Upload FalconForCausalLM

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "./model_final",
+  "alibi": true,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
+    "AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "falcon",
+  "multi_query": false,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_kv_heads": 32,
+  "parallel_attn": false,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a8daf2b45132526a94efde023cd9a72eb7ea362471be3d19cba862bfca6736a
+size 4977933368

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3eadc96017122d7f929bf9fd40cb41f9d4bf70e3fed878d886c62b07e7a62e
+size 268601552

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 5246500864
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00002.safetensors"
+  }
+}