c4a6bfd806ad9" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "14580b4d64927ae4fdd3b5f8b50e8889" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.46.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.47.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.48.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "5c58d9390e1d4858d7570911aa0db804" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "eca2ef1c7b0e444c99b07cc36050602f" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "cb705bdba02d01704fb614aa32b2bb38" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.49.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "96ad1e4907252fe163c600ef791e723a" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2114c4292828df499a0159f166588dca" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bd24ad6d7395d76362716f979a5b48fa" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "75db6ac509b7d9ddc43ce63f8fdd0b33" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.50.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "016bc4a3304a8cd34ca5ab297defa696" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "41d4d7bed32becae70b36315a443e31a" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.49.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.50.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "5d61eeb2a2dbadeb879c8548bda4ff7b" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.51.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c01a55683acbf6f15e7c0b3929af9bae" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "de2ccc63968b9564a20173c314197819" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9e1d0b561dc0bf82a54220655e9aa592" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "54711db97eeb40358dd63f3825551b06" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "59f7f003aa0744e6669117109a812d28" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "868d2c3b7ea97da6e9d648155b4bc69f" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.52.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "27a9c162ff397380e192a8343ec9374a" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6e9e8b9e3e29f38af153cc335e6dc947" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "02ff856d99434b76a853cc73478a4c48" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "2ae29f87e9d9c3187867e6011f550c96" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.51.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.52.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "577e75ef42e9895879103627b6e59569" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.53.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5a50c2da8466d4f489652a7c14f81119" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0f5ca0a8c67158b7ba8690d03558ed1b" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4e707c9066d278882227c601ffec7be9" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "75c4bcbc5598bc0ca99cd2b25ae266d1" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.54.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "330c1759f96dbd89eb91a4b46435a8b9" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "7c5feecb3d0c3b30a35df361caf052de" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ca640ddfb7780978dd56ccb748ad087a" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f731f4f07ff38e2ba2a49d840f67d02e" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.53.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.54.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "330cc1c93bfee923a2e88f5c68a5501d" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "99a911d9e99864e2112bd5bb2bbdd19c" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ead61be16475f36814978181e51bb030" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8a1fbfa9f095c9efafb9c08e2919635b" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.56.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "24acaddfb91d4d9e74f7bf2bd4edace7" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f6644ba7fba7c575e2332b2910ec0a5f" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fbec254bcfafb4a22b230e14465f55f0" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a7490365bca18bd717987e5517df436e" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fca77f1911f6cba5136d18caa2fef548" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.55.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.56.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "43dc193856d323fdbf266a38c5779922" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.57.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "974d58217cdf72a2c91b64446733b325" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3387563bbe45c6be27975ad29def2f1b" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "461839505502c7881d7da79512bb8051" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9f095a3501e07a91c8289cd60e95bc23" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.58.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3056122712a9e98bd07f226320cd0ba8" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "17e46ef0062d108e06a864f616a2c3aa" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.59.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bb75dc4c14cde443e6debad84382c04e" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "54329f61ad47b31a0b7a9a81b57a47bc" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "21392cf5420d3688a46b0927e797c470" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8f7a8f9e05406bd12565e33e3b0e0e96" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.57.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.58.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.59.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "c1b2e40578bc6042b7d023c56d8a5632" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "455cdd15aaaf909d319b2332e5ac01bb" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b555cac78f362b83f2955b1c91acda13" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.60.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "62d775ed72e59fe3a10e5195da6bd512" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f937e8d2b6305a0d9802099dedca9728" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c636517d8768268e583f243a8a29d09b" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "01facfd13b0b7f6594c97c88576ed25d" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.61.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "614148f4d2e7ff69587a8d59e7f4e2c4" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "002c17ae124cfeaaea821689ee3a4f1c" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.60.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.61.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "62966aa2b64023f68363749a2c513464" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0f92ac9205729489247fb07340aace96" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "5d6f856c59ff079f1ee34add0de3e67d" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "97d895a505843509fae065a1d009678b" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b74aaefa562355bc2bfafedbbf0ef6ae" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d201407c61d540d89e2f9efaf9baf0da" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0e124bcd7ebda229c9096eb81266a12b" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.63.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "347cdaf3db0a34a79cc8cbac16ad2f12" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9aef1782bb8e5988ffb3c20665112a64" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cfc16648f202ee46262772795c40e678" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "376643fd129e576b2188c51090bc9fa0" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.62.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.63.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.64.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "83aa3ef04a09aa01336db05f112e7f61" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.64.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "ad54bde685b2da77bbfb037dfa5e4914" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.64.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3898c37583b477474612f15fc5b99081" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f28b2a7e2b01dc4d87f2c954eccbccca" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "18b457f196e38a7ab0bf752ca0328763" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.65.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a476f5ddaa2cd9b6aa1f1b150db5e847" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.65.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "10b61940d19aca36e28269d1f890d461" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f5de856bc2e9c87f505428588fc1443b" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "dc2031a03433ea5c03a06172b995bd18" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.64.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.64.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.64.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.64.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.65.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.65.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.65.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.65.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.65.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.65.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.66.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.66.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "33ec8db5e6d881993612a125dd851df9" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.66.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cea6639f3428190c4a039b2d078fa87f" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.66.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "502585ec5e7ca20ef1727c835d40ba83" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f304cbfab1f9f824ce17ecae669fcb23" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.67.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7375b61c4ea7cf7802bdf215d34f3e23" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.67.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b0483199c9b4013c5d9c52ac48c79fe4" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2cb5a1e7df3a88545b6be7dcaa2d4166" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "da47d56092c6f118b4b3d393bd6e8328" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9cda5c50ad22b9159e9ef3b2f336ad2e" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 26804224, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.66.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.66.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.66.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.67.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 9715712 + }, + { + "name": "model.layers.67.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 17055744 + }, + { + "name": "model.layers.67.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 18366464 + }, + { + "name": "model.layers.67.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19415040 + }, + { + "name": "model.layers.67.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 19431424 + }, + { + "name": "model.layers.67.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + }, + { + "name": "model.layers.68.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23117824 + }, + { + "name": "model.layers.68.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23134208 + } + ], + "md5sum": "60a37d160cf0222635c3f2b5ab40c4a3" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.68.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8c644e70185676b42ae8cb6ef8f191b9" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "22866b1f21bbc156691e02f3ea9989c2" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d72cfd9e9d541f5f24218fb753f48f25" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c80fb10606f530a7ab1606317bd9ae0f" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.69.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e88d60d923855df24a71ef7e5aadc7ff" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.69.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8771096b7586c86515d98c36d2f1a966" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.70.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "01f85b64c7bb79f7c1056b27b80ed53a" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.70.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d83f35dd24c463b14c23c285af255d19" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c70b9f741f2fb6ca5302398f220d1649" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9d0cfc8e5a2c95d39a6cd70c13242d27" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 29163520, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.68.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.68.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.68.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.69.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.69.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9732096 + }, + { + "name": "model.layers.69.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13402112 + }, + { + "name": "model.layers.69.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20742144 + }, + { + "name": "model.layers.69.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20758528 + }, + { + "name": "model.layers.69.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22069248 + }, + { + "name": "model.layers.70.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 23117824 + }, + { + "name": "model.layers.70.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 24428544 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 25493504 + } + ], + "md5sum": "a6877ed82ed9c968276a136b6e378859" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e343cc99e4836e3fbbacf6556887076b" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f9f9d4ef4a016398997488ab821b13f8" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "cb75286bf1aaa8372cb7f2b89aa36e6b" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9c13c0f00ac62c298118b39b6fdb84bd" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "209becb42877a79b6a0d51983ae5064f" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ed4bb5a6f09424c9ffda78abdd16f3c4" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6ef2af93afd89be6a09cbdc23f2e3143" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d45f467ef38e313da8d61512088eb729" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "28288364a5a12c9f02a303278bc84c0f" + }, + { + "dataPath": "params_shard_324.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "68e19189d9232b9f041bc581ec68b0a5" + }, + { + "dataPath": "params_shard_325.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 7356416 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 8404992 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 8421376 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 12091392 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 19431424 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 19447808 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 20758528 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 21807104 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25477120 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26787840 + }, + { + "name": "model.layers.70.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 27836416 + }, + { + "name": "model.layers.70.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "ae8965ae4e77a6b282ffdfbb5c41786e" + }, + { + "dataPath": "params_shard_326.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "27c0fedb0e17e26b9be8e127b588b89c" + }, + { + "dataPath": "params_shard_327.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a9a474ce035753e67d6557a5bc7ca207" + }, + { + "dataPath": "params_shard_328.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "679ce937c544dc6a6be3ccf13b22e7de" + }, + { + "dataPath": "params_shard_329.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1be261207bdc1993e1e59f1ca416e347" + }, + { + "dataPath": "params_shard_330.