Upload 5 files

config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "TransformerForCausalLM"
+  ],
+  "model_type": "transformer",
+  "vocab_size": 5000,
+  "max_position_embeddings": 128,
+  "hidden_size": 128,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "intermediate_size": 512,
+  "hidden_act": "gelu",
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-05,
+  "use_cache": true,
+  "pad_token_id": 3,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "num_experts": 4,
+  "top_k_experts": 2
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "max_new_tokens": 100,
+  "do_sample": true,
+  "temperature": 0.7,
+  "top_k": 50,
+  "top_p": 0.95,
+  "eos_token_id": 2,
+  "pad_token_id": 3
+}

model.safetensors.index.json

@@ -0,0 +1,16 @@
+{
+  "weight_map": {
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors",
+    "lm_head.weight": "model.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,26 @@
+{
+  "version": "1.0",
+  "model": {
+    "type": "BPE",
+    "vocab": {
+      "<unk>": 0,
+      "<s>": 1,
+      "</s>": 2,
+      "<pad>": 3
+    },
+    "merges": []
+  },
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false
+  },
+  "post_processor": {
+    "type": "ByteLevel"
+  },
+  "decoder": {
+    "type": "ByteLevel"
+  },
+  "normalizer": {
+    "type": "Lowercase"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "model_max_length": 128,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "padding_side": "left",
+  "truncation_side": "right",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>"
+}