Upload FalconForCausalLM

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "vilsonrodrigues/falcon-7b-instruct-sharded--configuration_falcon.FalconConfig",
+    "AutoModel": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconModel",
+    "AutoModelForCausalLM": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForCausalLM",
+    "AutoModelForQuestionAnswering": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForQuestionAnswering",
+    "AutoModelForSequenceClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForSequenceClassification",
+    "AutoModelForTokenClassification": "vilsonrodrigues/falcon-7b-instruct-sharded--modeling_falcon.FalconForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 4544,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "falcon",
+  "multi_query": true,
+  "new_decoder_architecture": false,
+  "num_attention_heads": 71,
+  "num_hidden_layers": 32,
+  "num_kv_heads": 71,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.33.0.dev0"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d9e156390dd5b418eddf39109c1d1f18ad0ae8a4399a3449befa24c2f35435
+size 1917120969

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e5d486e6385c6d2de0ba7bab163ad2cff5a0533a2630887bf318327f8473ac
+size 1986955207

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5201014e98f432be6c5a6f2d4b31c16daee67e59fa911949c5bd961ab4f8fd
+size 1905508341

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027f1047a6e26895593107aca507fb31b9025c6d2cfc616e9b27f2d44404bb97
+size 1905527129

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71107833b8741a7e6f7d2d8a867d0d7fd662ff4cb2bb2d80af9226b73618ff09
+size 1986955271

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4231834ed68831ab63c0029e960c29143401da057340f9244f0b6eb1c51bfc13
+size 1905508341

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c08de4ee0cfb1c43d0bf186e64b91557ccc58e97cf1fb37514a05c969b8e0ad
+size 1905527129

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543190c357219fea05224ae17e774ec9e1494e58be0c36f5197a54106352d5ed
+size 330405759

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 13843441408
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00004-of-00008.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00005-of-00008.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00006-of-00008.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00008.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00008-of-00008.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00008.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00008.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00007-of-00008.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00002-of-00008.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00003-of-00008.bin",
+    "transformer.ln_f.bias": "pytorch_model-00008-of-00008.bin",
+    "transformer.ln_f.weight": "pytorch_model-00008-of-00008.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00008.bin"
+  }
+}