Add model files

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "ahxt/llama2_xs_460M_experimental",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layernorm_epsilon": 1e-05,
+  "max_position_embeddings": 1024,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.1",
+  "use_cache": false,
+  "vocab_size": 50257
+}

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": "4.34.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7096d33a443b7987f80cc809b5826e7a340841500b424fb3d64efa8ccf1bfc8c
+size 1846428918

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "#",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "\"",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "\"",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "#",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "#",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "\"",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aefbd6d3bb727e076e892ca4f59fca1e1b95f605531ce4d1345aed94d9314db
+size 4472

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "ahxt/llama2_xs_460M_experimental",
+    "data_path": "data/",
+    "project_name": "trained-model-460M",
+    "train_split": "train",
+    "valid_split": null,
+    "text_column": "text",
+    "rejected_text_column": "rejected",
+    "token": null,
+    "lr": 0.0004,
+    "epochs": 1,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_torch",
+    "scheduler": "cosine",
+    "weight_decay": 0.01,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "add_eos_token": true,
+    "block_size": 2049,
+    "use_peft": false,
+    "lora_r": 16,
+    "lora_alpha": 16,
+    "lora_dropout": 0.05,
+    "logging_steps": 50,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "auto_find_batch_size": true,
+    "fp16": false,
+    "push_to_hub": false,
+    "use_int8": true,
+    "model_max_length": 4096,
+    "repo_id": null,
+    "use_int4": false,
+    "trainer": "sft",
+    "target_modules": null,
+    "merge_adapter": true,
+    "username": null,
+    "use_flash_attention_2": false,
+    "log": "none",
+    "disable_gradient_checkpointing": false,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt"
+}