Upload checkpoint

config.json

@@ -0,0 +1,22 @@
+{
+ "architectures": [
+ "LlamaForCausalLM"
+ ],
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "hidden_act": "silu",
+ "hidden_size": 512,
+ "initializer_range": 0.02,
+ "intermediate_size": 1024,
+ "max_position_embeddings": 256,
+ "model_type": "llama",
+ "num_attention_heads": 8,
+ "num_hidden_layers": 16,
+ "pad_token_id": 0,
+ "rms_norm_eps": 1e-06,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.29.1",
+ "use_cache": true,
+ "vocab_size": 16000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "eos_token_id": 2,
+ "pad_token_id": 0,
+ "transformers_version": "4.29.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e70f468fa96d3315408eb500704ecab718cc4d2afeb44acdd9e4389fec53ab
+size 233432542

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+ "bos_token": "<s>",
+ "eos_token": "</s>",
+ "pad_token": "<pad>",
+ "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+ "add_prefix_space": false,
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 128,
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87eba57770d6a732b822fe5b995d45644035322d2cc476b45c94d7d50b111e86
+size 4288