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.72.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7acd59ac92dff12ad89705be643a8734" + }, + { + "dataPath": "params_shard_331.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "15aec20d9f7a52c6395631a8a2157d16" + }, + { + "dataPath": "params_shard_332.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1f4fe57a25173dde5790e288976cf5da" + }, + { + "dataPath": "params_shard_333.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "817d9fd51f1349d90b7bd1e896518403" + }, + { + "dataPath": "params_shard_334.bin", + "format": "raw-shard", + "nbytes": 33112064, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.70.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.71.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7356416 + }, + { + "name": "model.layers.71.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 7372800 + }, + { + "name": "model.layers.71.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 11042816 + }, + { + "name": "model.layers.71.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18382848 + }, + { + "name": "model.layers.71.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 18399232 + }, + { + "name": "model.layers.71.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 19709952 + }, + { + "name": "model.layers.72.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.72.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 20774912 + }, + { + "name": "model.layers.72.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 24444928 + }, + { + "name": "model.layers.72.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 31784960 + }, + { + "name": "model.layers.72.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 31801344 + } + ], + "md5sum": "267a2940a282cee7b97afbf50f523ef2" + }, + { + "dataPath": "params_shard_335.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.73.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9f0d72234c0eda43ac969f1916277aea" + }, + { + "dataPath": "params_shard_336.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a02c2c9a204b338e8b4ca06716ef1f21" + }, + { + "dataPath": "params_shard_337.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "226aa134c762243f65dac492574bd5f2" + }, + { + "dataPath": "params_shard_338.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e04364b7107ca3f637367a3a433ea82a" + }, + { + "dataPath": "params_shard_339.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.74.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "192a4fc4e93f2fa8fbdead2181b60cc3" + }, + { + "dataPath": "params_shard_340.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "4146daf127622c5203528f7d7eb2b0c8" + }, + { + "dataPath": "params_shard_341.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.74.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "728d4f6fa381506740311c0e652fcd38" + }, + { + "dataPath": "params_shard_342.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.74.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2c3a00cef5e3998ec483e4d31e880a57" + }, + { + "dataPath": "params_shard_343.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "55a05edfcb0264d0007026b0b6eec428" + }, + { + "dataPath": "params_shard_344.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d9ed65ae2697b361c805f3cd6c2b13cb" + }, + { + "dataPath": "params_shard_345.bin", + "format": "raw-shard", + "nbytes": 31522816, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 0 + }, + { + "name": "model.layers.73.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 1048576 + }, + { + "name": "model.layers.73.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 2359296 + }, + { + "name": "model.layers.73.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 2375680 + }, + { + "name": "model.layers.73.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 6045696 + }, + { + "name": "model.layers.73.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13385728 + }, + { + "name": "model.layers.73.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 13402112 + }, + { + "name": "model.layers.74.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14450688 + }, + { + "name": "model.layers.74.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 14467072 + }, + { + "name": "model.layers.74.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 18137088 + }, + { + "name": "model.layers.74.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 25477120 + }, + { + "name": "model.layers.74.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 25493504 + }, + { + "name": "model.layers.74.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 26804224 + }, + { + "name": "model.layers.75.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 27852800 + } + ], + "md5sum": "b699643b2520ef6b115b0e6dd129f5a1" + }, + { + "dataPath": "params_shard_346.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.75.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c72a3ee63224b4eb34bfe3485b6db29a" + }, + { + "dataPath": "params_shard_347.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.75.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "81161a0da23723c17d2c2a7866daa899" + }, + { + "dataPath": "params_shard_348.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d4ac69960637e5343bfd6398c42d5edd" + }, + { + "dataPath": "params_shard_349.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "22b2b394e0c1f77e4bb3bee4db94fb23" + }, + { + "dataPath": "params_shard_350.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.76.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1245f194787660c939e06d20ed222a7e" + }, + { + "dataPath": "params_shard_351.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.76.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b7fe10f14840df968251131693d3e104" + }, + { + "dataPath": "params_shard_352.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_weight", + "shape": [ + 3584, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0d589884b18c58bb00c05dcf73aa82d7" + }, + { + "dataPath": "params_shard_353.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_weight", + "shape": [ + 1024, + 57344 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "dedf357090aef5a98c35fdef9c4a8818" + }, + { + "dataPath": "params_shard_354.bin", + "format": "raw-shard", + "nbytes": 26820608, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.75.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7340032 + }, + { + "name": "model.layers.75.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8650752 + }, + { + "name": "model.layers.75.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9699328 + }, + { + "name": "model.layers.75.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9715712 + }, + { + "name": "model.layers.76.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9732096 + }, + { + "name": "model.layers.76.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 9748480 + }, + { + "name": "model.layers.76.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 13418496 + }, + { + "name": "model.layers.76.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 20758528 + }, + { + "name": "model.layers.76.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 20774912 + }, + { + "name": "model.layers.76.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 22085632 + }, + { + "name": "model.layers.77.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23134208 + }, + { + "name": "model.layers.77.mlp.down_proj.q_scale", + "shape": [ + 224, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 3670016, + "byteOffset": 23150592 + } + ], + "md5sum": "58ec1be3855a545fcfcd4ccac65fa43f" + }, + { + "dataPath": "params_shard_355.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.77.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d7f2388bce4f1c3bdd4dd110980b8326" + }, + { + "dataPath": "params_shard_356.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.77.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "85bca053d1fd892872f3daf5fbdd0c16" + }, + { + "dataPath": "params_shard_357.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.78.self_attn.qkv_proj.q_weight", + "shape": [ + 1024, + 10240 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b5a152a305b212fd71d88efa0d378cab" + }, + { + "dataPath": "params_shard_358.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.78.self_attn.o_proj.q_weight", + "shape": [ + 1024, + 8192 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c7effcf6de4bc739855d76b26e152423" + }, + { + "dataPath": "params_shard_359.bin", + "format": "raw-shard", + "nbytes": 12075008, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_scale", + "shape": [ + 64, + 57344 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 7340032, + "byteOffset": 0 + }, + { + "name": "model.layers.77.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 7340032 + }, + { + "name": "model.layers.77.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 7356416 + }, + { + "name": "model.layers.77.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 8667136 + }, + { + "name": "model.layers.78.self_attn.qkv_proj.q_scale", + "shape": [ + 64, + 10240 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1310720, + "byteOffset": 9715712 + }, + { + "name": "model.layers.78.self_attn.o_proj.q_scale", + "shape": [ + 64, + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 1048576, + "byteOffset": 11026432 + } + ], + "md5sum": "c5e9da5090e20220c4c20ae36ddedb1e" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..d95aebac7d4b5d97e4052bb7cbe5bc87400fa455 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ed387cf45a835bf9e9de38d9665d743cfc926ced7533a890a4959a246533691 +size 525336576 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea1a8d9a798aa90b8cabe010206c46ad60981df8 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d063fcde695dc5aed8bb2da6b614493f9ac87c3dbbb9a8882d7e0993c641425 +size 117440512 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..40f1e4c9b00276065f02a5f65fc1cc41ba230ff6 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c6643ba6fc2fe6b80b7327625687c07fb0da6009506cae43cf7ad9c9c6e4d0f +size 234881024 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..990a8d7420fb00c71ecae420721495e032303cfc --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7e42b1dc2e98ba65c1c83e28ea8c45023ba774c106016640d209c999c0e610f +size 41943040 diff --git a/params_shard_101.bin b/params_shard_101.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa7477bbde86326c56ad2c53df0007865122b47f --- /dev/null +++ b/params_shard_101.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d616d5b996540515b52d06cced2a6424064f6c5c7757b398cab538084994502d +size 33554432 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..b173bfc3a64a6b213a98c3d5878ca6433a481df3 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d7fd62bb81b5b39d47dcba02a0d13d9e00c02a12ce869cf597ad031b00fd8c +size 41943040 diff --git a/params_shard_103.bin b/params_shard_103.bin new file mode 100644 index 0000000000000000000000000000000000000000..450d58d20e2b0c007acea24beeb62b72fea06191 --- /dev/null +++ b/params_shard_103.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34c941afe3019499d227a5aaa02c6b073662af100c96f5150361774803b1ebd +size 33554432 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..34f0895119d6d23f423a061843e379d0d35d254d --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:697b99a5c57e04c9c7ca34928566ecb3604e75e559e92e1ae9436abad2b1ca39 +size 117440512 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..1fa6d61d9e2f0aac1882e04150737d8a03c3dcfa --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c444ac4c27708f66cc825c912cc81ecdee15bce522bd13946e57bde70b036d16 +size 234881024 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..91c3b765022352ba501f69ba7297bf3d510d1cd1 --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d1917761a9f4dbed93a976ac922192b0205bb1ea6da4b50f315b45ad6b1bf5 +size 117440512 diff --git a/params_shard_107.bin b/params_shard_107.bin new file mode 100644 index 0000000000000000000000000000000000000000..a0433e98834231a5501de5435dae07f0885ce62a --- /dev/null +++ b/params_shard_107.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e0854f2628798278a88bbc19db28c48617d7a222637cfb4c3243fd881d8db50 +size 234881024 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..9495f3948fbcfcdc0491f4052bc93a1b49d4adfa --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898b71b9b31e63b6522382b5c44fd22bce17707d1e53cb4e552969fab890283b +size 26804224 diff --git a/params_shard_109.bin b/params_shard_109.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ee48d76d82d98f684fe95bb5b7441ed66b7f740 --- /dev/null +++ b/params_shard_109.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19d516eb5570d8be92df5821ff4c5a18fcf37902650bb6853e345a0717ac902c +size 41943040 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..bd49e60855bff456fd521fecb004333186b207ff --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6078fa49b91662de95dafd14477ef29357e44e881c3a4c668c8339362a8a031 +size 29835264 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..7b5954e5206dfb593709fa4cbc9c73ea072a81f1 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4474eacc02918b62017cb1d1d7be97fb98e1c5e1f4394ea88dfcf4e5eab99e +size 33554432 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..67ef8f8ad319e2ebcbd34532ef30dc0320196a7f --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f38ae0c435e52ff4cff647f61883a1d23a31696528861eeeeead1af12495988 +size 117440512 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..948c348b57ba5039c86c1a038e5411fdc4f78e0d --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc6c383ac8427ee4c7d53bc126b50e6f8fc920c264e7518d1da302eeadbfd73 +size 234881024 diff --git a/params_shard_113.bin b/params_shard_113.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e982fe4bdba71e998e854e0d1b621f4c15044f6 --- /dev/null +++ b/params_shard_113.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a412783880a551fe11f3a1474f05347293594f892a67f917db4b10b6a23a86 +size 41943040 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..937ace8f86f20254d4582dab8ad8432f904eb3cd --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79099404b1dc3f9f164ddc9709f20ddc95531049e61e095c68835e231475d9f9 +size 33554432 diff --git a/params_shard_115.bin b/params_shard_115.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed8b8b42e3a2bf91d5c647140c84ddd4174f9725 --- /dev/null +++ b/params_shard_115.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2bee2917571a13816003e266c9308cfad76616f9c26e3a8499a85c970194fd1 +size 41943040 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..26f04e79cb032e5cb266149aae743e0c89ea511e --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd05b75f0eafe0dc2b7b132e182b34312070a49a2a0597cebcb9f89b37062f1a +size 117440512 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..85f8438b51d1c4ecf48200f009ae856a60fd16da --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f74ba536475d6e31f10902dbee2488f48e70e6c28a2dcb3442f73432fde3ee7 +size 234881024 diff --git a/params_shard_118.bin b/params_shard_118.bin new file mode 100644 index 0000000000000000000000000000000000000000..5344362276c540f870f7128e074dec3dc518aa3c --- /dev/null +++ b/params_shard_118.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd30d8cd59130a6ec359f3c08158fd4ee5b15d24a82e8a4f8376c4e9062693ae +size 28114944 diff --git a/params_shard_119.bin b/params_shard_119.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc28d2391ba195286d815cb964a0bb674d2f302e --- /dev/null +++ b/params_shard_119.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b63058f1f2d3aa2a880b5c4223d13f8420fa6fa8fc2a92b5559c309901574e +size 33554432 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..0e8d890b276642230cdf1746968237e216258366 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:527409fa3c5921ad432efbd43b617d77c1ee8ab9a94da83919d479df7ef720e8 +size 41943040 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..02f9b593247d98bda87a5001d4181ae757db6d63 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bd515a2268f94ed67576c9a05ce5c2bcf5678d375d4fc83cab017327339c3d +size 117440512 diff --git a/params_shard_121.bin b/params_shard_121.bin new file mode 100644 index 0000000000000000000000000000000000000000..3bea72bc81a94f12e6bdb24cb63a034cf5a25282 --- /dev/null +++ b/params_shard_121.