Upload folder using huggingface_hub

step_llm/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/mnt/shared-storage/tenant/opensource/step_llm",
+  "allow_transformer_engine": false,
+  "architectures": [
+    "Step1Model"
+  ],
+  "attention_dropout": 0.0,
+  "attention_impl": "GQA",
+  "base_batch_size": 128,
+  "embedding_weights_in_fp32": false,
+  "ffn_hidden_size": 16896,
+  "fp32_residual_connection": false,
+  "hidden_dropout": 0.0,
+  "hidden_size": 6144,
+  "kv_channels": 128,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 16384,
+  "num_attention_groups": 8,
+  "num_attention_heads": 48,
+  "num_layers": 48,
+  "orig_vocab_size": 65536,
+  "overlap_p2p_comm": true,
+  "padded_vocab_size": 65536,
+  "params_dtype": "torch.bfloat16",
+  "seq_length": 16384,
+  "swiglu_recompute_silu_dot": true,
+  "tokens_to_generate": 512,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_flash_attn": true,
+  "virtual_pipeline_model_parallel_size": 3
+}

step_llm/model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc79bad96b5f9fdd56106864c56fdc7955627062de4d023ee99944ddac0c930
+size 4976668520

step_llm/model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2112d1a56602599f5cd9c8f3e80b47a9df5861b5a03c565fbd29f4cbc8b7acc
+size 4794241224

step_llm/model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7bd774bd5c30b51ae342ae92ae9d2706d631bf4ee817fd0997ccc1b0b651c3
+size 4794241248

step_llm/model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d9d688d310ef2098b9f219d7fd84245d13a46b969497de5c111cdd3196a86e
+size 4794241248

step_llm/model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe129667571adf93917a54839a7af52f702bd7c7e63aee34912228507d6c1dc
+size 4794241248

step_llm/model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4f01bd89d7e047de600579071e6e5e17dfff7aaf8143323ab2989ec840db26
+size 4794241248

step_llm/model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e9ba842a20b0a0fe9bc00646135b5c82cf544c6fba83aaa3630748f9c9ada9
+size 4794241248

step_llm/model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40c5fd462b5422bdb8665fcb2e4c461cbdbd39f92c9b5e677f87a77044c259af
+size 4794241248

step_llm/model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d707aa08cd795a137e6b18558658e65bd9969a27a8aca34d201e3a1b1a68fa4e
+size 622879216

