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 29a16441c701e76b9926cc6a8d453342724f8963..e0e07e8b63c25a0f32ce4cdbada7073f07843e9b 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,18 @@ --- +language: + - en + - de + - fr + - it + - pt + - hi + - es + - th license: llama3.2 +base_model: FuseAI/FuseChat-Llama-3.2-3B-Instruct +base_model_relation: quantized +library_name: mlc-llm +pipeline_tag: text-generation --- + +4-bit [OmniQuant](https://arxiv.org/abs/2308.13137) quantized version of [FuseChat-Llama-3.2-3B-Instruct](https://huggingface.co/FuseAI/FuseChat-Llama-3.2-3B-Instruct) for inference with [Private LLM](http://privatellm.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..4a4653240eb1e47ebe25efae2c7cb61dd997183b --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,3521 @@ +{ + "metadata": { + "ParamSize": 283, + "ParamBytes": 1656834048.0, + "BitsPerParam": 4.069857841273854 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 197001216, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 197001216, + "byteOffset": 0 + } + ], + "md5sum": "bea7b3700665284b32c46cb59b820162" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d3d29e354396dabcf5fc284baded49db" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 32913408, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6156288, + "byteOffset": 0 + }, + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 6156288 + }, + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 6162432 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 18745344 + }, + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 19138560 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 19924992 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 19931136 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 27795456 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 28041216 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 32759808 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 32907264 + } + ], + "md5sum": "ff45501a865ba014c28b32ad75268ee5" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "6e3b66dee6a9345df2b29b410fc2c614" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "2c41244b3f01d92520438ba4211cc2b9" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "cb653b1a932d23a45421fdaad39ae1cb" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "f3369a54776b240bc4fad808c40d7f7f" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "abf0a2ca79930f02077cefc5cfcacf50" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "57dba5c22847c32f46d7ed55aaf95115" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "7b4f8bffe34f2473ba57750375a56e0a" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "5f8c53f4e2819df0554f99b5fb968c2b" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "676ea9c3a008f1730ecf1ccdea0a1350" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "7bb909e3de8973500ccae65cf0d2dc63" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "8d8557f6da03f0e080b37204bd757c5f" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "3a1ac46757a30a88beebf622a0c59116" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "b918e61bf49b820e4e175e291be839e4" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "79f9c6f01c4f8319211285775f6a5899" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "34c29e3dffc353e345e61bc70676d55f" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "1e71a816245ed8744e2a6e89d7bf1e95" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "35fe279bf2ee52f53a81b5008305c6e6" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "1007f8e89fcee1a6a45f2c746938fc5c" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "d63fdf1034ae64773374ddb2ad8bcc4c" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "7c79dc78f088dbc8fa43b980f1fda5e2" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "b0c11f8d44c556ba656fa228f6e38dc0" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "c2e4be67c44e700d994c8b23b64769b1" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "f65411b7642b0b18c500b41593e4eebb" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "3ab080c0ccc4ea7ccbbdc19faad1e521" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 27531264, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 26744832 + } + ], + "md5sum": "a1159440770d9b311cc175ac65a2a665" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "4c79578e94a1c351852efa723535a4f2" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "4b2c8ac996699ac73db771dff759e40b" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "2bb309b7125cf3bc2a2059f002f3bf42" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "ded7a94a90de73e68e39f6835fbe519b" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "bfe8195f6e187a6604628e31d5274a16" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "1231f6765917340d9ab57ea5f0525a67" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "a7be16e23bd7a7b97ad5d2b4e1ae20a3" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "c59c76cfdc4baeae9cc0d2c82b07a37c" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "43e28bfa99c71771c541adcf711a5273" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "f09950a64d23304442167e514657a753" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "66b72b3e22eccb891a51111776e4c0ae" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "9450dce6ec5df60784d70c5c7e510b8d" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "95ed9a4257dbe1905d24da3e71b9b333" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 