Upload folder using huggingface_hub

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "tiiuae/falcon-11B",
+  "activation": "gelu",
+  "alibi": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-11B--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-11B--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-11B--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-11B--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-11B--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "ff_factor": 4,
+  "ffn_hidden_size": 16384,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 8192,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": true,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 60,
+  "num_kv_heads": 8,
+  "num_ln_in_parallel_attn": 1,
+  "parallel_attn": true,
+  "rope_scaling": null,
+  "rope_theta": 500042.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "vocab_size": 65024
+}

.ipynb_checkpoints/model.safetensors.index-checkpoint.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 22205644800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.24.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.input_layernorm.bias": "model-00002-of-00005.safetensors",
+    "transformer.h.25.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.26.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.26.self_attention.dense.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.27.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.30.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.34.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.35.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.36.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.37.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.38.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.input_layernorm.bias": "model-00003-of-00005.safetensors",
+    "transformer.h.39.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.40.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.40.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.40.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.40.self_attention.dense.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.40.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.41.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.44.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.45.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.46.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.47.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.48.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.49.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.50.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.50.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.51.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.52.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.input_layernorm.bias": "model-00004-of-00005.safetensors",
+    "transformer.h.53.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.54.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.54.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.54.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.54.self_attention.dense.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.54.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.55.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.56.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.57.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.58.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.input_layernorm.bias": "model-00005-of-00005.safetensors",
+    "transformer.h.59.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.self_attention.dense.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
+    "transformer.ln_f.bias": "model-00005-of-00005.safetensors",
+    "transformer.ln_f.weight": "model-00005-of-00005.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00005.safetensors"
+  }
+}

config.json

@@ -34,7 +34,6 @@
   "parallel_attn": true,
   "rope_scaling": null,
   "rope_theta": 500042.0,
-  "rotary_base": 5000042,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.2",

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f12d1629a8a47b89f57b80c7fc4781347970f47df4c2c35d7908948ee285bd
-size 4978844408
+oid sha256:39a018223c3be981175c7b36024f7c939ec82cd274d4b6b34557e48321d81f5c
+size 4978844536

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01ca0693ff809a32700e4255c2d85aaf5ba4934edbea289a9055b5661abb5fcf
-size 4932740832
+oid sha256:43299e48da013aff2037099c2a79c50788143c1eb7d39e3e7c7e29f54a8bd135
+size 4932740968

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31b75705b43abca86920c0bc8cc12bb0ec62ca99e9e8ce928946d878936ae2b
-size 4932740832
+oid sha256:7747d394a507c6e6f84d776523473a605affcd6583297f4312c14cea4b5d37a6
+size 4932740968

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1880ff98c2c5227b8436514be14f1261a48e2bbf426974b2143d6e41de6280f6
-size 4932740832
+oid sha256:aa373243a06fa7244d40b0e28c745e11fb6fb406578f422f9a4710e6868ee6bf
+size 4932740968

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0c1b5f09be4f2019194d03767fa53226bdbe33f560c15893f968581064f8a1
-size 2428620904
+oid sha256:5f0df799812b7ce0b3ae6ed859f34d188e85b4ebb2f31154b1bdf6c87e562367
+size 2428620960