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa73cbbc46fdc17f751f17d36b4c2db87f39684653a84c8cfb3230e54b1dfe70 +size 234881024 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3d4eee8777ef13acab275e7fda949fcb9373bbb --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa2d94e2b7b413655b01ae09f5c3d76d8eeba0b01363834a42a59173155edf0a +size 41943040 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..eabf8ab812e2e5d827d0f58641d3301e7cda163b --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5445f3b606e1bdca41a5e6b113ebfba479c210d8164971f99c618b0a43a0a1cf +size 33554432 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..e913f87d92b8fbaf22576dc1a9e24881bbdea263 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162184e0892a0309cb03ada25a18d9fea9383f4d1a885b1ac46aa0f84dbdb0a6 +size 117440512 diff --git a/params_shard_125.bin b/params_shard_125.bin new file mode 100644 index 0000000000000000000000000000000000000000..15692e0262145e84b4360601e78b29add913f164 --- /dev/null +++ b/params_shard_125.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7113716a25832ee1e8bb1bc64f64e855b1c83c4ca650e7128527d035423dc2c2 +size 234881024 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..9cd25e822c3355b75c7dce99e194250b09aa8864 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e66cd9768b305d87fd58a79a5c8eafae4b32c352c886c49582ab3ac21a2c3f +size 41943040 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..51c9818026e0ef7c9324795143e7d9d31524f28e --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22720a28e914dbeb6e07e5a4cd2cda9778eb12f6e9d9669354ee0c3ff44b71d9 +size 32817152 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..fc910b619792790df78070af7e4a8f8f14f46589 --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c09ef0695a36868fbe4e4a1380d9c2845573bfd1f438659db6f951411754ada1 +size 33554432 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..02c49ca13d66099585113e522c67927f5dbdbaca --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6c6278901ea383738f7fdbaebb51e05fa300b1f3b3bcf90dd2f9f22a9144c6 +size 117440512 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..5dd4a946d31acccef2c7850c380029f22c4cca05 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faec2f2a3a76730388731adf81bb29399ed1dd00a50dc5fd82e9a8b46c3b8def +size 33554432 diff --git a/params_shard_130.bin b/params_shard_130.bin new file mode 100644 index 0000000000000000000000000000000000000000..aa76b0c33ec4da87c7f1bc00fa1d3ec1cee43ac9 --- /dev/null +++ b/params_shard_130.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08144f96d01061cc84e453fc1a834b0a93a749ca96022fa325a1b66b5e0756e6 +size 234881024 diff --git a/params_shard_131.bin b/params_shard_131.bin new file mode 100644 index 0000000000000000000000000000000000000000..925b705901c44fe3355af37502f09598ac07e94a --- /dev/null +++ b/params_shard_131.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d217fbb4188c77ff52ffe3f34881f2a8fb46268a9859b2a0dee8d1f4ca127cce +size 41943040 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d21ca3331822daced0694460bb85e2f5df6c6ac --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ff60c051b3c005318f6f6687afdaecd2c5a65ad429f369dd1a492e0beaa040 +size 33554432 diff --git a/params_shard_133.bin b/params_shard_133.bin new file mode 100644 index 0000000000000000000000000000000000000000..6d0d9497d83a9303bb3c2fba0cb3d41bd424311b --- /dev/null +++ b/params_shard_133.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85dd35b56dc20aaf5589d2ac6c2f7a995ee12695806b57958aa664aa903fd804 +size 117440512 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..a6e4510cff9409ad6e04dbc23ff8c7425663b784 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4199ce13a8912cb02735e345ec3357db48f070ee19001f5df7a875089e9a69bf +size 234881024 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1960088fd9d948594cf5eef060a192b6eeaf70e --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ad65703c1223b45bf2c8892484ed3a539c785c7606af1df5c86330054bda862 +size 41943040 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a76a20bc4ce1e2070665721919c376ba2345280 --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8157158570fbec102c4f3abe066ecd5890a5b13c919600e4b94f4f1bf8c0b359 +size 33554432 diff --git a/params_shard_137.bin b/params_shard_137.bin new file mode 100644 index 0000000000000000000000000000000000000000..2337ee090e1b6c5ca1f9e6398bd81a933d2d614a --- /dev/null +++ b/params_shard_137.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0f411dbb0856190c581268387634c772c6023abc04205aa1468f5234017ea4 +size 234881024 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..1c09bfe25467c171b5ba58852afab3f73fdd9131 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0673f87406fb7c9f3be5332c843dca0a95a2ff23f6a057bbe708cde490a4a34 +size 29196288 diff --git a/params_shard_139.bin b/params_shard_139.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f8b5367bd302f7521dec3aa05af5e4b01b4b6a5 --- /dev/null +++ b/params_shard_139.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ed4490b31593e8bc7d9e215760e599d5b50e9bb336b7f95e8b19b7a224352c8 +size 41943040 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..99e50d929408b1c67f017b801a63ab9d64209c72 --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a1f8ecc87f233397a51ad5c5b5a4ea6fee5f96ff9761fc19c7e2d298fdce53a +size 234881024 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..97831df7a2e39642a1399d52da7833f5f7aebc77 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a01f7e55b255f002069972d2e3ef8a5e4ddc29fa423dec69bdcd7c26769d4a +size 33554432 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..4bfcb3e9568668610dee6d325eaf180c28cb19fe --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb779fba55d88d205c7c9c85d22651e47a8549236bc8b40f9d8d2eb83918502a +size 117440512 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..51e18af0742cf77bdeb06274e0f7ad2e90d5eefe --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:193c478c8065e34b44d52d3865a30f7bc231e168077302e2103c541cbd53ce96 +size 117440512 diff --git a/params_shard_143.bin b/params_shard_143.bin new file mode 100644 index 0000000000000000000000000000000000000000..efc98008054f39a41fa308e86706d7fac8e6d799 --- /dev/null +++ b/params_shard_143.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52f9cba21af86652adb70cbba96a1ef09bb3932e1f776cea98068193a5c5edbb +size 234881024 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..a840cdf7bd9ad7b27a1e11fa46de4ed6c583857c --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a149d4837e99a773ea10301770605768e6b2f239bca12457137e4d8f78d1322 +size 41943040 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..884bf52276471ab5b23e70900255689323973498 --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2f84c9851fe36bc335b5afb8fb007aa78d1d08cbe92712032c76ac2bcc4862 +size 33554432 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..fbf68c1868bf337d88e149d25cbe6d32003feb9d --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a36626b997be23efe532059ceddf52918682d6842c50c671dac9e7befbe95e +size 117440512 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..9c10a2c20dc8f0087a3fb43fe23fbae8603932a7 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7323fe51a60bf2f64d4352df9e0201e25a982a905d2d3b04b616cd0338732c91 +size 234881024 diff --git a/params_shard_148.bin b/params_shard_148.bin new file mode 100644 index 0000000000000000000000000000000000000000..691ecec30e700478e84be36e5f2f09f5a3119151 --- /dev/null +++ b/params_shard_148.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b62317d66e35680b780258d9afe7a32df79aa4b3780273021176eff4ac7685d +size 30490624 diff --git a/params_shard_149.bin b/params_shard_149.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3895e3474617a5487ee86c9f7f67efc6fe50b36 --- /dev/null +++ b/params_shard_149.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf3c32e74f1373060ed99492f4a04886f57bdd6b4d421509466b8b37b8da45b +size 41943040 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..e11bd635bea089f416f64bf56fbe20a52e1ce2e2 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01b36fe06567e064e3ed108f2823208ab64bbb7c7c3d22a137216a1c9edb005 +size 41943040 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e04f64be0d4f3f5f86d448890fcb03608cf8687 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93dcb1f6c66610b1feeae00c22ee5faa3da684af13f14e5182b321e991152075 +size 33554432 diff --git a/params_shard_151.bin b/params_shard_151.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5a4ff87d3cb8d792f4e40a4d9ebef8c21e82474 --- /dev/null +++ b/params_shard_151.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601095d1ea60a831a2d3b8820470d71d3e4cf35199b4b1bcf0fcb7e185837144 +size 41943040 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..518d8715c3566fa94699ecd49808855952084fec --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f477b6da79501470ba13235215baf833f275f2b86b342cd26dd3a2b91138b5 +size 33554432 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..4b816867dabfc660130627dce692738252ec7a60 --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e47fed9b2c0b41c7ca7d1338ecafaf5427206887d90f589c6e0565eb54ccc492 +size 117440512 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..155cbb5d36d39760773b169d0a0579fb6e7deea2 --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f370348f1c443ca391a43d3c54d4388bbe4ae804d1fe4f64b10a70f14312860f +size 234881024 diff --git a/params_shard_155.bin b/params_shard_155.bin new file mode 100644 index 0000000000000000000000000000000000000000..e99c18c0f737ac4b371de655e26c716f50e09a31 --- /dev/null +++ b/params_shard_155.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedde64bf9a1fba97e5615cb436b53910ec9af4998e214696790f87ad2607b45 +size 117440512 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ba6a4464716b44f7920af52469603cded89e089 --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed56774799650f430fe8d3621eeac923dbe75669b46b90df749168335bb8c791 +size 234881024 diff --git a/params_shard_157.bin b/params_shard_157.bin new file mode 100644 index 0000000000000000000000000000000000000000..3efa23fe0d84dd978e90e27188652bea346d80c7 --- /dev/null +++ b/params_shard_157.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98db50d322d2e45de3dea2096e70993908f40f3b30bca36ee442ff7fac2519db +size 26804224 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..d330af22855fcf305fbc0ed925012bfbf0163e5d --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b91e2c73e56a87082844a4e957339519596b2501547bbcfce66a03723fffd69 +size 41943040 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f467cc3a190cae5688f614e5d42104a044e303e --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1173e24d7cd6d90a2517499bf9d3de3c187ce04e965b28d866863b8757c67f49 +size 33554432 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..d08fb537cefa477ff424194cadef91781c8258e6 --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7da61970eefad5563e2abf88fbcd6128b97452701329796e4e4171115d947bed +size 33554432 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..41400679cfe25bf2a152e930cddc3d29e0d2be74 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4085bad4f144f69481fb13d3ef5caa405a87813e5c367b2d0097224f46666dcb +size 117440512 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..9201fa7da7070dd868677082ceba122c35f14e61 --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc33cd73d9e63f6ed0870a5184d80ab03bfe0e3fc8ced0628478744f14eb964 +size 234881024 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8228e9783dfbf0eb2352ab83eecf00143c36d73 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abfd208f98d031d1c0086a24183f4533ec51a62c0547bd6947528598211d5f2 +size 41943040 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ecca799b1bbe05149d9972cf9babeaf727cdb31 --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c784630fb84084cee9eff9783d5ad880e7c51e81ba13228eb5c3121425d88ea +size 33554432 diff --git a/params_shard_164.bin b/params_shard_164.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b8ed18b6939b0ea7301937652c9dfcd0d95d719 --- /dev/null +++ b/params_shard_164.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551ae9f2122e4a9e2cfd980817885b2f88d11b508c9caa7236367276293b35d4 +size 41943040 diff --git a/params_shard_165.bin b/params_shard_165.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8d522f3ffa3b46af4c16874ad871bcc029ce49b --- /dev/null +++ b/params_shard_165.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6cb9566f982eac43b1fbfc679f2cf67bea405be8f9f3c224ab1e9c70916109 +size 117440512 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..ccc7f8f0bb7c2ee966044e2d1007006394ef2df1 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1d5d0d8789ba350808a0aac0a2d082c7fd83e22b07877e8d2b837d500825263 +size 234881024 diff --git a/params_shard_167.bin b/params_shard_167.bin new file mode 100644 index 0000000000000000000000000000000000000000..8bb33ca31b7318e81caa15f7556c6a0468b33a73 --- /dev/null +++ b/params_shard_167.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3144df283be504f0da6ded844f294f9600cede327083f78d61d6a712c38671f7 +size 28114944 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..21f7fbbc56e349b99f8ab46a8920edbd7001305f --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cde2f391e585eb25532bb3337ebe05ffc80422612610699ef47f4d1e851b15a9 +size 117440512 diff --git a/params_shard_169.bin b/params_shard_169.bin new file mode 100644 index 0000000000000000000000000000000000000000..2786208b1005364b317705de1028b7c8ed7e36df --- /dev/null +++ b/params_shard_169.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c551ef94505a71420ec226d6859a0c169723b267d33084282929426640246c +size 234881024 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..13d1cf8e96e5d8a98e70ded09eff877e4c10de42 --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8f3dd791824a363cd2f7937f7da8414fecf0a1fd460b492b6a53a9fc64ecd5 +size 117440512 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..a24de48b745517f0223d495e84b3999cd0be9919 --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3681c0b563c3a641d1d0d40b4b5bb51e181be83acc2e8cf78921d4ac4318ba +size 41943040 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..0abbf216f1972ffcbbbfd481acdabfb55cbafdb0 --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999949f99d5e4d1a2f771697679139f7f9a32205e7c740e5178666c1fffa93b8 +size 33554432 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..f72b6fb8480d22a98c822c5b69030689d458b5bd --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542e9280c648eddbdb696187ba741a44a1e2d1fc9fa93cf9163b81d47b6aa031 +size 117440512 diff --git a/params_shard_173.bin b/params_shard_173.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1af6ab16d781fa7423781b75a1a169b7b85db98 --- /dev/null +++ b/params_shard_173.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fadc2a63217b321c4e78937cc88ee695e9ea50467c3557a15652e6a19f2f1eb +size 234881024 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..10ded34cd382d6ea8cacaa8583bd13eeb5a070e3 --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dddc915d314d6bb5b638df4981aea3e7c30d4facf786b82af3ddec38ca053f1 +size 41943040 diff --git a/params_shard_175.bin b/params_shard_175.bin new file mode 100644 index 0000000000000000000000000000000000000000..c4045c3c8d024a40c789a8a212525beac5e713dd --- /dev/null +++ b/params_shard_175.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40788848220fb940ffe685578b5fb06de864a3e766fe1bc65febbabed8f1a0ca +size 33554432 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..c17cf68e757ddfffd92e08743e24e8b676d71e74 --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17259218bff555bf5e1014e765b211ecc3aab58f6037aa6dd0b2e04bed4b3f73 +size 33112064 diff --git a/params_shard_177.bin b/params_shard_177.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d9e761d57f57eefcc456528c4895a0bcea48484 --- /dev/null +++ b/params_shard_177.