Upload 7 files

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "tiiuae/falcon-7b",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "FalconForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "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,
+  "n_head": 71,
+  "n_layer": 32,
+  "parallel_attn": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1,203 @@
+{
+    "metadata": {
+        "total_size": 14434379520
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.30.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.31.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.ln_f.bias": "model-00008-of-00008.safetensors",
+        "transformer.ln_f.weight": "model-00008-of-00008.safetensors",
+        "transformer.word_embeddings.weight": "model-00001-of-00008.safetensors"
+    }
+}

pytorch_model.bin.index.json

@@ -0,0 +1,203 @@
+{
+  "metadata": {
+    "total_size": 14434379520
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-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-00003-of-00008.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00003-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-00004-of-00008.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00004-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-00005-of-00008.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00005-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-00006-of-00008.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00006-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-00001-of-00008.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-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-00007-of-00008.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00007-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-00002-of-00008.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00002-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"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}