step_llm/model.safetensors.index.json

@@ -0,0 +1,296 @@
+{
+  "metadata": {
+    "total_size": 78318403584
+  },
+  "weight_map": {
+    "tok_embeddings.word_embeddings.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.attention.wo.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.attention.wqkv.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.attention_norm.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.feed_forward.w1.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.feed_forward.w2.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.0.ffn_norm.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.attention.wo.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.attention.wqkv.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.attention_norm.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.feed_forward.w1.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.feed_forward.w2.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.1.ffn_norm.weight": "model-00001-of-00017.safetensors",
+    "transformer.layers.10.attention.wo.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.10.attention.wqkv.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.10.attention_norm.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.10.feed_forward.w1.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.10.feed_forward.w2.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.10.ffn_norm.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.11.attention.wo.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.11.attention.wqkv.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.11.attention_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.11.feed_forward.w1.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.11.feed_forward.w2.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.11.ffn_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.attention.wo.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.attention.wqkv.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.attention_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.feed_forward.w1.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.feed_forward.w2.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.12.ffn_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.attention.wo.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.attention.wqkv.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.attention_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.feed_forward.w1.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.feed_forward.w2.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.13.ffn_norm.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.14.attention.wo.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.14.attention.wqkv.weight": "model-00005-of-00017.safetensors",
+    "transformer.layers.14.attention_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.14.feed_forward.w1.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.14.feed_forward.w2.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.14.ffn_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.attention.wo.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.attention.wqkv.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.attention_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.feed_forward.w1.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.feed_forward.w2.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.15.ffn_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.attention.wo.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.attention.wqkv.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.attention_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.feed_forward.w1.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.feed_forward.w2.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.16.ffn_norm.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.17.attention.wo.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.17.attention.wqkv.weight": "model-00006-of-00017.safetensors",
+    "transformer.layers.17.attention_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.17.feed_forward.w1.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.17.feed_forward.w2.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.17.ffn_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.attention.wo.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.attention.wqkv.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.attention_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.feed_forward.w1.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.feed_forward.w2.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.18.ffn_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.attention.wo.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.attention.wqkv.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.attention_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.feed_forward.w1.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.feed_forward.w2.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.19.ffn_norm.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.2.attention.wo.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.2.attention.wqkv.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.2.attention_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.2.feed_forward.w1.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.2.feed_forward.w2.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.2.ffn_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.20.attention.wo.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.20.attention.wqkv.weight": "model-00007-of-00017.safetensors",
+    "transformer.layers.20.attention_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.20.feed_forward.w1.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.20.feed_forward.w2.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.20.ffn_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.attention.wo.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.attention.wqkv.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.attention_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.feed_forward.w1.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.feed_forward.w2.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.21.ffn_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.attention.wo.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.attention.wqkv.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.attention_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.feed_forward.w1.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.feed_forward.w2.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.22.ffn_norm.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.23.attention.wo.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.23.attention.wqkv.weight": "model-00008-of-00017.safetensors",
+    "transformer.layers.23.attention_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.23.feed_forward.w1.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.23.feed_forward.w2.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.23.ffn_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.attention.wo.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.attention.wqkv.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.attention_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.feed_forward.w1.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.feed_forward.w2.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.24.ffn_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.attention.wo.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.attention.wqkv.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.attention_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.feed_forward.w1.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.feed_forward.w2.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.25.ffn_norm.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.26.attention.wo.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.26.attention.wqkv.weight": "model-00009-of-00017.safetensors",
+    "transformer.layers.26.attention_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.26.feed_forward.w1.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.26.feed_forward.w2.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.26.ffn_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.attention.wo.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.attention.wqkv.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.attention_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.feed_forward.w1.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.feed_forward.w2.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.27.ffn_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.attention.wo.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.attention.wqkv.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.attention_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.feed_forward.w1.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.feed_forward.w2.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.28.ffn_norm.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.29.attention.wo.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.29.attention.wqkv.weight": "model-00010-of-00017.safetensors",
+    "transformer.layers.29.attention_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.29.feed_forward.w1.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.29.feed_forward.w2.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.29.ffn_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.3.attention.wo.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.3.attention.wqkv.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.3.attention_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.3.feed_forward.w1.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.3.feed_forward.w2.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.3.ffn_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.30.attention.wo.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.30.attention.wqkv.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.30.attention_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.30.feed_forward.w1.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.30.feed_forward.w2.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.30.ffn_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.attention.wo.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.attention.wqkv.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.attention_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.feed_forward.w1.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.feed_forward.w2.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.31.ffn_norm.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.32.attention.wo.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.32.attention.wqkv.weight": "model-00011-of-00017.safetensors",
+    "transformer.layers.32.attention_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.32.feed_forward.w1.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.32.feed_forward.w2.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.32.ffn_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.attention.wo.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.attention.wqkv.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.attention_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.feed_forward.w1.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.feed_forward.w2.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.33.ffn_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.attention.wo.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.attention.wqkv.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.attention_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.feed_forward.w1.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.feed_forward.w2.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.34.ffn_norm.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.35.attention.wo.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.35.attention.wqkv.weight": "model-00012-of-00017.safetensors",
+    "transformer.layers.35.attention_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.35.feed_forward.w1.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.35.feed_forward.w2.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.35.ffn_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.attention.wo.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.attention.wqkv.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.attention_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.feed_forward.w1.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.feed_forward.w2.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.36.ffn_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.attention.wo.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.attention.wqkv.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.attention_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.feed_forward.w1.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.feed_forward.w2.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.37.ffn_norm.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.38.attention.wo.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.38.attention.wqkv.weight": "model-00013-of-00017.safetensors",
+    "transformer.layers.38.attention_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.38.feed_forward.w1.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.38.feed_forward.w2.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.38.ffn_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.attention.wo.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.attention.wqkv.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.attention_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.feed_forward.w1.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.feed_forward.w2.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.39.ffn_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.4.attention.wo.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.4.attention.wqkv.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.4.attention_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.4.feed_forward.w1.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.4.feed_forward.w2.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.4.ffn_norm.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.40.attention.wo.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.40.attention.wqkv.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.40.attention_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.40.feed_forward.w1.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.40.feed_forward.w2.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.40.ffn_norm.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.41.attention.wo.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.41.attention.wqkv.weight": "model-00014-of-00017.safetensors",
+    "transformer.layers.41.attention_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.41.feed_forward.w1.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.41.feed_forward.w2.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.41.ffn_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.attention.wo.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.attention.wqkv.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.attention_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.feed_forward.w1.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.feed_forward.w2.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.42.ffn_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.attention.wo.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.attention.wqkv.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.attention_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.feed_forward.w1.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.feed_forward.w2.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.43.ffn_norm.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.44.attention.wo.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.44.attention.wqkv.weight": "model-00015-of-00017.safetensors",
+    "transformer.layers.44.attention_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.44.feed_forward.w1.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.44.feed_forward.w2.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.44.ffn_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.attention.wo.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.attention.wqkv.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.attention_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.feed_forward.w1.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.feed_forward.w2.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.45.ffn_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.attention.wo.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.attention.wqkv.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.attention_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.feed_forward.w1.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.feed_forward.w2.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.46.ffn_norm.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.47.attention.wo.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.47.attention.wqkv.weight": "model-00016-of-00017.safetensors",
+    "transformer.layers.47.attention_norm.weight": "model-00017-of-00017.safetensors",
+    "transformer.layers.47.feed_forward.w1.weight": "model-00017-of-00017.safetensors",
+    "transformer.layers.47.feed_forward.w2.weight": "model-00017-of-00017.safetensors",
+    "transformer.layers.47.ffn_norm.weight": "model-00017-of-00017.safetensors",
+    "transformer.layers.5.attention.wo.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.5.attention.wqkv.weight": "model-00002-of-00017.safetensors",
+    "transformer.layers.5.attention_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.5.feed_forward.w1.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.5.feed_forward.w2.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.5.ffn_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.attention.wo.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.attention.wqkv.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.attention_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.feed_forward.w1.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.feed_forward.w2.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.6.ffn_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.attention.wo.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.attention.wqkv.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.attention_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.feed_forward.w1.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.feed_forward.w2.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.7.ffn_norm.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.8.attention.wo.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.8.attention.wqkv.weight": "model-00003-of-00017.safetensors",
+    "transformer.layers.8.attention_norm.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.8.feed_forward.w1.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.8.feed_forward.w2.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.8.ffn_norm.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.attention.wo.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.attention.wqkv.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.attention_norm.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.feed_forward.w1.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.feed_forward.w2.weight": "model-00004-of-00017.safetensors",
+    "transformer.layers.9.ffn_norm.weight": "model-00004-of-00017.safetensors"
+  }
+}

step_llm/step1_chat_tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae238f74162b98d3384eb1ceef143ed67f822528a6b0d6c5e351f87d7f4a651a
+size 1053360