Model save

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: SymLM
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# SymLM
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 1024
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_attn_implementation_autoset": true,
+  "adapters": [
+    "lnn"
+  ],
+  "bos_token_id": 2,
+  "chunk_size_feed_forward": 64,
+  "d_model": 2048,
+  "do_sample": true,
+  "dropout": 0.1,
+  "eos_token_id": 3,
+  "max_length": 512,
+  "max_seq": 4096,
+  "min_length": 64,
+  "model_type": "symbiotic-llm",
+  "n_heads": 32,
+  "n_layers": 16,
+  "no_repeat_ngram_size": 1,
+  "pad_token_id": 0,
+  "rope_base": 1000000.0,
+  "tie_embed": true,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3",
+  "typical_p": 0.95,
+  "use_flash": false,
+  "vocab_size": 37524
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd87fa15eade18cff547142d30993b473c03b049865e622eca8899d0f05abfd
+size 11082456279

special_tokens_map.json

@@ -0,0 +1,52 @@
+{
+  "additional_special_tokens": [
+    "<pad>",
+    "<unk>",
+    "<bos>",
+    "<eos>",
+    "<mask>",
+    "<user>",
+    "<assistant>",
+    "<system>",
+    "<image>",
+    "<graph>",
+    "<soft_token>",
+    "<vis_0>",
+    "<vis_1>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "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
+  }
+}

symbiotic_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53e9897b690e69095a7191f11cc2ef23d62253d547d46a4ba10bc7587902c6a
+size 10557096952

tokenizer_config.json

@@ -0,0 +1,172 @@
+{
+  "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": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<eos>",
+      "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
+    },
+    "5": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<graph>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<soft_token>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<vis_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<vis_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<pad>",
+    "<unk>",
+    "<bos>",
+    "<eos>",
+    "<mask>",
+    "<user>",
+    "<assistant>",
+    "<system>",
+    "<image>",
+    "<graph>",
+    "<soft_token>",
+    "<vis_0>",
+    "<vis_1>"
+  ],
+  "bos_token": "<bos>",
+  "bos_token_id": 2,
+  "chat_template": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "eos_token_id": 3,
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "mask_token_id": 4,
+  "max_length": 256,
+  "model_input_names": [
+    "input_ids",
+    "token_type_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 32000,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_id": 0,
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "special_tokens_map": {
+    "additional_special_tokens": [
+      "<pad>",
+      "<unk>",
+      "<bos>",
+      "<eos>",
+      "<mask>",
+      "<user>",
+      "<assistant>",
+      "<system>",
+      "<image>",
+      "<graph>",
+      "<soft_token>",
+      "<vis_0>",
+      "<vis_1>"
+    ],
+    "bos_token": "<bos>",
+    "eos_token": "<eos>",
+    "mask_token": "<mask>",
+    "pad_token": "<pad>",
+    "unk_token": "<unk>"
+  },
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "unk_token_id": 1
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b65796bd11cacf21704d65ced17aaff7d6b567784c997fbefb6a628e49f499
+size 5713