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f01293d2e8b395d46006aa984e410d91ebcaceae439897ff12150462ca72f94c +size 41943040 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..5926d19c8e87b5bb66f91bc10e5ca927d4134ffc --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f8eaef8c7faaa81347e03c12351962ac67fd5107f7bea1367af617bcf9b67be +size 117440512 diff --git a/params_shard_179.bin b/params_shard_179.bin new file mode 100644 index 0000000000000000000000000000000000000000..d908ec065d8c34883198ecfeca9c2e6e73d165cb --- /dev/null +++ b/params_shard_179.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01575bc2c2606acdca5d0ad428a0ed6477575d1160d94e314af060aff9f58d5e +size 234881024 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..c7f78bcce23237821e6e53ae23e35036bb34fc0a --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6abe7f323253b79997927fcd1704ddd8940f19d66b9c551ab6aeb7d33e994182 +size 117440512 diff --git a/params_shard_180.bin b/params_shard_180.bin new file mode 100644 index 0000000000000000000000000000000000000000..29344c12ec8f31a2bd9bdcba5bcfd06951d416b2 --- /dev/null +++ b/params_shard_180.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b637733759c3c7946055d803f37a3db95bbffd6cf25426fc383d521ec0ec305 +size 33554432 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d4eaaa45403368dc95030d2a70f6fb26a879413 --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f354b522727974d405125aa60b731ce8b76ac67388a181f1050b2ae3836a25b +size 117440512 diff --git a/params_shard_182.bin b/params_shard_182.bin new file mode 100644 index 0000000000000000000000000000000000000000..d41c59a3b3a017f4aa2d350cefa14a47c7c19aef --- /dev/null +++ b/params_shard_182.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca40acdbd9de3ef48c570e0871d3afd22893d5b1661862cbd965fb6553be1b1 +size 234881024 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb1653de892f46d27d66358d1a0bf4ebfa1a30c9 --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bed5554c47ac8f73988a5fef8de06da7f9ef1ffc80a457a46070f32b5ca313 +size 41943040 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..497bbc5978c960c99e1fb79fa2e37b0ceb31ab67 --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834231e16c644641e498cd13f821abcec9df6f57855e340f6ebf85c305bb831b +size 33554432 diff --git a/params_shard_185.bin b/params_shard_185.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5c88f0fa739b99404172db7106291da1fc7d705 --- /dev/null +++ b/params_shard_185.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f41423417dcdc58235a277b234c71730e2322d448c737a5d2151a77dd454f26 +size 117440512 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..642d6af6ab6363f714b547875ae0dd11f83f2654 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f423ac7220c7c0ea903e8f05ed921f7912bca6a5040bda7e12a1217213c17bb +size 234881024 diff --git a/params_shard_187.bin b/params_shard_187.bin new file mode 100644 index 0000000000000000000000000000000000000000..abdf077aae80f68683d098ed49afadde6a7800af --- /dev/null +++ b/params_shard_187.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80c318c0bedd97acb2c5fdb13872beba85f8ea67ed34d509e5ba3dbfe397685b +size 31522816 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..1793b57cc18d2cb7390cd1334ab25109141700f6 --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d48976c492444cf44ae9acc00d155a1a590ffec3db0d735617790926d1c66a +size 41943040 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ab132d715e829e4f937406d891584bec921dab4 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cdf1e9b784462f3564dd9bc4781e994cfe0d51738460786d6c8ca32ffc4983e +size 33554432 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..e03f32c1403ae5974f7685ca30a12fb04fc8357d --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13cdff8fee85cb8f38fc418f3960995d35b57a3ad3a37aaf09e25d12dab019af +size 234881024 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..23d70902d518f8daca87860b8594591cf755988e --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072d9665f99fd3782e78d14a338dead7750a0ae60c2fc573bf37d30fb9eaec74 +size 117440512 diff --git a/params_shard_191.bin b/params_shard_191.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb28020cc1f8d932d99f1605cb9519266bc53009 --- /dev/null +++ b/params_shard_191.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3cb9507f119b0dcbe5a8e2b0d7fb5d37e2a8103b9fc84fff0d61f761e6fa86 +size 234881024 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..388e5e1c69a39e22c3801d4063b7d3a5a15d1c4d --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e8c236ef455de7ea6f65a681b87f45c17d4eb73346984768cb8e79d6e0adac +size 41943040 diff --git a/params_shard_193.bin b/params_shard_193.bin new file mode 100644 index 0000000000000000000000000000000000000000..bc8c875cd095c299be72ba60779508ecc2732e28 --- /dev/null +++ b/params_shard_193.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d84f8d0cbcce304f2012c66f50b917c5854538e834f0aca0fda4e52704f86ed +size 33554432 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..a7e4129561dd72b18916197058c5dbf4273028ee --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10826adb7ddf537329b2120a3c1cff15875fd62102e60b1024674a2e8e0a7c02 +size 117440512 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..694ceb528bc7c8d6461b52e8bf783a3972efd56f --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2660e11e5b233c6ca70843a386b48b31a5bf472225a8499483a23e93807624 +size 234881024 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf76ff2de6ee9d6080d48a89c8d02fec83170fdd --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a547a62bef92ae35b2818f62b23ed431ff6bf543ba4cb22104fd52441d62222 +size 26820608 diff --git a/params_shard_197.bin b/params_shard_197.bin new file mode 100644 index 0000000000000000000000000000000000000000..67324d4ec4c502866bd8b7e9626e8d9cca053e1f --- /dev/null +++ b/params_shard_197.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b4c038e6a4462cfcc7a99931c70a3a7087dc7eb8b74defbf5b7c3a60c57ed6 +size 41943040 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e751d4bbfd3c59db3f15b919067e4293d10ec63 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07da329e5d6a63ab5b7f0b555067e5e34c8451b96839fe4a612e4df10dc3355 +size 33554432 diff --git a/params_shard_199.bin b/params_shard_199.bin new file mode 100644 index 0000000000000000000000000000000000000000..c259d79d7199641adc6ff15113074970b6eedc80 --- /dev/null +++ b/params_shard_199.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2d8f72751a9289ab6db410dc7b1394fc25e3b147cb65afbf121a08e696801f +size 234881024 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..65f90fb9a83c086de641387973ae273b8c36fefc --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f921bea3da8c396697a8c04b8ffd65dfc0ca209eb2e7fb572fef8c175ec83033 +size 234881024 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..5de496d09875b09878e098d19865024827eb8f17 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb024367ba196cd6781957ae08053311c4dd17cde0520a9694f55511880f9c4 +size 26804224 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..54244b3f00c937c342a8f26be906070567a37948 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1e55cf9b6afeedb00a9ca73405db392cfc0188f233be15e1a9108910ea24f5 +size 41943040 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..e9d6e60521ffe8c707c64b3e2c2a7128aff684b9 --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4329a3a46454a95a528ea6b5d4003d40b01a8f6021afdb0ee872d59214d2a859 +size 33554432 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..0200df370fa86c3f148ff1208e63b2a46c0dab95 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d474c3547a8deafa166ba4c842d0a2351dba5f2915c636ca7f7b5312bfbeff +size 117440512 diff --git a/params_shard_203.bin b/params_shard_203.bin new file mode 100644 index 0000000000000000000000000000000000000000..a34d1ed889f8b1613be06bf1e2e7475be7e892dd --- /dev/null +++ b/params_shard_203.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a54cbbd46290ac6dc7e3d4574d420d5053be9808c23ea1e49702e23e7421957 +size 117440512 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1bc5494d79ed5cf43c48443a23b595c5632fbdc --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af25afeb6fb1ae0faf7bb24c78672e6abfa72f3a2139c9cd92b13fd8f5158a2e +size 234881024 diff --git a/params_shard_205.bin b/params_shard_205.bin new file mode 100644 index 0000000000000000000000000000000000000000..9748fb3a57e75154df8b502c088ca9e35856c486 --- /dev/null +++ b/params_shard_205.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f8b39219197af042d42bbdbdd0fcf2b0fa064e199839a607491924161e834a +size 26804224 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..91e15632d898c0d1de75260d258c3b412c496834 --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1674dfaa711b6ebdded25b36d9ea5aebd44f4ea54a49712496db86d5e7700000 +size 41943040 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..92565e84462c1c1df868ea15196c57c93bbe0734 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dddd4fd1c7956c9ede7a40ad1931da581cc6e5069c293977851853b78dc49f7 +size 33554432 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..018f2df7781bb8c1915493015b2dc0d801e26c48 --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b4d99440aab71be2111a5096d1d707e8ee42ac654b52022bd8415217395366a +size 117440512 diff --git a/params_shard_209.bin b/params_shard_209.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1cf393ce1e23242705e64ba688d3839e8de789d --- /dev/null +++ b/params_shard_209.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a20d9a4409758d3b0286ef06869892e8099b895c0e3c86c8376ab7ce0a12134c +size 234881024 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..e47dcde7954799554ee0252e575a50358f5847db --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f96383c953a507986daf40ba5134503f006cdbbf35aef8ed4833d95e1c6b00d +size 41943040 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..78fd609df4fb585e6d8dbade90edf6aefa5779d7 --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1925465223c57c163b70017abb1048c3ff0e625d342f724b4934bc4d311ed4ae +size 41943040 diff --git a/params_shard_211.bin b/params_shard_211.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0c095f4538ba9a5e4ea84813ae9c979c299d3d6 --- /dev/null +++ b/params_shard_211.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:927bacc6cafd8c439bfcdcfd6eb572cfd37d23ca5b1bbef2dd38945b2e53963d +size 33554432 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..9b100487a397656c733ebf6956b25954e86d1d05 --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aedf2a82a25b76b12ec8a8ef7849fa4a7d92fc5c4d6d16b594fd8862f0e61423 +size 41943040 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a9a333501c04a5ad92867dee354680d6a62b6d6 --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0482d866ee56c5ffb64ff1c46a7fc51d8cfc82daa3c171dad5963fb242d4e58d +size 33554432 diff --git a/params_shard_214.bin b/params_shard_214.bin new file mode 100644 index 0000000000000000000000000000000000000000..247609f0d1d154d86abf189b65e29601765e0c9a --- /dev/null +++ b/params_shard_214.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90afd422a33be87c1813a80308b56d5f4f4804b7e8862116fa6476ea506c767 +size 117440512 diff --git a/params_shard_215.bin b/params_shard_215.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea3d3332fb7b3726be077b90b527ecf92e9ebd3f --- /dev/null +++ b/params_shard_215.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f55ce528aab7d068bc31880923179c116a616acf7c80548057a5cc47a059c5 +size 234881024 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..21d7217324858b20bcf3d462f307c2b4bcb205cd --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15f2e1c25c075c8ef2636951282477e593bf3d4aa31248078eb0c71d2f07d1cb +size 29163520 diff --git a/params_shard_217.bin b/params_shard_217.bin new file mode 100644 index 0000000000000000000000000000000000000000..35cce2189e1c5348e3b4a9b1350c60041de332c3 --- /dev/null +++ b/params_shard_217.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cec6d38353addefaee9b7f9d141b7fc611b0e48b0bdfd6d1ae66baaacbd40ec +size 117440512 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..79836bbb421938c65dbe026119347cfb7998c128 --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89330cb50a3fa3aa268801246bd5495e299f77632d8338df817e9405cbb659ad +size 234881024 diff --git a/params_shard_219.bin b/params_shard_219.bin new file mode 100644 index 0000000000000000000000000000000000000000..ecd51b5f168f9e08e84a1f2114941d03fb1020f8 --- /dev/null +++ b/params_shard_219.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1db28cac7f474a40676b0b291499392e632452286ea5a0289a82f9f29db22e +size 41943040 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b45f8e773a1a41503bb45dacf5bab1cae3c6743 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ae25a7b9959e1d9e01976c52c3245fa85f45dfe7933e95768c250c133c965e +size 33554432 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..2e66bc0839e19ff454c4a26eb8639cc4426b60f3 --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5f4c3d5102c2fc713e5021744a6bf71b7c602c4d36e6b3e4191f2b5e870fe5 +size 33554432 diff --git a/params_shard_221.bin b/params_shard_221.bin new file mode 100644 index 0000000000000000000000000000000000000000..71d9c33177de1c898594873bc126d7b2f352700b --- /dev/null +++ b/params_shard_221.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb3a68db3484a8290058bd70acd025651bb57d309d8de4e04d4b16acfdcd61e +size 117440512 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..f473a29265aac6cf37702a31547625ea4e37168c --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c66b597d784bac644f4350bc4a377135d1d73e80f32ab6f6125f18bce7ac9a5 +size 234881024 diff --git a/params_shard_223.bin b/params_shard_223.bin new file mode 100644 index 0000000000000000000000000000000000000000..08c231c160d6369f7b8b52001b7de1a2952b83ea --- /dev/null +++ b/params_shard_223.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cc20e2f8fd83374198257855f34f1a3c111bf550d790e507e1b820c0f64f1c +size 41943040 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..510fde1ec543848e7837277f15e521dc40107d22 --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a2b4f1a1ea538a218b25c5393a178b4e498e88d1ce11aa3ea2bad316b7111d9 +size 33554432 diff --git a/params_shard_225.bin b/params_shard_225.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba71088ef125ed98cea4ccd340b211c50282e65f --- /dev/null +++ b/params_shard_225.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffe9f14df7df793de9306a79bdc8f66cff842cfe1c9b43748e419b42dc6052f +size 33112064 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a7e4ff8782f3675ae44cec1e3510eb619208aaa --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0aa345a41c7ce8069ea95f0e5eaf55274ba64b0cdc6490b74a8ad833d0c9c4 +size 41943040 diff --git a/params_shard_227.bin b/params_shard_227.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7761a65957869a93d7663ddf58ff94dc0e024ac --- /dev/null +++ b/params_shard_227.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:031a61ba6e378821f6eb66edd08de751e1532be7cf7263466e60a879696deb48 +size 117440512 diff --git a/params_shard_228.bin b/params_shard_228.bin new file mode 100644 index 0000000000000000000000000000000000000000..ba1428126e506c5385caed833bbf1aac43cfb7d7 --- /dev/null +++ b/params_shard_228.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cbbb5485a2793b32d98ae2c79b4676de0ff603bb3eea03c033b761421c5c3b4 +size 234881024 diff --git a/params_shard_229.bin b/params_shard_229.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d7ffae2dd6b2da39000186973f5d555e5c855b5 --- /dev/null +++ b/params_shard_229.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cee1263050a648e70243dbded843a9c6af0bd4218f3b25d9f22663a49a86997 +size 33554432 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..aebe4b6a8c8fbb51516bdd44376b59a74899266e --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea02e6f14a72b72db4cd3e5ff6cad37429aa84614d9b3c53334e8a3b974e062 +size 117440512 diff --git a/params_shard_230.bin b/params_shard_230.bin new file mode 100644 index 0000000000000000000000000000000000000000..f6c2dfa2a08a453a57a1fd236201002e19705320 --- /dev/null +++ b/params_shard_230.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f7c65647f95c398a049b1c1d811b7f91f498768614a2dc93a3c7120495ef32 +size 117440512 diff --git a/params_shard_231.bin b/params_shard_231.bin new file mode 100644 index 0000000000000000000000000000000000000000..d885d57cc53ae9524d9699da2eed1be154da7749 --- /dev/null +++ b/params_shard_231.