25958400 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "89374bee4f353b2fba6714e033cba37f" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 25970688, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 0 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 7864320 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 8110080 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 12828672 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 12976128 + }, + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 12982272 + }, + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 25565184 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 25958400 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 25964544 + } + ], + "md5sum": "eed9ec82343fd1d07f54cef05be22a21" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "1e264253b93ae69b85189d1f467a1ce1" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "6b354aa667e2f4d0e772364884cc53f3" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "f2702337eb9b684de541c2e6c077706d" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "4419015cf4fcea010969597c9e73d946" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "0d0724288b43879730683490a291d5d0" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "b5a962d01ec4070a162e181d94e75309" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "b136d5fad594b1705841521ee621c691" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "7dda4c02b8f4837fc827cc9fc5b525e3" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "7cd9318f54e3b6ab4bd5cd756d71f5af" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "ee53781c62fa7ccf74d2d32b33c24a6f" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "92c82148336d420832def3583431dd51" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "d06a88538d56b2f9c32637d86eed386e" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 25165824, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 16384, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 25165824, + "byteOffset": 0 + } + ], + "md5sum": "1a503b912f1e7d8cc8700d01cfb31391" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 26750976, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 3072, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 12582912, + "byteOffset": 0 + }, + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 3072, + 64 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 393216, + "byteOffset": 12582912 + }, + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 16384, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 786432, + "byteOffset": 12976128 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 13762560 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 5120, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 7864320, + "byteOffset": 13768704 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 5120, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 245760, + "byteOffset": 21633024 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 3072, + 384 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 4718592, + "byteOffset": 21878784 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 3072, + 24 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 147456, + "byteOffset": 26597376 + }, + { + "name": "model.norm.weight", + "shape": [ + 3072 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 6144, + "byteOffset": 26744832 + } + ], + "md5sum": "012bdae88feb56af3ee300a6e04c58f6" + } + ] +} \ No newline at end of file diff --git a/params_shard_0.bin b/params_shard_0.bin new file mode 100644 index 0000000000000000000000000000000000000000..eb4d9152b046b6dbe961d988995656d837ffbda5 --- /dev/null +++ b/params_shard_0.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffacbac6872665a491316b3d5dee888145e285faccf5098707a02127c561eda6 +size 197001216 diff --git a/params_shard_1.bin b/params_shard_1.bin new file mode 100644 index 0000000000000000000000000000000000000000..a391e115211702a8b250c656a0eddd8c44349f56 --- /dev/null +++ b/params_shard_1.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3dbac42c28bc6e76d0d751c628c2288a4533327cc0945541252a0971b4ae2c5 +size 25165824 diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..d7113df0f63924758d0dc353b13f9d87c11b4268 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c92ed0d8952d5c93b6d49363dd70796608e76024db86017d7a3a5eb6f8953ea +size 26750976 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..18cfc70d764df453987c1b6fec3211ac63ed90f2 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65125a8edb0c7ed8719a64e9d2c9003cfb5dc359930d74a5cccecb8505b02382 +size 25165824 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..48d18c876bbd0ce96f5e34a982a5a2a7c648a28d --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1bb8efcb67a7d5b27d105bd2f4cd5c9f5e0fa922bbf60b467dcff9ea79324e +size 26750976 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..73b2df78d72381b32e35efff477e081e87506132 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fc4ca845c3f9439b2a6353743d8ccaa608ab2dbbcebc52087ee036d4fa5f5aa +size 25165824 diff --git a/params_shard_14.bin b/params_shard_14.