model.safetensors.index.json

@@ -6,366 +6,366 @@
     "lm_head.weight": "model-00005-of-00005.safetensors",
     "transformer.h.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.0.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.0.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.0.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.1.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.1.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.1.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.10.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.10.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.10.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.11.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.11.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.11.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.12.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.12.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.12.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.12.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.13.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.13.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.13.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.13.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.14.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.14.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.14.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.14.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.15.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.15.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.15.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.15.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.16.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.16.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.16.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.16.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.17.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.17.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.17.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.17.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.18.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.18.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.18.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.18.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.19.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.19.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.19.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.19.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.2.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.2.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.2.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.20.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.20.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.20.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.20.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.21.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.21.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.21.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.21.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.22.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.22.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.22.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.22.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.22.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.23.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.23.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.23.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.23.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.23.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.24.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.24.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.24.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.24.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.24.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.25.input_layernorm.bias": "model-00002-of-00005.safetensors",
     "transformer.h.25.input_layernorm.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.25.mlp.downscale.weight": "model-00002-of-00005.safetensors",
-    "transformer.h.25.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.25.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.26.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.26.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.26.mlp.upscale.weight": "model-00002-of-00005.safetensors",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00002-of-00005.safetensors",
     "transformer.h.26.self_attention.dense.weight": "model-00002-of-00005.safetensors",
     "transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
     "transformer.h.27.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.27.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.27.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.27.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.28.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.28.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.28.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.28.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.29.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.29.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.29.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.29.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.3.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.3.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.3.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.30.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.30.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.30.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.30.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.31.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.31.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.31.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.31.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.32.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.32.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.32.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.32.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.32.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.32.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.33.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.33.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.33.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.33.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.33.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.33.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.34.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.34.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.34.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.34.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.34.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.34.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.34.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.35.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.35.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.35.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.35.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.35.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.35.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.35.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.36.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.36.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.36.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.36.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.36.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.36.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.36.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.37.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.37.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.37.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.37.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.37.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.37.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.37.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.38.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.38.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.38.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.38.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.38.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.38.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.38.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.39.input_layernorm.bias": "model-00003-of-00005.safetensors",
     "transformer.h.39.input_layernorm.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.39.mlp.downscale.weight": "model-00003-of-00005.safetensors",
-    "transformer.h.39.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.mlp.dense_4h_to_h.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.39.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.39.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.39.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.4.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.4.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.4.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.40.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.40.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.40.mlp.upscale.weight": "model-00003-of-00005.safetensors",
+    "transformer.h.40.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.40.mlp.dense_h_to_4h.weight": "model-00003-of-00005.safetensors",
     "transformer.h.40.self_attention.dense.weight": "model-00003-of-00005.safetensors",
     "transformer.h.40.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
     "transformer.h.41.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.41.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.41.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.41.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.41.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.41.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.42.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.42.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.42.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.42.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.42.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.42.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.43.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.43.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.43.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.43.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.43.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.43.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.44.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.44.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.44.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.44.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.44.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.44.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.44.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.45.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.45.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.45.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.45.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.45.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.45.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.45.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.46.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.46.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.46.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.46.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.46.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.46.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.46.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.47.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.47.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.47.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.47.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.47.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.47.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.47.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.48.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.48.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.48.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.48.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.48.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.48.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.48.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.49.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.49.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.49.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.49.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.49.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.49.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.49.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.5.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.5.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.5.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.50.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.50.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.50.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.50.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.50.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.50.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.50.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.51.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.51.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.51.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.51.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.51.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.51.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.51.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.52.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.52.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.52.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.52.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.52.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.52.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.52.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.53.input_layernorm.bias": "model-00004-of-00005.safetensors",
     "transformer.h.53.input_layernorm.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.53.mlp.downscale.weight": "model-00004-of-00005.safetensors",
-    "transformer.h.53.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.mlp.dense_4h_to_h.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.53.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.53.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.53.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.54.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.54.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.54.mlp.upscale.weight": "model-00004-of-00005.safetensors",
+    "transformer.h.54.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.54.mlp.dense_h_to_4h.weight": "model-00004-of-00005.safetensors",
     "transformer.h.54.self_attention.dense.weight": "model-00004-of-00005.safetensors",
     "transformer.h.54.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
     "transformer.h.55.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.55.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.55.mlp.upscale.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.55.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
     "transformer.h.55.self_attention.dense.weight": "model-00005-of-00005.safetensors",
     "transformer.h.55.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
     "transformer.h.56.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.56.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.56.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.56.mlp.upscale.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.56.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
     "transformer.h.56.self_attention.dense.weight": "model-00005-of-00005.safetensors",
     "transformer.h.56.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
     "transformer.h.57.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.57.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.57.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.57.mlp.upscale.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.57.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
     "transformer.h.57.self_attention.dense.weight": "model-00005-of-00005.safetensors",
     "transformer.h.57.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
     "transformer.h.58.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.58.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.58.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.58.mlp.upscale.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.58.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
     "transformer.h.58.self_attention.dense.weight": "model-00005-of-00005.safetensors",
     "transformer.h.58.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
     "transformer.h.59.input_layernorm.bias": "model-00005-of-00005.safetensors",
     "transformer.h.59.input_layernorm.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.59.mlp.downscale.weight": "model-00005-of-00005.safetensors",
-    "transformer.h.59.mlp.upscale.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.mlp.dense_4h_to_h.weight": "model-00005-of-00005.safetensors",
+    "transformer.h.59.mlp.dense_h_to_4h.weight": "model-00005-of-00005.safetensors",
     "transformer.h.59.self_attention.dense.weight": "model-00005-of-00005.safetensors",
     "transformer.h.59.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
     "transformer.h.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.6.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.6.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.6.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.7.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.7.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.7.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.8.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.8.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.8.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.h.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
     "transformer.h.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.9.mlp.downscale.weight": "model-00001-of-00005.safetensors",
-    "transformer.h.9.mlp.upscale.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00005.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00005.safetensors",
     "transformer.h.9.self_attention.dense.weight": "model-00001-of-00005.safetensors",
     "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
     "transformer.ln_f.bias": "model-00005-of-00005.safetensors",
     "transformer.ln_f.weight": "model-00005-of-00005.safetensors",
     "transformer.word_embeddings.weight": "model-00001-of-00005.safetensors"
   }
-}
+}