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b5663c86f25119f5b3391ad5d2bd172ac8d44c24ba8bb21f61724187cfe897 +size 234881024 diff --git a/params_shard_232.bin b/params_shard_232.bin new file mode 100644 index 0000000000000000000000000000000000000000..f4d76b3407b54a3b117952c2d2ce6e2da242eec5 --- /dev/null +++ b/params_shard_232.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e090dd1560aec8acc4647c27df3887274c1bf70bc68865b8e578ef37624dac1 +size 41943040 diff --git a/params_shard_233.bin b/params_shard_233.bin new file mode 100644 index 0000000000000000000000000000000000000000..a8ee958e04dc6bcf73e1096b0a7836096e0d6ff6 --- /dev/null +++ b/params_shard_233.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45de6ded618a110edf5563d41760030ce6308a0f44ad0bb3943428189df5a711 +size 33554432 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..e60844722b8bfe66b75aaa1df0ccc0e5557d57a3 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247071c45b05e756c99cd63235cb42670e5cc960738bf26d90f908d315ad3044 +size 117440512 diff --git a/params_shard_235.bin b/params_shard_235.bin new file mode 100644 index 0000000000000000000000000000000000000000..459c23bfe2dfd510b9b0d589a27387e31169dafe --- /dev/null +++ b/params_shard_235.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc049d8d7457764f009b88e26fd4b893b2026fa3ce25753cc45b1fd0b704f47 +size 234881024 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..6e72088bad42730775e82bc39a1fb4e09879f516 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07e247b95ae0911e447f0e485c29c43ff051e9c6f185bd5e6ceb84af002ed86a +size 31522816 diff --git a/params_shard_237.bin b/params_shard_237.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec99e49d4a08aab9c8ba7b8c923d033b8d3e7a3b --- /dev/null +++ b/params_shard_237.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9260228ab159b25ff5686846f1ef61cecd761446baa1a704f30e6a0eef9e2b +size 41943040 diff --git a/params_shard_238.bin b/params_shard_238.bin new file mode 100644 index 0000000000000000000000000000000000000000..d99eeabd8a8e7fcbe01614c7f38f89fa1006cef1 --- /dev/null +++ b/params_shard_238.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb5c9b57425f591428e8e50d3257bf8759c76d6f1ef9a95150edc0b92f3f7df +size 33554432 diff --git a/params_shard_239.bin b/params_shard_239.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7edbb07572cabc5b3f4ab3ef4b6f4f741a51d7e --- /dev/null +++ b/params_shard_239.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadd94ec162779bf0fc27ddcf62faaf4f8363a96239a1883534e1e0dac899d57 +size 117440512 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f74b45ad52673af953d413d1bc0efcfb78bba4f --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63a3e196a19e0276a64a2a18cc2c2e7e5e6dfd4ad1d2b0f4b3f25ebcd62859eb +size 234881024 diff --git a/params_shard_240.bin b/params_shard_240.bin new file mode 100644 index 0000000000000000000000000000000000000000..a06abe51e2744a2518073d8d19c970aea53b8d9f --- /dev/null +++ b/params_shard_240.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0105d6aba9729edee9d9abee4025d3867ca04181c9a2e411bbc5abef1d5b5321 +size 234881024 diff --git a/params_shard_241.bin b/params_shard_241.bin new file mode 100644 index 0000000000000000000000000000000000000000..79201228e69839ab780643fcd23d8987e9128fc5 --- /dev/null +++ b/params_shard_241.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e9c3922cbcf7c8d66b01ef3044a5d3d1f2fd390edc05f341d693fca840df45 +size 41943040 diff --git a/params_shard_242.bin b/params_shard_242.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b7fa377a9268f11838c728aac3476fee964dc8d --- /dev/null +++ b/params_shard_242.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb1863049e4dc43e0cfcf0510a6ba46dad7fc294de4eff881db6e1a24a68495 +size 33554432 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1e3864f49bee2587f45e916e7396184e72e18b1 --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f525c8913042ab6bfbd638760dcfdc60ec060069c8d0f1a97788d9748b7fd22 +size 117440512 diff --git a/params_shard_244.bin b/params_shard_244.bin new file mode 100644 index 0000000000000000000000000000000000000000..4dcc7fc49379762d3204fc299d43ccef3207ed42 --- /dev/null +++ b/params_shard_244.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa5568cbc0d6181b24b51567413a4eac2152ec954b1f5ff02efd2306db56dc3 +size 234881024 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..66a00d07a9055aa14a861e13edc140a7a8f4e9fa --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079284baf7c93c318401f01d2ba384a3f36b97f8b03563f5fb16b0726f7e6798 +size 26820608 diff --git a/params_shard_246.bin b/params_shard_246.bin new file mode 100644 index 0000000000000000000000000000000000000000..c69fc1302b5c83909663f503e6e27e4c91b27dea --- /dev/null +++ b/params_shard_246.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e57efa9bb4ae1761eb12937cd178b05697806242f5df7f1de273b7e95491f2 +size 41943040 diff --git a/params_shard_247.bin b/params_shard_247.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e6f2c43e4a78da332d98d358f687546937caa40 --- /dev/null +++ b/params_shard_247.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014234808dc37082527a101f321d7e7b198e98754eabad103d9097958539b71b +size 33554432 diff --git a/params_shard_248.bin b/params_shard_248.bin new file mode 100644 index 0000000000000000000000000000000000000000..3650dd92b70522377227157aafb75fe2ff62e3f2 --- /dev/null +++ b/params_shard_248.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e798278486eb13d3acceb6e8c80ab7c04f4b29bb42865e3c2e0a4290d776368 +size 234881024 diff --git a/params_shard_249.bin b/params_shard_249.bin new file mode 100644 index 0000000000000000000000000000000000000000..5058df5cd24516f9e714054d1526595d5ac6d71b --- /dev/null +++ b/params_shard_249.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:291476349d03e3a4901ed448bfad959698c1d7314a24cb4ce7b676a28ccb92aa +size 41943040 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..9eb9ed93c7a8bda65dabe5ee1c90078300a70269 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae68a584855d6faeb112d52a3d314a49a688900716c5afe77270ce2a9572018 +size 41943040 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..780f8f65ce0356edf0cc351d65f54d8bdb6e04de --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3baf175660a58880a53ee9d601d1e497aded842ea29c1d34f04d65a9fe5abb2a +size 33554432 diff --git a/params_shard_251.bin b/params_shard_251.bin new file mode 100644 index 0000000000000000000000000000000000000000..a37343ca448ce9b2a248b9a527b3af152bb33564 --- /dev/null +++ b/params_shard_251.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84830a813b1780469cfff9eb17b95386482bc4cd4b45c56f25fe1165c454b4bf +size 117440512 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5ee67358e35181c232ca18853e08c7290255a48 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47a41a960c61352012ee1ad88651a86b0c2aa04bd1528c8fd57cbc2cb0397d5 +size 117440512 diff --git a/params_shard_253.bin b/params_shard_253.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ae2ddb0bce38396a2140b95b38c070b98519c4e --- /dev/null +++ b/params_shard_253.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbc9afbd953d628b2f0789b1186e5da0d45b2737a7247bc02fb21e9fa674443 +size 234881024 diff --git a/params_shard_254.bin b/params_shard_254.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c99d8f7e78181bbb7f50355aa97a283dae3fe37 --- /dev/null +++ b/params_shard_254.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef5f545c995d19a3ab1869057322d7514ff891a7f4d9977bf661e6c468c4f67 +size 26804224 diff --git a/params_shard_255.bin b/params_shard_255.bin new file mode 100644 index 0000000000000000000000000000000000000000..19f95f21718575e250092905c47e42d59926b211 --- /dev/null +++ b/params_shard_255.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ad00b359ea97de6bb050ad37335df43b98ce404df0a498c6dc3efc882dd39e +size 41943040 diff --git a/params_shard_256.bin b/params_shard_256.bin new file mode 100644 index 0000000000000000000000000000000000000000..d81558d1197d9dfbf1f27846c760421807444d4d --- /dev/null +++ b/params_shard_256.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3cbece64fe39bd2b558316227dab90480cfcbed4dfa15ba1613eb4ce965c48f +size 33554432 diff --git a/params_shard_257.bin b/params_shard_257.bin new file mode 100644 index 0000000000000000000000000000000000000000..398eca3d955de2cdc917ff68abb9139aa8502725 --- /dev/null +++ b/params_shard_257.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5663389c6e265e25157bb8bdae69256fc9b0d46857eb683f12ec00c64e23090 +size 117440512 diff --git a/params_shard_258.bin b/params_shard_258.bin new file mode 100644 index 0000000000000000000000000000000000000000..73c28e786802a89fdf77e0e52217ff17f3c7a8a0 --- /dev/null +++ b/params_shard_258.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dff1498198aafaa8a2f4e6ef8c43ce5099899a9dedd96baa11eb4bc131db8636 +size 234881024 diff --git a/params_shard_259.bin b/params_shard_259.bin new file mode 100644 index 0000000000000000000000000000000000000000..b68750a083ff2fc1ee7631de8557f4f57a368e54 --- /dev/null +++ b/params_shard_259.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af32407f7d1f114abc27b5cc355d0cf7ed8a21b21ce4593a4f85961f8b79062c +size 41943040 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..1de99df06521367a596df184f65e1beb1d40c086 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd43b9012e19b89ceba8c18d0467d58e398e2745d2b7cc026da58d5f8364666 +size 33554432 diff --git a/params_shard_260.bin b/params_shard_260.bin new file mode 100644 index 0000000000000000000000000000000000000000..796662a9af373772cb2092304cbae7942aeb8e32 --- /dev/null +++ b/params_shard_260.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f18973a42ffea3b8646c3ffa634478cf79b2226b98835c08b9953b3231da9b +size 33554432 diff --git a/params_shard_261.bin b/params_shard_261.bin new file mode 100644 index 0000000000000000000000000000000000000000..4628b3d83ab5c94a4fcb4dc4cd40c55073cdf75b --- /dev/null +++ b/params_shard_261.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57102079c286c45df51cb104f1008e6ae080375fe18297185099610a50aef66e +size 41943040 diff --git a/params_shard_262.bin b/params_shard_262.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb661072f9150436c36928dd3bbbf015a7fe566a --- /dev/null +++ b/params_shard_262.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7502c2be9a100503bb074fd9b400b816783128bca7b23a79a3b413a4acb15baa +size 33554432 diff --git a/params_shard_263.bin b/params_shard_263.bin new file mode 100644 index 0000000000000000000000000000000000000000..d3888fdd369a73a33baec8ce19fffaafa68c6dd5 --- /dev/null +++ b/params_shard_263.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7bec061c19465153b2c4124631694ba4a36fbadf6e8dd1743893df94874592 +size 117440512 diff --git a/params_shard_264.bin b/params_shard_264.bin new file mode 100644 index 0000000000000000000000000000000000000000..3653fd0f667841f93ee19a9c27723a24be02056f --- /dev/null +++ b/params_shard_264.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cda19f46e70381447df7d7e2aa49e042bee59eb0bf4cf0696600c768447bd8 +size 234881024 diff --git a/params_shard_265.bin b/params_shard_265.bin new file mode 100644 index 0000000000000000000000000000000000000000..3de6cae17b7ef50b3624e001199c45f15951e27e --- /dev/null +++ b/params_shard_265.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a60150875ad6f6016de83dcb8a8395e47704908bc0e08b25b3591b5b7571255 +size 29163520 diff --git a/params_shard_266.bin b/params_shard_266.bin new file mode 100644 index 0000000000000000000000000000000000000000..b74e586cca1248ed4ae088e7684e18884b08b67b --- /dev/null +++ b/params_shard_266.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2044a67faf19641099a59e60264ea4a5cdfdf3f2348264bd9559842b7cb3203b +size 117440512 diff --git a/params_shard_267.bin b/params_shard_267.bin new file mode 100644 index 0000000000000000000000000000000000000000..34861a83aa33dd26fdb80afacafaeeb62b2205ef --- /dev/null +++ b/params_shard_267.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e785794520e9bc4db8fb4f56b7287766c1b3ae95f956175d45a2536d3a9fa9 +size 234881024 diff --git a/params_shard_268.bin b/params_shard_268.bin new file mode 100644 index 0000000000000000000000000000000000000000..686569b1d97d9260eb080c73833caafa5d1dd495 --- /dev/null +++ b/params_shard_268.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8e6d9c5a40febe7a31eaa20f214a1c6f85f5bcbde6af4a1369740b9bcdc4b6 +size 41943040 diff --git a/params_shard_269.bin b/params_shard_269.bin new file mode 100644 index 0000000000000000000000000000000000000000..bdb74c75af057a0d0d0049d3fdc3ad6fbaa65e09 --- /dev/null +++ b/params_shard_269.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbd119841897140ba69c108c55547ab7c05b925c045dcbdacf6dbe79d65d664 +size 33554432 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d623942649296e0d65398d5affdfbc6fec6ae4f --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6477ccf2f6b9ea4fb4fd91cff005bcdc52940feeb2b2012497f8332a3768cf5c +size 41943040 diff --git a/params_shard_270.bin b/params_shard_270.bin new file mode 100644 index 0000000000000000000000000000000000000000..3f8620430c763d468d0dfd3b4c91f555143dea21 --- /dev/null +++ b/params_shard_270.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250ff65d20843df1c417ce870f451a2b73b5a0c7e119ef74bfa9e45ef5990d3a +size 117440512 diff --git a/params_shard_271.bin b/params_shard_271.bin new file mode 100644 index 0000000000000000000000000000000000000000..b287afafb4cbaf64015a76aa5a6f3f6fa005c734 --- /dev/null +++ b/params_shard_271.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49922890827b31832309fc8418eaccb72b1950520aa39b5be8087e6ff2b6315c +size 234881024 diff --git a/params_shard_272.bin b/params_shard_272.bin new file mode 100644 index 0000000000000000000000000000000000000000..701fd0fe709329f22e5d432ee26f860bc4f117e7 --- /dev/null +++ b/params_shard_272.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7728d391c5570821ec3297db5dadab1e5410cbe6dccce7aa9bf5d6b32d8c3211 +size 41943040 diff --git a/params_shard_273.bin b/params_shard_273.bin new file mode 100644 index 0000000000000000000000000000000000000000..143e646acbc8cbd640a803534807e8ce114cf125 --- /dev/null +++ b/params_shard_273.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa12e8a23c5b89afc2bae1d91d48fa996552cb5ec0d6e77aec776f08e9735b68 +size 33554432 diff --git a/params_shard_274.bin b/params_shard_274.bin new file mode 100644 index 0000000000000000000000000000000000000000..4e908bc7b32f8080323510302fe4a75bf0608321 --- /dev/null +++ b/params_shard_274.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2a39d171d51d46693518a178a8baef2920c1a5261487d6c4f519e095dd92a9d +size 33112064 diff --git a/params_shard_275.bin b/params_shard_275.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ceb4cc7c1e253bb21a3a50d01705c47ccc7fffe --- /dev/null +++ b/params_shard_275.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba24bb49a8b20f93d8b7b3047c66ba785c12fba7f11defb8de1fb5ad356484d8 +size 41943040 diff --git a/params_shard_276.bin b/params_shard_276.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d3cf204698d9926ca326b876421a197924f6303 --- /dev/null +++ b/params_shard_276.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e222d9cf2fc8f1224ff08c64c1a217bc2387dc46352bf90251f5b4a97d8eb68 +size 117440512 diff --git a/params_shard_277.bin b/params_shard_277.bin new file mode 100644 index 0000000000000000000000000000000000000000..7ca9c88a593b32b6439dde73103815a8063bd20c --- /dev/null +++ b/params_shard_277.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b944cf63ad47a54570f1aca5063498fde9f396c8b243f9d923222e878468b52 +size 234881024 diff --git a/params_shard_278.bin b/params_shard_278.bin new file mode 100644 index 0000000000000000000000000000000000000000..d914e6a21e107eaffecc4b98e10f14bcf0b94d51 --- /dev/null +++ b/params_shard_278.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce605d7bf4446625d1ec04db0df4d1898544299f85a9c7a16cab6d1d500e93a +size 33554432 diff --git a/params_shard_279.bin b/params_shard_279.bin new file mode 100644 index 0000000000000000000000000000000000000000..55c1ad8516238b88b40fc8a4f5842f25a568b121 --- /dev/null +++ b/params_shard_279.