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a042972fbdb1fcd94cd37a9eb602c652cba1c4f --- /dev/null +++ b/params_shard_14.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0341c1ce95f54a8a6e5149bdbb92617f7e00e9e18152c4a1436fe22541aed4 +size 26750976 diff --git a/params_shard_15.bin b/params_shard_15.bin new file mode 100644 index 0000000000000000000000000000000000000000..055e04bf6f10d71e83d4724f6a652270b418f2e6 --- /dev/null +++ b/params_shard_15.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba9afa26655d54c4aaec364af149fad2570149fbee8ca195f34978e969f5dc23 +size 25165824 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..978d3f2bfcff9567a4f15942da1e25735a9ade8d --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06eb972dc28116819294a40fdca2ce332811405d2f0d2feb8b15431d5e660df5 +size 26750976 diff --git a/params_shard_17.bin b/params_shard_17.bin new file mode 100644 index 0000000000000000000000000000000000000000..9393256c088ea0d8a5d476434c0e6673ddd738ff --- /dev/null +++ b/params_shard_17.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49259b54b32331a3a7af751a1e49390d9e92ecd9796e95e9b310ee51d7a51d0a +size 25165824 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..6955bb143ada4c8b6b6d6aec53a3039ca6f546a3 --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7eecb4d42fd8504736a32c9380415648091dd6c4c51e340b7809833794a4e6e +size 26750976 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..e694b3bb814e2787d2b5455b23a8018d9d1f8618 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbf5f8f902e6e0a5c374926df230a0dffcdc230d346b2183b07974de5255fe6 +size 25165824 diff --git a/params_shard_2.bin b/params_shard_2.bin new file mode 100644 index 0000000000000000000000000000000000000000..26a416c93070351f18825963e50d2b8bbdb573f5 --- /dev/null +++ b/params_shard_2.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6bae781153bd459d880be2e70887b0e8f907ea4edfc55e1c4e8741caa0191e +size 32913408 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..bf34b94e6d811cc0ee62be6adffad7faf7d55600 --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:198cca22c8e0dffd25b1698f53e39fcfae654647a25ff9ca5bc08adb7f8cad9a +size 26750976 diff --git a/params_shard_21.bin b/params_shard_21.bin new file mode 100644 index 0000000000000000000000000000000000000000..d8ecd99d57385270c2400598e5c817c82ab594f2 --- /dev/null +++ b/params_shard_21.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6f9e6f71d9efa167fe1d220113a6634de1ce2aba77fbf706e0f1ce526515d9 +size 25165824 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..1ac4b6b4e32f9c4c3a52465f9272401869865945 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3160a31a5ec468664339c70ea88d7f8f52b2d436e401c92ab459acbc9ae2a41 +size 26750976 diff --git a/params_shard_23.bin b/params_shard_23.bin new file mode 100644 index 0000000000000000000000000000000000000000..49b999db8f27b2d962aeef10a103567e883e1f84 --- /dev/null +++ b/params_shard_23.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:196834066b869d080358c55778fa25c0bfad18af796044aaa5f8b3aac37aa233 +size 25165824 diff --git a/params_shard_24.bin b/params_shard_24.bin new file mode 100644 index 0000000000000000000000000000000000000000..244f7e3ebe7f28dc9ffbddb2411605a01901a084 --- /dev/null +++ b/params_shard_24.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49af566bd6e35e850ae6b0531b6add59dd154a4430a00d4b1660f165df69748 +size 26750976 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..3d0916c03ce08fbf0312ceb697b9e8ef2321ee89 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef78c2926629e6cb9023ce44f23c94d8ed0b5249edada4059c1848fcd61be30 +size 25165824 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..13f8d49c3a9d684a3f267e7ebc742990272bbdb6 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c9fa6d45ed2fcb95b874075eb34d784129907dd373f6b7bca8fbf2dc6835d83 +size 25165824 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..8d29a8e92b845f286c9fd09ed90852e974957b0f --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a73694b322c17466ec7e4c4df30934fe3d946671aabfac9c65a9f85f8f98f8 +size 27531264 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..44d6cfce942e0e7225ffaaaf63629f5e6d988010 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94af8a43dbe932d5c368938f2d7df9ca2661b5dee286891ef37bed3a76c260f1 +size 25165824 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..f142531a641a95f989f7caa43022042ea3ce7b22 --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc64506d006899888cd9499d257cade9603685a09379bb983b8fee838520329e +size 26750976 diff --git a/params_shard_3.bin b/params_shard_3.bin new file mode 100644 index 0000000000000000000000000000000000000000..2264215268add1da1ed6087b23f24530cff41ed2 --- /dev/null +++ b/params_shard_3.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4af64e7f859cd73a64872f87d985e59603ffe7fe5a35be434955fb0d7e94a434 +size 25165824 diff --git a/params_shard_30.bin b/params_shard_30.bin new file mode 100644 index 0000000000000000000000000000000000000000..01d7ec553898dd7e5fa0c91cbd447f223de3c6b8 --- /dev/null +++ b/params_shard_30.