update model

Browse files

Files changed (5) hide show

config.json +50 -0
model.safetensors +3 -0
special_tokens_map.json +30 -0
tokenizer_config.json +44 -0
vocab.txt +267 -0

config.json ADDED Viewed

	@@ -0,0 +1,50 @@

+{
+  "_name_or_path": "../model/finetune/PlantDna_Mamba_4mer/plant-multi-species-sequence-conservation",
+  "architectures": [
+    "MambaForSequenceClassification"
+  ],
+  "bos_token_id": 0,
+  "conv_kernel": 4,
+  "d_inner": 1536,
+  "d_model": 768,
+  "eos_token_id": 0,
+  "expand": 2,
+  "fused_add_norm": true,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Not_conservation",
+    "1": "conservation"
+  },
+  "initializer_range": 0.1,
+  "intermediate_size": 1536,
+  "label2id": {
+    "Not_conservation": 0,
+    "conservation": 1
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "mamba",
+  "n_layer": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pad_vocab_size_multiple": 8,
+  "problem_type": "single_label_classification",
+  "rescale_prenorm_residual": false,
+  "residual_in_fp32": true,
+  "rms_norm": true,
+  "ssm_cfg": {},
+  "state_size": 16,
+  "time_step_floor": 0.0001,
+  "time_step_init_scheme": "random",
+  "time_step_max": 0.1,
+  "time_step_min": 0.001,
+  "time_step_rank": 48,
+  "time_step_scale": 1.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0.dev0",
+  "use_bias": false,
+  "use_cache": false,
+  "use_conv_bias": true,
+  "use_mambapy": false,
+  "vocab_size": 267
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5024b1a7201c630b047e2f614a941d54543cd29163fd8cc6577dc53f6f3b4b
+size 362933784

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": null,
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "tokenizer_class": "EsmTokenizer",
+  "unk_token": "<unk>"
+}

vocab.txt ADDED Viewed

	@@ -0,0 +1,267 @@

+<unk>
+<pad>
+<mask>
+<cls>
+AAAA
+AAAT
+AAAC
+AAAG
+AATA
+AATT
+AATC
+AATG
+AACA
+AACT
+AACC
+AACG
+AAGA
+AAGT
+AAGC
+AAGG
+ATAA
+ATAT
+ATAC
+ATAG
+ATTA
+ATTT
+ATTC
+ATTG
+ATCA
+ATCT
+ATCC
+ATCG
+ATGA
+ATGT
+ATGC
+ATGG
+ACAA
+ACAT
+ACAC
+ACAG
+ACTA
+ACTT
+ACTC
+ACTG
+ACCA
+ACCT
+ACCC
+ACCG
+ACGA
+ACGT
+ACGC
+ACGG
+AGAA
+AGAT
+AGAC
+AGAG
+AGTA
+AGTT
+AGTC
+AGTG
+AGCA
+AGCT
+AGCC
+AGCG
+AGGA
+AGGT
+AGGC
+AGGG
+TAAA
+TAAT
+TAAC
+TAAG
+TATA
+TATT
+TATC
+TATG
+TACA
+TACT
+TACC
+TACG
+TAGA
+TAGT
+TAGC
+TAGG
+TTAA
+TTAT
+TTAC
+TTAG
+TTTA
+TTTT
+TTTC
+TTTG
+TTCA
+TTCT
+TTCC
+TTCG
+TTGA
+TTGT
+TTGC
+TTGG
+TCAA
+TCAT
+TCAC
+TCAG
+TCTA
+TCTT
+TCTC
+TCTG
+TCCA
+TCCT
+TCCC
+TCCG
+TCGA
+TCGT
+TCGC
+TCGG
+TGAA
+TGAT
+TGAC
+TGAG
+TGTA
+TGTT
+TGTC
+TGTG
+TGCA
+TGCT
+TGCC
+TGCG
+TGGA
+TGGT
+TGGC
+TGGG
+CAAA
+CAAT
+CAAC
+CAAG
+CATA
+CATT
+CATC
+CATG
+CACA
+CACT
+CACC
+CACG
+CAGA
+CAGT
+CAGC
+CAGG
+CTAA
+CTAT
+CTAC
+CTAG
+CTTA
+CTTT
+CTTC
+CTTG
+CTCA
+CTCT
+CTCC
+CTCG
+CTGA
+CTGT
+CTGC
+CTGG
+CCAA
+CCAT
+CCAC
+CCAG
+CCTA
+CCTT
+CCTC
+CCTG
+CCCA
+CCCT
+CCCC
+CCCG
+CCGA
+CCGT
+CCGC
+CCGG
+CGAA
+CGAT
+CGAC
+CGAG
+CGTA
+CGTT
+CGTC
+CGTG
+CGCA
+CGCT
+CGCC
+CGCG
+CGGA
+CGGT
+CGGC
+CGGG
+GAAA
+GAAT
+GAAC
+GAAG
+GATA
+GATT
+GATC
+GATG
+GACA
+GACT
+GACC
+GACG
+GAGA
+GAGT
+GAGC
+GAGG
+GTAA
+GTAT
+GTAC
+GTAG
+GTTA
+GTTT
+GTTC
+GTTG
+GTCA
+GTCT
+GTCC
+GTCG
+GTGA
+GTGT
+GTGC
+GTGG
+GCAA
+GCAT
+GCAC
+GCAG
+GCTA
+GCTT
+GCTC
+GCTG
+GCCA
+GCCT
+GCCC
+GCCG
+GCGA
+GCGT
+GCGC
+GCGG
+GGAA
+GGAT
+GGAC
+GGAG
+GGTA
+GGTT
+GGTC
+GGTG
+GGCA
+GGCT
+GGCC
+GGCG
+GGGA
+GGGT
+GGGC
+GGGG
+A
+T
+C
+G
+N
+<eos>
+<bos>