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b4b24ab3fdc93707beb2df7643f56419a7eda4830ae5b7a87fbc921fd96aea +size 117440512 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..915f64296a4938a1c7a6aa1dca00c3c0ac667728 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3220ecaeacdc227d495beb51fb525e33e37af21e70114146300d7df3bc17f04c +size 33554432 diff --git a/params_shard_280.bin b/params_shard_280.bin new file mode 100644 index 0000000000000000000000000000000000000000..0764b134b3557c4b2beb54bc07de68633d6cd075 --- /dev/null +++ b/params_shard_280.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753c2ef3e5970430601db49cc351eb0072f6252b212c8a25f0f77e88d96e5b02 +size 234881024 diff --git a/params_shard_281.bin b/params_shard_281.bin new file mode 100644 index 0000000000000000000000000000000000000000..e6b0fe50403deaf87b717c181087cece0f0b0a19 --- /dev/null +++ b/params_shard_281.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d386e96c85e5800e8b592969b771ba068b5ca5cc8093239367e00fead08d46a3 +size 41943040 diff --git a/params_shard_282.bin b/params_shard_282.bin new file mode 100644 index 0000000000000000000000000000000000000000..48deaebaf3579b803179e5af32bb2539936cb60d --- /dev/null +++ b/params_shard_282.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c666494c0c6c943e02071f53b40d32c671016c276247177f71e39b351ba24c1 +size 33554432 diff --git a/params_shard_283.bin b/params_shard_283.bin new file mode 100644 index 0000000000000000000000000000000000000000..c95bf55a6c640dd46ca14073c633a3882febabbc --- /dev/null +++ b/params_shard_283.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b748b79e89d4d144306d31b88d690d006cbfb46b8a0a1bf4899119b32740f627 +size 117440512 diff --git a/params_shard_284.bin b/params_shard_284.bin new file mode 100644 index 0000000000000000000000000000000000000000..790f3ed7232b675023bc8ad3eb949a08962a5e53 --- /dev/null +++ b/params_shard_284.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9923e6162eb04b4334bdbf7f1a72ca24377f6d2d754be6fa59cbb42dbe98f26f +size 234881024 diff --git a/params_shard_285.bin b/params_shard_285.bin new file mode 100644 index 0000000000000000000000000000000000000000..84d60233cacc273ff60b08c7b804ea4fc95772de --- /dev/null +++ b/params_shard_285.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c49e9447221e364bf5dcd88b73abca94b07fdf86a419815fc942e183593e440 +size 31522816 diff --git a/params_shard_286.bin b/params_shard_286.bin new file mode 100644 index 0000000000000000000000000000000000000000..b97a984401cbdc60aeb2594be92637e11fb47dfe --- /dev/null +++ b/params_shard_286.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175b331abee721db9ca5c0b9654e1cc5c7d6d5d94aaa94d7875b5eb83c9923e1 +size 41943040 diff --git a/params_shard_287.bin b/params_shard_287.bin new file mode 100644 index 0000000000000000000000000000000000000000..815828432218e017cfce4afd4e3476c204917167 --- /dev/null +++ b/params_shard_287.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f79073d5e8b735166402edf1f5ca895db067fe4941b54a72245751459f623d0 +size 33554432 diff --git a/params_shard_288.bin b/params_shard_288.bin new file mode 100644 index 0000000000000000000000000000000000000000..85b8f44aa49fa64f786c10f2c78869cc032010e7 --- /dev/null +++ b/params_shard_288.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce925aa3d974690cf41b07f40e55b0066153fe46e2876987b6334381998a0372 +size 117440512 diff --git a/params_shard_289.bin b/params_shard_289.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ced355bc5ad20625365cbfd55ace664c4cfa95d --- /dev/null +++ b/params_shard_289.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a160485abb24217bc4dbd51671d91aa870f678c21d1c5f1a1bec2ec2bed3ab3 +size 234881024 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..24aefe311340386ee4908c4d5ebb7eef0181734b --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34faf1cc92d0cd2ffe81bf46d509832f073b218dbee023f9fb6cfbdd87deb111 +size 117440512 diff --git a/params_shard_290.bin b/params_shard_290.bin new file mode 100644 index 0000000000000000000000000000000000000000..00caede454fcf87bba80c2de3276bfe4531ce8f3 --- /dev/null +++ b/params_shard_290.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f63a3405c1739afde845a1d28818ae8096a73ad7dab3c76859846a545fdd5c +size 41943040 diff --git a/params_shard_291.bin b/params_shard_291.bin new file mode 100644 index 0000000000000000000000000000000000000000..3bd39a5d319d88c99f7db32dd04b1d9504ad522f --- /dev/null +++ b/params_shard_291.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df88e319bd49c1457e1364560ed7b9d08476bbbfd23b15324c230cb76053aead +size 33554432 diff --git a/params_shard_292.bin b/params_shard_292.bin new file mode 100644 index 0000000000000000000000000000000000000000..322c139afe9d7ca65618e38de0d033dfb264cae3 --- /dev/null +++ b/params_shard_292.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:595b9b4dc1bb2fff9568e18721fbc1d9407aba7eb0242fa007bb45d903e875be +size 117440512 diff --git a/params_shard_293.bin b/params_shard_293.bin new file mode 100644 index 0000000000000000000000000000000000000000..4ae9c303a937b87647f7924e170572b21a291472 --- /dev/null +++ b/params_shard_293.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d605760f1d164c2fbe20be6c59ff7dec5427d996a2cd322b17456644a1703b +size 234881024 diff --git a/params_shard_294.bin b/params_shard_294.bin new file mode 100644 index 0000000000000000000000000000000000000000..363630fbe7ab9d15a86c0d1f6c053cda46570ecd --- /dev/null +++ b/params_shard_294.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d5788e3c87843e35eb9d7d0215db405ac77747a24372f0e7d13d9987b2db8d9 +size 26820608 diff --git a/params_shard_295.bin b/params_shard_295.bin new file mode 100644 index 0000000000000000000000000000000000000000..38751ec2e97d62de95c504d5035ec54bdbf858ee --- /dev/null +++ b/params_shard_295.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2694fe2d030db270f0c8cea6625925b96184d3e28a4b2edb3d7af2d2b0369ba4 +size 41943040 diff --git a/params_shard_296.bin b/params_shard_296.bin new file mode 100644 index 0000000000000000000000000000000000000000..af42b38cdc2c5803c80e5e7ab73cd46982f7c32a --- /dev/null +++ b/params_shard_296.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:135315423a1f7342e1bba6d15bb1b32f4ed8576ef133cc6fd0da6c1bc18df58e +size 33554432 diff --git a/params_shard_297.bin b/params_shard_297.bin new file mode 100644 index 0000000000000000000000000000000000000000..80fe6b8d0d92e55a9b3edef6517f868a615dff59 --- /dev/null +++ b/params_shard_297.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296b79e6c1ccbe20d48490b2a3c767e02e397466d5eac3a4c21a7530f92561da +size 234881024 diff --git a/params_shard_298.bin b/params_shard_298.bin new file mode 100644 index 0000000000000000000000000000000000000000..67328d8429c29d02ffa21d503d3fd0aacc35bfbe --- /dev/null +++ b/params_shard_298.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8439d3ab16fae571c897e38cfaea737e24aaf7fe5ff3c17c8e7bd2270420b336 +size 41943040 diff --git a/params_shard_299.bin b/params_shard_299.bin new file mode 100644 index 0000000000000000000000000000000000000000..127e528abb87082f97845f112c2113d6e479c52e --- /dev/null +++ b/params_shard_299.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fe81e954ed626a9c4116705aef5888cecbbd8be7d56ffdd2eeb27e1adb91fa6 +size 33554432 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..06e1930617e885a25de585afa64bb28981c2fe52 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091b08ac533ddb9a79b566e78f36416a02e099462deb4ffa271df9248824b90b +size 117440512 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..772494a3d1a5c0939b5db20c24f551bb8e76b89f --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7146348dc1e4f6d5a78d2807d15f7da6e2649da6062122693680cc95380d38 +size 234881024 diff --git a/params_shard_300.bin b/params_shard_300.bin new file mode 100644 index 0000000000000000000000000000000000000000..2a699165e512fbaaa8fb325e8ae9d37b2847f7fb --- /dev/null +++ b/params_shard_300.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc6a60eb3aa44c687366e15a43ffe1d1dc2a0ce235168595b0652f6c8c1e6f6 +size 117440512 diff --git a/params_shard_301.bin b/params_shard_301.bin new file mode 100644 index 0000000000000000000000000000000000000000..9adcf152dab88e3884be9cc3438b6f16a883891d --- /dev/null +++ b/params_shard_301.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae92c82faa40b93120e0e4669e205e9a038b4c8f82ef696c13ed35e9e6cc0b3b +size 117440512 diff --git a/params_shard_302.bin b/params_shard_302.bin new file mode 100644 index 0000000000000000000000000000000000000000..cdcedfbaf8e5b29d2caad4aa4279b97ede9d1add --- /dev/null +++ b/params_shard_302.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e5973622d911d2ccbb018c1a1b929f88496cad3524ad833c869bab9d65ae91 +size 234881024 diff --git a/params_shard_303.bin b/params_shard_303.bin new file mode 100644 index 0000000000000000000000000000000000000000..6ce76515d8c6e9b375716ca06fdfc955cc301861 --- /dev/null +++ b/params_shard_303.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d395601ad997113cacadb36d450ccfeee55b2dc34789adb61f5cbfb3d96295df +size 26804224 diff --git a/params_shard_304.bin b/params_shard_304.bin new file mode 100644 index 0000000000000000000000000000000000000000..0a884b7a6d70c7ab4d49ff4a2d6beb374be280d7 --- /dev/null +++ b/params_shard_304.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ab0acb18427b649186df3eb62e1efce1313c9f8b2f77710b33677af3e256da +size 41943040 diff --git a/params_shard_305.bin b/params_shard_305.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb18a2c35dd339fcd4a3c4c0f92c578ee5908f8a --- /dev/null +++ b/params_shard_305.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a507770b2ba2d6964bf2b3d6140f966ab046a32d2db8c7cb7e153e767137cbc +size 33554432 diff --git a/params_shard_306.bin b/params_shard_306.bin new file mode 100644 index 0000000000000000000000000000000000000000..b0ba09a70af90eadd0c4ade246f5d13bcd318067 --- /dev/null +++ b/params_shard_306.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd5feaca8765a336f4461d59a35a07431cf676fd5fd64387344d35df9bc08e6 +size 117440512 diff --git a/params_shard_307.bin b/params_shard_307.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0f4f4b403a5bf368b634e7bcc4457ed86616a68 --- /dev/null +++ b/params_shard_307.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bee446ebc7385ed20be8f49cd8aa58671e574d28655c1fa523311c99f58002f +size 234881024 diff --git a/params_shard_308.bin b/params_shard_308.bin new file mode 100644 index 0000000000000000000000000000000000000000..7fc5a76ed99fe3955f10ee63643223f1cd9abfc9 --- /dev/null +++ b/params_shard_308.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c0bc8e16b88b8b9bf80f133d87d1d00d5f1a069a4ebbacc578ec545f87603c +size 41943040 diff --git a/params_shard_309.bin b/params_shard_309.bin new file mode 100644 index 0000000000000000000000000000000000000000..a5ada39bc1e54285d2bd6f659754ba3363cbfe19 --- /dev/null +++ b/params_shard_309.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38e31501c829f1494a730dfb581fc9daa0ac8adef47fb6282086728329cc8f3 +size 33554432 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..b2c0f03a4dd39f02c09fcef7edf532842be23ae4 --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb89d7f55d1b09ca59176a78cc4fae06b25beb510b6b640870d19f1f03375fcf +size 29163520 diff --git a/params_shard_310.bin b/params_shard_310.bin new file mode 100644 index 0000000000000000000000000000000000000000..d59ff08c9915ade2a0269b4dca909305e35545c7 --- /dev/null +++ b/params_shard_310.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4b4a6341a845a0b225a5e7a40f98bd39f3ec339d85de57aa12064572906303 +size 41943040 diff --git a/params_shard_311.bin b/params_shard_311.bin new file mode 100644 index 0000000000000000000000000000000000000000..c4fdba7b9ff37c6f7ae4392fc61d916639914660 --- /dev/null +++ b/params_shard_311.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d118737f8a8664c5a52d9370adb6ff7a70fdc77e56029eb6a431ff8f9880d56 +size 33554432 diff --git a/params_shard_312.bin b/params_shard_312.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7c4d7b61ae4c1785cabcedb973ae866cd0bc2c5 --- /dev/null +++ b/params_shard_312.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f753fac3f8a3dac1af5316753d3ddf19edc133f2b719793ec79a7984a8d47e62 +size 117440512 diff --git a/params_shard_313.bin b/params_shard_313.bin new file mode 100644 index 0000000000000000000000000000000000000000..07f6145ae3acd81ac8e8c0e23c81e384d3b2f06d --- /dev/null +++ b/params_shard_313.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb75367f1a7e6d82d7205186bda5716933d04823700d534d822f41d69a8b3da4 +size 234881024 diff --git a/params_shard_314.bin b/params_shard_314.bin new file mode 100644 index 0000000000000000000000000000000000000000..6587f3b3f4f8e7b6dc73766fa510fd2469cceefb --- /dev/null +++ b/params_shard_314.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29863a3ea70916151ae3c789adee6adf07365d401037fed3008f4cae0c98696b +size 29163520 diff --git a/params_shard_315.bin b/params_shard_315.bin new file mode 100644 index 0000000000000000000000000000000000000000..cc285371af903e870d5b1c062483df2602dd5eb8 --- /dev/null +++ b/params_shard_315.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7563c0784bc27a5a67ebbe69f0228c92cc4335b3f063a64b176a691523c0e335 +size 33554432 diff --git a/params_shard_316.bin b/params_shard_316.bin new file mode 100644 index 0000000000000000000000000000000000000000..d5a633a565e3b6cb7bd12ae72241a2121e3628de --- /dev/null +++ b/params_shard_316.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0cf8d6339eb018039406ac24f2c1ea28c8c18623ea6c7dbc65646f3953df0a +size 117440512 diff --git a/params_shard_317.bin b/params_shard_317.bin new file mode 100644 index 0000000000000000000000000000000000000000..724ecf04a68e028ece5ef533ee30aeabadee5cfa --- /dev/null +++ b/params_shard_317.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f980eaeb7f3118edd1f696147d0d185352dde2d9b0235a93b47bfe2f98567112 +size 234881024 diff --git a/params_shard_318.bin b/params_shard_318.bin new file mode 100644 index 0000000000000000000000000000000000000000..fa36b9d6ff932aaa5119c1d8269ab7111572613e --- /dev/null +++ b/params_shard_318.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a502cb51ab32d2b666896410ff8adde327d7f7b378629cd44853633a1f82d8f +size 41943040 diff --git a/params_shard_319.bin b/params_shard_319.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d1d0bd04e5b617458c39eb89f7be27a502d0d6d --- /dev/null +++ b/params_shard_319.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d8c10f84aecfcfc6f8719b63a5f83faad5b6b92b165cce00787c36ae100e50 +size 33554432 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..e1f29f44793c5212185984cc5f283d3de68d1005 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41352ddd15ab65c196df32cbe0dd48e4b6a18b90b4b1838e80f087947e303486 +size 41943040 diff --git a/params_shard_320.bin b/params_shard_320.bin new file mode 100644 index 0000000000000000000000000000000000000000..e2d17f153e66bbcf31433b3146275c0884936a5f --- /dev/null +++ b/params_shard_320.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef664369719a969a28c6a84a8c4a37f53f919ec09ae52fd11d83c9456ed1e6e3 +size 117440512 diff --git a/params_shard_321.bin b/params_shard_321.bin new file mode 100644 index 0000000000000000000000000000000000000000..e5b6b5ffe7716ffb0fa7eabd8d79832c020906b7 --- /dev/null +++ b/params_shard_321.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d880eabc5b0af5c4e2b3e478d397faab9de31465174be6991e90432873d8b80e +size 41943040 diff --git a/params_shard_322.bin b/params_shard_322.bin new file mode 100644 index 0000000000000000000000000000000000000000..83b6377ac55907d006e4dbcaa549f74dc093e9f7 --- /dev/null +++ b/params_shard_322.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d68a275dfeb3162c4c223d7408189069637039bb9d86c56e72c104218b081a5 +size 33554432 diff --git a/params_shard_323.bin b/params_shard_323.bin new file mode 100644 index 0000000000000000000000000000000000000000..91f17bb5fc68749effa4a26494bdd524b8211015 --- /dev/null +++ b/params_shard_323.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8add234ab6c2996f3583c1806642b50e604e8eea6fd3a641e34190472b8b2a17 +size 117440512 diff --git a/params_shard_324.bin b/params_shard_324.bin new file mode 100644 index 0000000000000000000000000000000000000000..1d72b56dd9167077c6a75d7cb5f1deb3c81eae2a --- /dev/null +++ b/params_shard_324.