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ac7ba3df111385103c2ba7810734bf90e4d4ea704ea0bb35580c01c7ceb08b +size 25165824 diff --git a/params_shard_31.bin b/params_shard_31.bin new file mode 100644 index 0000000000000000000000000000000000000000..e819157f8058306d7415b51c2cecfd54b0691d4f --- /dev/null +++ b/params_shard_31.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492bd85221f0c335d495fe161835eea165309acda108be615dcb39dd8df5dfd6 +size 26750976 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..3868ccc7ddc86e883d0fa7e2f5dd1ee74fe670e2 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf7602c92eb8c6e305c1e136e70460f674273453d13fef8584d3f2084982cac +size 25165824 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..11cc804174208bd090d418bf984ec97d9f70372b --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6db4a3a107523162f207c61485b187a25c26671ce6889a21567bb0c9294092 +size 26750976 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..5347e78984864504c398394d2b9d80d54c3111c0 --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1b71722299d8029c012d21aa26fd3f62053140edad8e1c7763a35d37306f76 +size 25165824 diff --git a/params_shard_35.bin b/params_shard_35.bin new file mode 100644 index 0000000000000000000000000000000000000000..0ba89b4f3c537b100103629fe6944d7daf0aa015 --- /dev/null +++ b/params_shard_35.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7368f80ff669141a050d9416a1ca55e025b9600e773895736085ffe3793ddce +size 26750976 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..6a8cba6254fe3a82d5b66ef6593a1b66e2ba3940 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:972f65903e86d10f145f7b4f3c84c5c4f70b2cd4d7ad836d5867fa8e594f7a7e +size 25165824 diff --git a/params_shard_37.bin b/params_shard_37.bin new file mode 100644 index 0000000000000000000000000000000000000000..c9078ac06bde3ce5b12b286b53d07344afdfea27 --- /dev/null +++ b/params_shard_37.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc8f57d0d1183cc626b527a49489489f7d8bd931004d502aa57d925234d42503 +size 26750976 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..6de2e60d8a950a19cf98c48cc993c47e005d2895 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a973f5af7a60fb89c3b3ed21233a350a5ad3dad1601ce9fa7270db7b4b5f6e +size 25165824 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..215b85115dd15ed5d1379d6ce80664224b219c44 --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac0f5447853f1d5c8572480b98969dc5ea5f4cf0cd9414bf5408e594da26c724 +size 26750976 diff --git a/params_shard_4.bin b/params_shard_4.bin new file mode 100644 index 0000000000000000000000000000000000000000..61b12b100a1d7e53ca887f76e0622e1de03f44e4 --- /dev/null +++ b/params_shard_4.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45e442e267e7a71b9fb56f022e39aba5a85b9a68a8167394ea7402ce3ff1752 +size 26750976 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..f7c3aa7d3a5d1779b3d3e878317a5c47026995c7 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78396cbbd6cce646f6c7878a8213589f9383c9b34ec223e81c1f3e0d87a55b5 +size 25165824 diff --git a/params_shard_41.bin b/params_shard_41.bin new file mode 100644 index 0000000000000000000000000000000000000000..caa65135f8d7ff5da5fb5969e86c016642824763 --- /dev/null +++ b/params_shard_41.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41bd42b5a48efc749229fb2ce0b34fdf96e27fd645ed31f5ef8b2542d03b5cf3 +size 26750976 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..03c61dd26e064cad600fed54fbd9265fe878df17 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7365675a9fc790ef16e7022f1a7d4546f370d0b5de320b4480b0c87a1d15aae4 +size 25970688 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..401c2c2b00af1e000e87ece8deab4c99f18b7bd7 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af571758f9e690e71a74c0afe5c5be25ddffb8ecd496f4c4d010b527f4549913 +size 25165824 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..71dc82d52ee5c87c1191db99c212ad95d522b158 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b30ab6348f840c3cb50c160ded615ea5f810155e9507366d53a4ccb4809e62fa +size 26750976 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..f9705621e2d632094de80158b42eb6a2794b5eb0 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644fa756da992ee110d7ba38f4b658e772c042f2b2158528ac92cb348275d852 +size 25165824 diff --git a/params_shard_46.bin b/params_shard_46.bin new file mode 100644 index 0000000000000000000000000000000000000000..36eccee9d8c71ce362ee98572045dd0ecd6bbfa5 --- /dev/null +++ b/params_shard_46.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1660e4cf8ebd01dddf797c973e96e5c4737a6b005f9e9577fd9897760ee628c1 +size 26750976 diff --git a/params_shard_47.bin b/params_shard_47.bin new file mode 100644 index 0000000000000000000000000000000000000000..11f0b11dbb64c39f70c43cd68e8f79c06db0ca99 --- /dev/null +++ b/params_shard_47.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:863dc37ea36d6d852dbcef45ba8163c1c1700f2324b99beef5a05290f2a7e69f +size 25165824 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..96cff4daacbc575530c6b301fc4dc9e4aa0dfb8e --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0f7a44d6127d6ee845b0cae2b532dc5bdc69cd1a240d0b4a6f90447d73a94d +size 26750976 diff --git a/params_shard_49.bin b/params_shard_49.bin new file mode 100644 index 0000000000000000000000000000000000000000..596db4197d0c1a7506a36050578d2149270c6c3d --- /dev/null +++ b/params_shard_49.