Upload folder using huggingface_hub

README.md

@@ -2,9 +2,9 @@
 license: apache-2.0
 ---
 
-# LucaOne/LucaGPLM(old checkpoint: 17.6M)
+# LucaGPLM
 
-LucaOne/LucaGPLM - The LUCA Gene-Protein language model.
+LucaGPLM - The LUCA general purpose language model.
 
 ## Installation
 
@@ -20,26 +20,17 @@ pip install lucagplm
 from lucagplm import LucaGPLMModel, LucaGPLMTokenizer
 
 # Load model
-model = LucaGPLMModel.from_pretrained("LucaGroup/LucaOne-default-step5.6M")
-tokenizer = LucaGPLMTokenizer.from_pretrained("LucaGroup/LucaOne-default-step5.6M")
+model = LucaGPLMModel.from_pretrained("Yuanfei/LucaOne-default-step17.6M")
+tokenizer = LucaGPLMTokenizer.from_pretrained("Yuanfei/LucaOne-default-step17.6M")
 
 # Example usage
 seq = "ATCG"
-# seq_type="gene", which includes DNA or RNA(Nucleotide Sequences)
 inputs = tokenizer(seq, seq_type="gene",return_tensors="pt")
 outputs = model(**inputs)
 
-print(outputs.last_hidden_state.shape)
-
 seq = "NSQTA"
 inputs = tokenizer(seq, seq_type="prot",return_tensors="pt")
 outputs = model(**inputs)
 
 print(outputs.last_hidden_state.shape)
 ```
-
-
-## Github
-For long sequence embedding, please refer to the git repository:
-
-https://github.com/LucaOne/LucaOne

config.json

@@ -0,0 +1,34 @@
+{
+  "alphabet": "gene_prot",
+  "architectures": [
+    "LucaGPLMModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout_prob": 0.0,
+  "embed_scale": 1.0,
+  "ffn_dim": 10240,
+  "flash_attention_causal": false,
+  "flash_attention_dropout": 0.0,
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 2560,
+  "ignore_index": -100,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1280,
+  "model_type": "lucagplm",
+  "no_position_embeddings": true,
+  "no_token_type_embeddings": false,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 20,
+  "pad_token_id": 0,
+  "pooling_type": "avg",
+  "pooling_units": null,
+  "token_dropout": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_embed_layer_norm": false,
+  "use_flash_attention": false,
+  "use_last_layer_norm": true,
+  "vocab_size": 39
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1134d95d306d1f8fa54896923ec453328a38a00d66b955a8d3a6529484bcacd9
+size 4930878944

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69de48464242d3eab3390e4ff511924d116f4d63680584973e42ec28f502c5f4
+size 1363720440

model.safetensors.index.json

@@ -0,0 +1,351 @@
+{
+  "metadata": {
+    "total_size": 6294561280
+  },
+  "weight_map": {
+    "embeddings.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "embeddings.embed_type.weight": "model-00001-of-00002.safetensors",
+    "encoder.last_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.last_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.fc2.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.15.fc2.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.15.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.16.fc1.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.fc1.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.fc2.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.fc2.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.post_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.post_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.pre_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.rot_emb.inv_freq": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.fc1.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.fc1.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.fc2.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.fc2.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.post_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.post_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.pre_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.rot_emb.inv_freq": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.fc1.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.fc1.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.fc2.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.fc2.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.post_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.post_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.pre_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.rot_emb.inv_freq": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.fc1.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.fc1.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.fc2.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.fc2.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.post_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.post_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.pre_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.pre_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.rot_emb.inv_freq": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "encoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.post_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.post_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.pre_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.pre_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.rot_emb.inv_freq": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "LucaGPLMTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.json

@@ -0,0 +1,41 @@
+{
+  "[PAD]": 0,
+  "[UNK]": 1,
+  "[CLS]": 2,
+  "[SEP]": 3,
+  "[MASK]": 4,
+  "1": 5,
+  "2": 6,
+  "3": 7,
+  "4": 8,
+  "5": 9,
+  "L": 10,
+  "A": 11,
+  "G": 12,
+  "V": 13,
+  "S": 14,
+  "E": 15,
+  "R": 16,
+  "T": 17,
+  "I": 18,
+  "D": 19,
+  "P": 20,
+  "K": 21,
+  "Q": 22,
+  "N": 23,
+  "F": 24,
+  "Y": 25,
+  "M": 26,
+  "H": 27,
+  "W": 28,
+  "C": 29,
+  "X": 30,
+  "B": 31,
+  "U": 32,
+  "Z": 33,
+  "O": 34,
+  "J": 35,
+  ".": 36,
+  "-": 37,
+  "*": 38
+}