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd6ad38e17c698c05e19f938ce0494273e0254deee10fe90d86ed8ff6303345 +size 234881024 diff --git a/params_shard_325.bin b/params_shard_325.bin new file mode 100644 index 0000000000000000000000000000000000000000..c9788ca5fcb99fb1026be83957edaa1cad29043f --- /dev/null +++ b/params_shard_325.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9155abddec3f84919ccf2d4502758e5102e9d9fdd3d79b1f91a9c545ab91f15 +size 31522816 diff --git a/params_shard_326.bin b/params_shard_326.bin new file mode 100644 index 0000000000000000000000000000000000000000..a475835b2fdf2df912776d7da771c20c55e16653 --- /dev/null +++ b/params_shard_326.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39951ed21ae2896acda9627f217d55d898e264863ad8fcd3489ba51189088012 +size 117440512 diff --git a/params_shard_327.bin b/params_shard_327.bin new file mode 100644 index 0000000000000000000000000000000000000000..36b40350a20e2b71c47763f9469b692194d6e3f6 --- /dev/null +++ b/params_shard_327.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb9856463290ef7e5aa62ad915b67b14ab4b20d2ed7eb9af4df44063035fcd8a +size 234881024 diff --git a/params_shard_328.bin b/params_shard_328.bin new file mode 100644 index 0000000000000000000000000000000000000000..45cc7d09acd19a070365e263909ae46de491b092 --- /dev/null +++ b/params_shard_328.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397d18475d98d1c72517ef3bcaf8db0271f90ac836204b22f512986aa739ceea +size 41943040 diff --git a/params_shard_329.bin b/params_shard_329.bin new file mode 100644 index 0000000000000000000000000000000000000000..05bf937ee9cddf614ba8f6fe0103e82a0607ba9d --- /dev/null +++ b/params_shard_329.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c412ec7225629185950530f3518a7a1e0d0e347fc54a78a803f1fec20b4c2979 +size 33554432 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..b1573cb3cbd80ba0e58e5366d34b6893c8100cd7 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b459c223eb9b3b1209fcbfeb37b450c9f04db2b119c0b1f5b16be7a086506cf +size 33554432 diff --git a/params_shard_330.bin b/params_shard_330.bin new file mode 100644 index 0000000000000000000000000000000000000000..18ab448dd3f503a689717a77cd717ffa3b4fdc9b --- /dev/null +++ b/params_shard_330.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae83996ca2e7c53c57cbcb0711824ebcdae8c5d943435237a15d6e7ab499c6a6 +size 117440512 diff --git a/params_shard_331.bin b/params_shard_331.bin new file mode 100644 index 0000000000000000000000000000000000000000..8eddfb8512fc933a378957300024b74e4163a6be --- /dev/null +++ b/params_shard_331.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f892a8ea778f610eb4c422b1f3118b64b42c1d9ad92b3e33b99d297abde7322 +size 234881024 diff --git a/params_shard_332.bin b/params_shard_332.bin new file mode 100644 index 0000000000000000000000000000000000000000..8fb89a73bc021dab8d9083b0a26db0da91f21aa3 --- /dev/null +++ b/params_shard_332.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:763996008b5c7acb663d9d1a06efa642a81520e564dafc22e9d3ec3e514a4678 +size 41943040 diff --git a/params_shard_333.bin b/params_shard_333.bin new file mode 100644 index 0000000000000000000000000000000000000000..42749ab211513dd1f1fc8f985533d3987bf34164 --- /dev/null +++ b/params_shard_333.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f3ec573c29567747348e1f2ac9e48bc49ec1fe68ee891997591a4d45be69118 +size 33554432 diff --git a/params_shard_334.bin b/params_shard_334.bin new file mode 100644 index 0000000000000000000000000000000000000000..881a14b3ee9e230d328f83e53efea3a17cb544c1 --- /dev/null +++ b/params_shard_334.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e8f75b9930756b03a637ea96cce0105807a4de445a28bdd19e6df82c590faf +size 33112064 diff --git a/params_shard_335.bin b/params_shard_335.bin new file mode 100644 index 0000000000000000000000000000000000000000..b67405b2960e75eaba2878cb17684c993da51b99 --- /dev/null +++ b/params_shard_335.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:518f134c806709b59647734b0e7d13db22c72fb79231d7eba8f74a2a517c9cbe +size 41943040 diff --git a/params_shard_336.bin b/params_shard_336.bin new file mode 100644 index 0000000000000000000000000000000000000000..db164adca0bcb9e6f15683f8b728006b079f98c6 --- /dev/null +++ b/params_shard_336.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d818084ab93b6ada7f9c780c467dd770970bd4d3c968a061076d3306c2a0ac70 +size 117440512 diff --git a/params_shard_337.bin b/params_shard_337.bin new file mode 100644 index 0000000000000000000000000000000000000000..9767ffac4151817820daf845e5bc0a7655ab1990 --- /dev/null +++ b/params_shard_337.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27aa3f6fb5428ae8ec8490acc7f8be1e4818d63602983fce5e5bc43336c05d0 +size 234881024 diff --git a/params_shard_338.bin b/params_shard_338.bin new file mode 100644 index 0000000000000000000000000000000000000000..91092db09094d554c0d856c7f8747ed1bfe1136d --- /dev/null +++ b/params_shard_338.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5eaf6604110678720254c687b3cfafe608087b40c422bd4c0ca166a50c93e1c +size 33554432 diff --git a/params_shard_339.bin b/params_shard_339.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf3faf80cbef6c8ddf5a28913ab91637d8d70b4a --- /dev/null +++ b/params_shard_339.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf129e041c62f57abf5b9e4cbf34664c9d5630ddffafe1314d86800072b7712e +size 117440512 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f356019a01685893eff8c5bf11b71eacef5d1d2 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a619fdcc9b943011c6ddc3fa8b1aefc668cecaf78df7d8606e86eb6128307bd6 +size 117440512 diff --git a/params_shard_340.bin b/params_shard_340.bin new file mode 100644 index 0000000000000000000000000000000000000000..f17d10126b0a5625254bd8cc62fd74a4e95a6022 --- /dev/null +++ b/params_shard_340.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8f000d7b1ee69d7d949a7d24483e5b1df1304a61411f1020059e70ad817f3a1 +size 234881024 diff --git a/params_shard_341.bin b/params_shard_341.bin new file mode 100644 index 0000000000000000000000000000000000000000..e32affde69043007479046556c4c04d21e02a1ae --- /dev/null +++ b/params_shard_341.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f0b7cadd08014a5fd2c026f69821bea2418622b17f3bfcaf2b3420e38165119 +size 41943040 diff --git a/params_shard_342.bin b/params_shard_342.bin new file mode 100644 index 0000000000000000000000000000000000000000..62a6f730339b256ffcf143e64c7fdb33644c885b --- /dev/null +++ b/params_shard_342.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67da6672ef88e85f82c119bd81a9d528403a289d4e9903cf19beb84eb9a0b91c +size 33554432 diff --git a/params_shard_343.bin b/params_shard_343.bin new file mode 100644 index 0000000000000000000000000000000000000000..af5599181e99d29aea3318bfe7f062e120ef7212 --- /dev/null +++ b/params_shard_343.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0aa8bfdb8e15f4afefaeb0e6fd88cce0e46445c59086fa56431c907ac9b78db +size 117440512 diff --git a/params_shard_344.bin b/params_shard_344.bin new file mode 100644 index 0000000000000000000000000000000000000000..face29daf65da1b90792202747e3e3da8bded46a --- /dev/null +++ b/params_shard_344.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b3efe220312179b7e6ad0fa1bd0cdbd639e44782cc6acb1372cc7033e81dae +size 234881024 diff --git a/params_shard_345.bin b/params_shard_345.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a3f111f88ee46d86b7271128fe49a6385ec3749 --- /dev/null +++ b/params_shard_345.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbf26b8cbf2bc7a78bf3198350f2f4aa0863222f0dd035ec8f10d95bdb162f91 +size 31522816 diff --git a/params_shard_346.bin b/params_shard_346.bin new file mode 100644 index 0000000000000000000000000000000000000000..21c1487049eb1b476490f608836d4592f31fcafb --- /dev/null +++ b/params_shard_346.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be3400f2b0e42b40961048cfa9799b5f0bb9f97214e4aa0edf7eca13d5bacad +size 41943040 diff --git a/params_shard_347.bin b/params_shard_347.bin new file mode 100644 index 0000000000000000000000000000000000000000..63e012083f0ff1d74cccde0a38e703894860e0dd --- /dev/null +++ b/params_shard_347.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0ea291d71724e47e431364cd0cbf0ebb06fc936fee82bcb8780535a4cb78c6 +size 33554432 diff --git a/params_shard_348.bin b/params_shard_348.bin new file mode 100644 index 0000000000000000000000000000000000000000..2b4c5e88f9b880e4122a4675e08f791f310d6897 --- /dev/null +++ b/params_shard_348.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ec37ebd495f24ca56bf9cb38448f46e6ea384220340c80ec923cc9f9e23a92 +size 117440512 diff --git a/params_shard_349.bin b/params_shard_349.bin new file mode 100644 index 0000000000000000000000000000000000000000..94cdbf1d01635dc6b90501b27682784f31fde25d --- /dev/null +++ b/params_shard_349.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e51e45df0f1f279ef15f88ab76be3c28b5c758b06939ff5938abbbb68280bcfd +size 234881024 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d9cb4f485e211580633c3403903e3ddf0f16838 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09608da0d4158775d39d181013e004475db7d63d94c388fe545211fd20ed5159 +size 234881024 diff --git a/params_shard_350.bin b/params_shard_350.bin new file mode 100644 index 0000000000000000000000000000000000000000..184e1301fd7d053c195392bd98568b8c3be4b6c8 --- /dev/null +++ b/params_shard_350.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9bc098435d3a51b0e5e2f3ff7edfbb5cefa8c19160d75e6824f2715344abd4a +size 41943040 diff --git a/params_shard_351.bin b/params_shard_351.bin new file mode 100644 index 0000000000000000000000000000000000000000..7f7b3578488e10a79f270e5369548518f8b8f3be --- /dev/null +++ b/params_shard_351.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870675594a318f20968f978f4cb913693b2a83d7ba79ad1317e6f975c28170ba +size 33554432 diff --git a/params_shard_352.bin b/params_shard_352.bin new file mode 100644 index 0000000000000000000000000000000000000000..fdb89d0eb12930b03b5ecaf5049734007d82493b --- /dev/null +++ b/params_shard_352.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c976138a444f4a19f48c154ddd310de16d36d7bc1471e02b7c7d9b297caeda85 +size 117440512 diff --git a/params_shard_353.bin b/params_shard_353.bin new file mode 100644 index 0000000000000000000000000000000000000000..b7bb80c5bf242eae972674b4fd5141abc692309d --- /dev/null +++ b/params_shard_353.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f020626cb1b95ce387fdc613e98073037ef2320cab6097dd7e290782931f1eb +size 234881024 diff --git a/params_shard_354.bin b/params_shard_354.bin new file mode 100644 index 0000000000000000000000000000000000000000..a35bc0294ab4252cce5f3d086746e902f6077590 --- /dev/null +++ b/params_shard_354.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a8e08ea815ddfd4d828e01ee67ab387d271307b112865338f5dd4dfcce7b20 +size 26820608 diff --git a/params_shard_355.bin b/params_shard_355.bin new file mode 100644 index 0000000000000000000000000000000000000000..ac4b261e9b734b5d85b8bbed4135712793b500a7 --- /dev/null +++ b/params_shard_355.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62572eef219d56bab4dd9145efb4394b58730dafc602cbf86c07587b9a1557d +size 41943040 diff --git a/params_shard_356.bin b/params_shard_356.bin new file mode 100644 index 0000000000000000000000000000000000000000..47a186cddf8ffb269b6b949c60224694354b211f --- /dev/null +++ b/params_shard_356.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f595f32539344eb2e7b3fd62dfd793c8e1e06bb6d678c23577277e165e8a6277 +size 33554432 diff --git a/params_shard_357.bin b/params_shard_357.bin new file mode 100644 index 0000000000000000000000000000000000000000..3cba432e6251a83bc06d4a7bc1bc5dde303be5db --- /dev/null +++ b/params_shard_357.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:437cfefc424a4288004bee1fef19201dff0e137608e7ad4a8450d2c9d91369d2 +size 41943040 diff --git a/params_shard_358.bin b/params_shard_358.bin new file mode 100644 index 0000000000000000000000000000000000000000..b5623300c7d7d61aa615a0dd95a82d41536bad4c --- /dev/null +++ b/params_shard_358.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a811e50c97f3064e4d3be581843499268b42a223cd835b540fa4b93ab3718a10 +size 33554432 diff --git a/params_shard_359.bin b/params_shard_359.bin new file mode 100644 index 0000000000000000000000000000000000000000..0090c204127563da9e389efb3aecda8cf7cfae2f --- /dev/null +++ b/params_shard_359.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0ec0619bbd202100d32577ddcda173c6f9aa44066aa563901f7440573351c5 +size 12075008 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fd7e3c44c0cac103015a4e70afe345467103416 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ff639aaeca909c44217a2d5e5460e7cf49e45c557abb824df002fe5261a7dc +size 41943040 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..f35a63b7a26616fdf09cd98b4c2a8f2ab3c04336 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b50b84c906106edb342eabaf03af098826940b13b569ad28841d38b797819b +size 33554432 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..0d8943d679f7de774e093bf3d9422d2e1c34de90 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77574a737aa3316817442cb081c79db62667fcecfc98d522bae69abb33e8dba +size 234881024 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..fd8136292c0072adf0bd72cb54ccd49799afd593 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f953cb1a819141f101b256206be69cfa669260cc186e50b55f9dea9c2264caf +size 41943040 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..b30cdfecfbb146bfdb2e18475c1d8f0590a23ee3 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1df5dd9ff8ee44de5cacd8edd26efe62c524ede293f400fc31f0a27f42017e +size 234881024 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..fdd0d7859e6f98dc5553d42d37f667ed67bc0cff --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d629646d2edd9299019e9a058280baa7adbf03766148369ddcfaacc8cc8ce5 +size 33554432 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..b03170c40cea83140b3b12997caf163c177cb8b4 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9021ad45dca14ef613fd408847909effada22551186ecdbf9c988e726f9dda95 +size 234881024 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..d00249875f68eb1050687fb3fc74cb1f9311a98a --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:347a375934f9025c9e658e96b4f896d657009de9cf569b2bc7a18c300454fd09 +size 32833536 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..70de9074687112947db932aa709e3ccd9757dd38 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a944d65f6795aadbd3be9d890fc82ed6bc68e315b016c7da17e6f573884141 +size 117440512 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..a14ff647845c5969177e37c0a1174ca86cc1e80f --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e619bb7f334be51abd7f70a3cccbe53dae0fb7db1850be4e5c08a24ad0a6708e +size 117440512 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ee7a67e8c86564cf541f8236c6bfd441826357a --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0592c8910333b3f4f2db115c8134751c77f63b2404aadddc27e63cd41c59c14 +size 234881024 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..97744a38cfc093883bd0fa6bbe7971f28b959f9f --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3497d430243096ffb75b2d5d9cfa3ec0f711765847b2f80042211e750bd7532 +size 41943040 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..dbcf9c90524c1be0bec778e04aa5a0ebdc74fe1e --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54a0b430ed5295be45d9ffd6e0191637ed4f01b2ed1c7f9650915538e2076c27 +size 33554432 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f430fe2ce68d1b01368d38c885a40e0acc21a29 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e48d1baa7b8f8488120d7e483c70136482fdb9d4cba41f943814f6e15733e7 +size 117440512 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..41b7a167026230fa025564abb7c6a79ab9cf45e0 --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dcffb20916b8d2c8cd1fd521b5c4927c5196d85886ec71b1066e4052f0c0986 +size 234881024 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..5c081b3544648b37347866d700be420eca26f344 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a30b49c8a7e2c9e5b14e78f89fbede32ba86cb9d0f22ba4cabe26f7dc7668f +size 31145984 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..eaa921868cb59d0b1d28e108421e5f08f29607c6 --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4f7ee33438bd9f55a6cadf4c7056b4d8bd87eb129aa6eb2bb134299c7080aa +size 28147712 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..256577922adedd616a258d72b054671ac46ef917 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7412e6cae8650e77c1a6b90a0541170a23a73266d0feb8366d66b273c62b1628 +size 41943040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..bb65c569838cb8fef15a0f32575dbc175d33ed94 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07862a61e1f6d2980d2a8acb2dc56ce4241cfc42f1ad1c3158bc7913234391d3 +size 33554432 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..18bf71fadfbeef05862b2e008df686c69c328c50 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9919956d4c4064fdb8b25456191da6e029c1f28f8f268ffbe61e726d95e203f +size 41943040 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d62a42c380c16fdbf387f291c5c77de6bbb1be8 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7bf4357edc92e638153be891919dace09ea55b5d899c75aa4143157af1e389e +size 33554432 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..2947b24d2435fcc7c8a08690bc9695e6407c6261 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aee34c2e069cad2f6625560167cfc92bed5938a79edd8bafb276a2e495e8f5f +size 117440512 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..900aa7ca3ffec0aff0b933c235bc2edb1d6cc767 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:734735ab3d05d2944a314bafdb93591943ad2acbf4db91d40ffe3fb115feea4e +size 234881024 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..6343f090e3beb36f653ca95daf80e704ab753d4a --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:473fa4159e40e439c2117bd92c573144618589b7a7939a5c3aa6e8dc574cad92 +size 117440512 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..3ae5cc512dfa9a60c2d0ef35489860d0a71cc49f --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c97ad587b8b7836940e39ee4a4e4ee868b5f2702ef96cce847deac0f8603aa +size 234881024 diff --git a/params_shard_59.bin b/params_shard_59.