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e2c448a8b68beb7d599e5f2d6812315e5780c1cb083909978ab6aec6f22d1b +size 25165824 diff --git a/params_shard_5.bin b/params_shard_5.bin new file mode 100644 index 0000000000000000000000000000000000000000..c16be5b99eb1ded4c49a5ef773157b0a4ea1a0a6 --- /dev/null +++ b/params_shard_5.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd047c1f7e2bc2749430a5590ae048a648785001ad962424f8e19ab8ccd9a6e0 +size 25165824 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..3fa1cb6ecc555f8349dd14b88d700289c6bb00f7 --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2630b12966ab8f4476d7d15b9c090880bc25d4a24895466e5cf3e21a36311be +size 26750976 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..524429429fc15329b9eb787c60bc3b65ded4ff7f --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eeed400291e132351f60c9c6d358fedd6a4b0ae776b1d9b10f5cbac2cdd8714 +size 25165824 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..2d66c5a5cbbbcf270622850e2e1a6af96f7ead26 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1bf7327daaab9356ed95bb87cb99753243739806c41b4108640ded537c7ba55 +size 26750976 diff --git a/params_shard_53.bin b/params_shard_53.bin new file mode 100644 index 0000000000000000000000000000000000000000..0b0c82938fdef239081c1e27c82e55d9e9ac3d46 --- /dev/null +++ b/params_shard_53.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13fb1c7a8af45e4fbe59337270626bb667d14448cee561b762e2a5f1369f81d +size 25165824 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..9cafc984904de4ed8848a0908758b765c52374c0 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f8755731f5bc74a37fd2630bda5fc63b5767b4e874e0cc0b3d48e923a079b3 +size 26750976 diff --git a/params_shard_55.bin b/params_shard_55.bin new file mode 100644 index 0000000000000000000000000000000000000000..5d07c0b2c19b0c19d844cb510f0eeadcfe318476 --- /dev/null +++ b/params_shard_55.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b59ce98a0fdb49860abc3d277047877ae370a823cce9fce31e66c05df6fca527 +size 25165824 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..3803ab3f7b4154ef2f9a707ebbe851cf0f275bc1 --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4c1a5eb8b2e8b006f792d301057ec620420a6efe2ac39bff193296cc8e8d4ec +size 26750976 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..16d46b294fc7f3e4afbdf428897d3c3fc897c982 --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6be1f882d59702a3c9f9cea2427b96848701c9df6ce6e12093d7698720be43a8 +size 26750976 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..9fbadae0539f4de63dfd30672935fac679ad567e --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f404789f036c1d0405f296ce3321361e5008d2b730e28882ff44124bbf31a47 +size 25165824 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..a88870e0e746ee615049c24b84d37738d6063163 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c401f9f56699f08e4170d8d313c0680d2f8a997b3f705ebe4ad224ef9e2bd5 +size 26750976 diff --git a/params_shard_9.bin b/params_shard_9.bin new file mode 100644 index 0000000000000000000000000000000000000000..ded3420bcc271a6425f16eeaa56510986ad26b11 --- /dev/null +++ b/params_shard_9.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b130e9efb038e91a5eab9a26970207157e820aba48c9bbfabbab5dfa2c9c25 +size 25165824 diff --git a/private-llm-config.json b/private-llm-config.json new file mode 100644 index 0000000000000000000000000000000000000000..d4c6b38fb80aaa8b4313ebbedc1544ba287cb3ec --- /dev/null +++ b/private-llm-config.json @@ -0,0 +1,55 @@ +{ + "model_type": "llama", + "quantization": "w4a16g128asym", + "model_config": { + "hidden_size": 3072, + "intermediate_size": 8192, + "num_attention_heads": 24, + "num_hidden_layers": 28, + "rms_norm_eps": 1e-05, + "vocab_size": 128256, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "context_window_size": 4096, + "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": 4096, + "sliding_window_size": -1, + "prefill_chunk_size": 128, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "mean_gen_len": 128, + "max_gen_len": 512, + "shift_fill_factor": 0.3, + "temperature": 0.6, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.1, + "top_p": 0.9, + "conv_template": "llama-3", + "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..af2d22fff23798bea98b1730ae7cdacaee0b087a --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade1dac458f86f9bea8bf35b713f14e1bbed24228429534038e9f7e54ea3e8b6 +size 17208712 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ce4b0ca7d1a8aaacc6c4db39f7d42e264fc566b6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2065 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "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": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "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_text|>", + "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "legacy": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 2048, + "pad_token": "<|eot_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}