Delete step_llm

step_llm/config.json

@@ -1,31 +0,0 @@
-{
-  "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": "float32",
-  "transformers_version": "4.46.3",
-  "use_flash_attn": true,
-  "virtual_pipeline_model_parallel_size": 3
-}

step_llm/model-00001-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dd053baa9f39e3222d097b11f820ff87d51b3530f2b228bf2a7dfd82d3717044
-size 4806772248

step_llm/model-00002-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b5b2e419d8c6f205ec8e6f5783e66b8d7451d55dccabe20e0117dfdbd1ad8b26
-size 4995565784

step_llm/model-00003-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:85e51f95a110bd86ab5b4ffedf1b0736cafec2d8b81969aef1b119241648072f
-size 4945234136

step_llm/model-00004-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ac3230ca5622d98750d776afed63a0578e2312b1e6cc0247446f8fa9b4420882
-size 4794239080

step_llm/model-00005-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:de7e57371be2d6457e07b0431ffef527df4929b23a42ab70967b5b38f0381979
-size 4794239088

step_llm/model-00006-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:854b71d52d65ffdee085f576654a5a6d76810e9e3461b7bb950783f1ee492542
-size 4794239088

step_llm/model-00007-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:af38cc39fd9094abf4aa65e90495d2643bdfe704c744afafe6253a0cf2f1c437
-size 4794239088

step_llm/model-00008-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6bf7e10cdfbc41e8f455852364862794f6d081b4e7afa2c3dc326ec3ee4c7a4d
-size 4794239088

step_llm/model-00009-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:459a960995bf619f888f7bf6502ecce49a58763258467eb4ea9413b41ecfaa60
-size 4794239088

step_llm/model-00010-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0702ad95609155b2e3baff9d481f9c29947b0212a138f61419b7c5abf3612876
-size 4794239088

step_llm/model-00011-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a8523b2f4590e22cfe7bfa80888908acc49d9db2795c6356d8b7409d9a37a60
-size 4794239088

step_llm/model-00012-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c044e5cb2b97ad06e4f8c61f695cdef43205f68c2f21ce3f58f8321d05dd8568
-size 4794239088

step_llm/model-00013-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b23b4c6e917389dd984291f8a5ee79728770d743a0d4c7f4e76e12ddb70e1e71
-size 4794239088

step_llm/model-00014-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a1f8b1517af67352f9188f6f733b87181c098d90d309d1d28e7138d73fc309b
-size 4794239088

step_llm/model-00015-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f30ae7f4165367f9e06ad3d53905d1f040e46c45e68c941cabacbc4fcd54e767
-size 4794239088

step_llm/model-00016-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:08839ebb25e2b7ff3ec37eb9f516f961a3499aa1d7a35bd7f8a7d00677577ba1
-size 4794239088

step_llm/model-00017-of-00017.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2441d58f0668f6a9d9f0e409f79b61dd983053d197c278a3c75196b21527f7cd
-size 1245757936

step_llm/model.safetensors.index.json

@@ -1,296 +0,0 @@
-{
-  "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

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