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5e76168142910c45f7b2383fb1224dab7b07d40 --- /dev/null +++ b/params_shard_59.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab365c1263cd85e453209de3ebebba58f379c54d69aa59fb313f7e0604d6540 +size 26804224 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..61fc951b988aa6c69f44b64749c83b452611307c --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc62a8853269fddcb20fc199d2c3d1c6ec988d20b52a020f4b1451daa817c3a4 +size 41943040 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..18f639a5134941b60ea91f681db3f34361e1c40c --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbeaf10d7c033c553dc67e3ddb03e23cbe55c65be1ff4bd9bf4ad6b60f4aedad +size 41943040 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..ed455db72923e22c63ba8cf655b289779abbf71f --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd7dffc8950bbf37b614a7251eb65c5693e8241030b2eea61d02a7b5a978abe +size 33554432 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..75c63fbd1db56e8dd86ea48e903116d9a56072d5 --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a6944ee21d984540c43ef8db4c697d64c178c791a31cd678b8938214113eda +size 117440512 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..89e71e120d3abb77a34db22797a2977f372b4830 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67932559bc70ee321f59cd32296347ba1632bf483d76ac8cd24ff432fe96c3c4 +size 234881024 diff --git a/params_shard_64.bin b/params_shard_64.bin new file mode 100644 index 0000000000000000000000000000000000000000..8f33cbf5dd293f7294fb329c325ee945bb86ff4f --- /dev/null +++ b/params_shard_64.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42d5abd3466990748fcfa6f43485b4f0db092524c88353ddc93a7dfd819ea7e +size 41943040 diff --git a/params_shard_65.bin b/params_shard_65.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2a5b2365c757a21adc1a7abf5d0ae660bc4e029 --- /dev/null +++ b/params_shard_65.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19c7cfa1ef6c51f1eb81cb3c3ca750a0c7ce06703fb09070c03062cf5f19718 +size 33554432 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c657fab90c7f15ccf4e05c76866e05eed8e3569 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc9337926546837526ad80f18667df84cd6c0fad9ea75139abe1435429bc95a +size 41943040 diff --git a/params_shard_67.bin b/params_shard_67.bin new file mode 100644 index 0000000000000000000000000000000000000000..4316c13aa4fa48c931746f56aaf9d4061e4cf900 --- /dev/null +++ b/params_shard_67.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b640ba7da4043b73b1cf1903169bf6cf09bc23b444441eac6063f75a86b99d7 +size 117440512 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..69c76f4611e9b14bd108c6a822e714f4643be332 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0611cd50b3e8dab338511c59b7bafe15f26d584131ba790eac43a91e8c575fe7 +size 234881024 diff --git a/params_shard_69.bin b/params_shard_69.bin new file mode 100644 index 0000000000000000000000000000000000000000..f46c729485294f6f3a6a0410c0d639b622ce89f7 --- /dev/null +++ b/params_shard_69.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f7e4b959504e01463ed1ae2f86895e80e77e9d7c607e7ce3a3909570dab89c1 +size 28114944 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..1da60c722ab46f95998b6389b16fa3243cc22603 --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d28b94ccf7e594a42cc7092a144faa836085d9e0371cce08f0b01faa202d43 +size 33554432 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..907f15b89b1d51205c48a2d9d6468a2c7eb8a570 --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570c19fee85dac5b500b9597fcf0e12a935d2606c8a6c819399e4a2d7c1d90d2 +size 33554432 diff --git a/params_shard_71.bin b/params_shard_71.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9b1a831edb154814ab7c2305dfac3b0c3870e1a --- /dev/null +++ b/params_shard_71.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1d11eca87eb5fdc1b25edca6891094e36b71de19d240f47319501bcff7170f +size 117440512 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..147ff684b78ad852f9f680a656f44603c1d7ac52 --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6e881be3959273bbfa0f3f5cb0ece6c1291147b9c3371768f8b715b777d5356 +size 234881024 diff --git a/params_shard_73.bin b/params_shard_73.bin new file mode 100644 index 0000000000000000000000000000000000000000..79ad4831cf12f89dced1b7664bb0f0aebc729cdd --- /dev/null +++ b/params_shard_73.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02392f3d05561ceb3b7b7d0dd3a6c4ee56b32bae9bccfea2b686cc0a5bfb4ae4 +size 41943040 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..773a09ce98e06c3ff2b5b74ac01982b6e6c483ce --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08178cb64893d320780083e4a9a0719257c45eef8eea16ba6fdc5dec742ec143 +size 33554432 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c5835023da2accb709810bd0f77ffaf9f8803fb --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e82294ac4d6d38f9fac62f4c799fcaf29babbee615cc3ec909fed96d55b07d9 +size 117440512 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..43779ea97018d25585fb323a1e99b083fa4077a2 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bcfd9883e809c58839e216f87d1ff16aa348c8a6c805cd1c76cac8ad2fefe5 +size 234881024 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..f84446cf29d2a17fe29ca7e87ab9b77c147b5219 --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9100a88f7080bdaf0b576719c1089e95f112bf5112316e841a6423d082a5c25 +size 41943040 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..304acefca667f5219159515c2eef144822a58f1d --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5886383d293d7cfe4ceb3044c7c6b1ded1c91234d29847b2ecf7b7dc03bcaac +size 32817152 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..50d1e78f2f58a329168f8ac95c1ef0627bba9999 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280905436d3096110fc63f4fcfa3dff25c59a5ec7189e0b37080574a303f9b3e +size 33554432 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..53fa5e9923cdd572fdc1e448340eff35fd1faf9b --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b5f95993582600de185b2b88b5bfa17b0e608c02e83881332010826e1ee52e +size 525336576 diff --git a/params_shard_80.bin b/params_shard_80.bin new file mode 100644 index 0000000000000000000000000000000000000000..93367b7e599cd099a8e79e8ccc2a00a94f67a4e9 --- /dev/null +++ b/params_shard_80.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e4e72cf8765e67afa7e8c8dc906791abfeb6947f715a3b97547d18efde478b +size 117440512 diff --git a/params_shard_81.bin b/params_shard_81.bin new file mode 100644 index 0000000000000000000000000000000000000000..f3b98cab194f5f83ce036177e44297e742434457 --- /dev/null +++ b/params_shard_81.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becd3d43e9fcd6ecb55b4c0d6208455f7ecdaed995f753be2b004ec0fd7e846b +size 234881024 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..7df00418e3cfaa6cf41e1b4f8559a2e21c010f8b --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:937b2a6644e97cf29c1bd03b7bda913c7f15ebaa3caf2c917440dadb355d6f44 +size 41943040 diff --git a/params_shard_83.bin b/params_shard_83.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7c61f1ddcab2885c1ada745207a5fb73c1d0c4b --- /dev/null +++ b/params_shard_83.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a4dbcf03094c0d2ee192de95cb0f0da11985660757875aff69a8b165027601 +size 33554432 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d3c8f2097f917d56af4abb10689567e8d1aa92e --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aeb77cbbf951c08c051947312d4886af64a328b804591855c1d52b6a1a41fc6 +size 117440512 diff --git a/params_shard_85.bin b/params_shard_85.bin new file mode 100644 index 0000000000000000000000000000000000000000..2ba42da46b756211d13e93d9bf84c9648fab0ed3 --- /dev/null +++ b/params_shard_85.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6212b0463f64789c6c6ad7f32ffe018990c591d9f4225f9d0063df56a52eb7cf +size 234881024 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..c42221a1f85e829095f2095951c2d8da923f3d06 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60df4891f26be9a14094bcfa63947e9dbe3b45e49559b7ddb9d7deb0e08a5e9 +size 41943040 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..9e91df38cdb5f62527b17dcd7016d8e88df514c3 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f7b236a7cdd4c4e769a43fcd764ab5e945eea94e1af3e4760c3ea2649c9897 +size 33554432 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..2cc117fc12f46cee43bb53a5e5fd1114097a8521 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c98876c11edc2cf6638215703e90239c6d654a141cda8243285acc21f74617e +size 234881024 diff --git a/params_shard_89.bin b/params_shard_89.bin new file mode 100644 index 0000000000000000000000000000000000000000..8cb8df814a8a1ca6280dd072b624f257a3a1de1b --- /dev/null +++ b/params_shard_89.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbba0ea250f496d79e8b62fdd9226cfda9406a8b9845d0ccfeaf0463225f0c93 +size 29196288 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..ea64c80ce93670df8d08398f2bde0d293b993c6c --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b61b755d2f2c9a063a52e734dd7b4d33dd880e05cf87da78473c5b826aa782 +size 117440512 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..5ccf89d74527894a641b14275623efdf7bbdaf22 --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:404a471281c6804060b370d9ada9c39f0f8e8db33eb78ef5d446fb75ed0b2e3e +size 41943040 diff --git a/params_shard_91.bin b/params_shard_91.bin new file mode 100644 index 0000000000000000000000000000000000000000..6b061836f6cdc18e2dd875843127dd7db5cc67bf --- /dev/null +++ b/params_shard_91.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa0bd1ee15a4cab66b7c1bfdfaab485c60331f29808482f909436ec644fbe45 +size 33554432 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..64e33bdcb621098e486a3da0ce3d66eb3ec436b6 --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47ade5fd981aeeab97d624ce4b9f2988162d2d602bee9ba9bee99d1637b02eeb +size 117440512 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c2a82b1e2309fcdaea9eaa6afeafa46290fe445 --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02cf6dd39163294ce96305b040d77f7c6633f70e2c91d16da3495e1270b4e6fe +size 117440512 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..79760cf9cef9760424f6ef3625b3861b86fd1183 --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9d2d79c022f71a27b505e21c81fc1e487afc630e406f755621fc1c199f032b +size 234881024 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..c19b7455c59c45814f4cc129fae42e2de21d7e25 --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f86b6cde4dad68cb96e62a2616dd033728ff9f9f9dcc539355b41fe92bbb1189 +size 41943040 diff --git a/params_shard_96.bin b/params_shard_96.bin new file mode 100644 index 0000000000000000000000000000000000000000..55ba0391e3728b17bc2d1ac373d705bef8038d6b --- /dev/null +++ b/params_shard_96.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af468f8a179cc713a85ada242acffdafba4e072ec8b41e2bebb7d911ac644d53 +size 33554432 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..0fb87f840aa8d3bff2d5d9f63d6e086f1f3e8796 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2085a5a41c595e773f702e846a261bb11c3ee8a04f582d1ab7070a01fad3e530 +size 117440512 diff --git a/params_shard_98.bin b/params_shard_98.bin new file mode 100644 index 0000000000000000000000000000000000000000..4f71a9702d7d61d7d0687634859a642bef07b6d6 --- /dev/null +++ b/params_shard_98.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e14fe054ef7a218bcfe8962d17b97a5e0330341d6b4ba61207df715858705140 +size 234881024 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..a82b89aaf32e8210d1467ff461d741a5aeddf185 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb1902482709f55c712a23a978dfb6fd2bc72e0c146328e9ab672029d2f1cc8 +size 30490624 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..51791b7f66078c8f06336667b45d97c52ee56376 --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,55 @@ +{ + "model_type": "llama", + "quantization": "w4a16g128sym", + "model_config": { + "hidden_size": 8192, + "intermediate_size": 28672, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "rms_norm_eps": 1e-05, + "vocab_size": 128256, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "context_window_size": 8192, + "prefill_chunk_size": 128, + "num_key_value_heads": 8, + "head_dim": 128, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "max_batch_size": 80 + }, + "vocab_size": 128256, + "context_window_size": 8192, + "sliding_window_size": -1, + "prefill_chunk_size": 128, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "mean_gen_len": 512, + "max_gen_len": 2048, + "shift_fill_factor": 0.3, + "temperature": 0.7, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.2, + "top_p": 0.95, + "conv_template": "deepseek-r1", + "pad_token_id": 0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "tokenizer_files": [ + "tokenizer.json", + "tokenizer_config.json" + ], + "version": "0.1.0" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..4f47952a1bdada713048f5e45fd3b52ad615fb34 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86 +size 17209530 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..11176da679c2fc9d85d25326f2a9a419b2cf189b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2067 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "128000": { + "content": "<|begin▁of▁sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end▁of▁sentence|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|User|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128012": { + "content": "<|Assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128013": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128014": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "128015": { + "content": "<|▁pad▁|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin▁of▁sentence|>", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|>'}}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|end▁of▁sentence|>", + "extra_special_tokens": {}, + "legacy": false, + "model_max_length": 16384, + "pad_token": "<|end▁of▁sentence|>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": null, + "use_default_system_prompt": false +}