Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "sapienzanlp/modello-italia-9b",
+  "architectures": [
+    "GPTNeoXModel"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout": 0.0,
+  "hidden_dropout_prob": 0,
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 34,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.4,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50176
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230b3b69f340e22f9bfef6db0a8034a1589e404de4784c5bcab0b9f9feebd0db
+size 4971404856

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7862e642b14c213305caccc530d89b9906fdfdad769bfd9cdefdc9921d5de04
+size 4982004552

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8694400f9000eed0447a09c82da358b7cdef00c839d4a9a5f2e81521ab1c550a
+size 4929539496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5738d25eb325473871d381476b5c1bac8857336c4b9f093b5259b558c1d632d9
+size 1678135784

model.safetensors.index.json

@@ -0,0 +1,418 @@
+{
+  "metadata": {
+    "total_size": 16561039360
+  },
+  "weight_map": {
+    "embed_in.weight": "model-00001-of-00004.safetensors",
+    "final_layer_norm.bias": "model-00004-of-00004.safetensors",
+    "final_layer_norm.weight": "model-00004-of-00004.safetensors",
+    "layers.0.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.0.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.0.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.0.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.1.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.1.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.1.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.10.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.10.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.10.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.10.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.10.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.10.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.11.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.11.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.11.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.12.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.12.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.12.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.13.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.13.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.13.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.14.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.14.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.14.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.15.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.15.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.15.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.16.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.16.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.16.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.17.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.17.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.17.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.18.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.18.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.18.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.attention.dense.bias": "model-00002-of-00004.safetensors",
+    "layers.19.attention.dense.weight": "model-00002-of-00004.safetensors",
+    "layers.19.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
+    "layers.19.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
+    "layers.19.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.2.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.2.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.2.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.2.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.2.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.20.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.20.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.20.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.20.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.20.input_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.20.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.20.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
+    "layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "layers.21.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.21.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.21.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.21.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.21.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.21.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.22.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.22.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.22.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.22.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.22.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.23.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.23.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.23.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.23.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.24.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.24.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.24.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.25.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.25.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.25.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.26.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.26.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.26.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.27.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.27.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.27.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.28.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.28.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.28.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.29.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.29.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.29.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
+    "layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.3.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.3.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.3.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.3.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.3.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.30.attention.dense.bias": "model-00003-of-00004.safetensors",
+    "layers.30.attention.dense.weight": "model-00003-of-00004.safetensors",
+    "layers.30.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
+    "layers.30.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
+    "layers.30.input_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.30.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "layers.30.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
+    "layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "layers.31.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "layers.31.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "layers.31.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "layers.31.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "layers.31.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "layers.31.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.32.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "layers.32.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "layers.32.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "layers.32.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "layers.32.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.32.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "layers.32.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "layers.32.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "layers.32.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "layers.32.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.33.attention.dense.bias": "model-00004-of-00004.safetensors",
+    "layers.33.attention.dense.weight": "model-00004-of-00004.safetensors",
+    "layers.33.attention.query_key_value.bias": "model-00004-of-00004.safetensors",
+    "layers.33.attention.query_key_value.weight": "model-00004-of-00004.safetensors",
+    "layers.33.input_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.dense_4h_to_h.bias": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.dense_4h_to_h.weight": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.dense_h_to_4h.bias": "model-00004-of-00004.safetensors",
+    "layers.33.mlp.dense_h_to_4h.weight": "model-00004-of-00004.safetensors",
+    "layers.33.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
+    "layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "layers.4.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.4.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.4.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.4.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.4.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.5.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.5.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.5.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.6.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.6.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.6.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.7.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.7.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.7.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.7.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.8.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.8.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.8.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.8.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00004.safetensors",
+    "layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.9.attention.dense.bias": "model-00001-of-00004.safetensors",
+    "layers.9.attention.dense.weight": "model-00001-of-00004.safetensors",
+    "layers.9.attention.query_key_value.bias": "model-00001-of-00004.safetensors",
+    "layers.9.attention.query_key_value.weight": "model-00001-of-00004.safetensors",
+    "layers.9.input_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "layers.9.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
+    "layers.9.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.bias": "model-00001-of-00004.safetensors",
+    "layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd74bea2ba620d87e0a2127d9a21196b862a5cc7942ba4638eb2159bbab3340c
+size 1090536

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}