instruct model

config.json

@@ -0,0 +1,16 @@
+{
+  "architectures": [
+    "SakhiModel"
+  ],
+  "model_type": "sakhi",
+  "embed_dim": 2048,
+  "num_heads": 8,
+  "ff_dim": 4096,
+  "num_layers": 10,
+  "vocab_size": 64002,
+  "chunk_length": 1024,
+  "hidden_act": "swiglu",
+  "max_position_embeddings": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-5
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46115a116611e651cb1e8b9465058b682763e842da97e68edd58921d41cb64df
+size 2727550716

tokenizer/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "<|eos|>",
+    "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/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "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": "<|eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}