Upload folder using huggingface_hub

README.md

@@ -0,0 +1,20 @@
+---
+license: apache-2.0
+datasets:
+- OEvortex/vortex-mini
+language:
+- en
+- hi
+library_name: transformers
+base_model: OEvortex/HelpingAI-Lite
+tags:
+- HelpingAI
+pipeline_tag: text-generation
+widget:
+- text: |
+    <|system|>
+    You are a chatbot who can be a teacher!</s>
+    <|user|>
+    Give three tips for staying healthy.</s>
+    <|assistant|>
+---

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "OEvortex/HelpingAI-Lite",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d385dfcd73c639f4d03a0b8e304425b94d59a72270fe7aac6668e443c115b3
+size 2200119664

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41212e1b85000977fdb3aa9d9f030cb2c5b893b05690b97ebe411fe27adaeff9
+size 2200164273

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>'  + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.00012304421224634436,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2e-05,
+      "loss": 1.3413,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4e-05,
+      "loss": 2.5983,
+      "step": 2
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6e-05,
+      "loss": 1.5431,
+      "step": 3
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 1.7992,
+      "step": 4
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001,
+      "loss": 1.2091,
+      "step": 5
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 2.7719,
+      "step": 6
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 3.317,
+      "step": 7
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014,
+      "loss": 1.1447,
+      "step": 8
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016,
+      "loss": 1.4177,
+      "step": 9
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018,
+      "loss": 1.851,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0002,
+      "loss": 1.9526,
+      "step": 11
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.7479,
+      "step": 12
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.3683,
+      "step": 13
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.527,
+      "step": 14
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.01,
+      "step": 15
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2848,
+      "step": 16
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2189,
+      "step": 17
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.4882,
+      "step": 18
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.5045,
+      "step": 19
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.454,
+      "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2887,
+      "step": 21
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.8272,
+      "step": 22
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.6697,
+      "step": 23
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6019,
+      "step": 24
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0745,
+      "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "eval_loss": NaN,
+      "eval_runtime": 4150.2492,
+      "eval_samples_per_second": 11.575,
+      "eval_steps_per_second": 11.575,
+      "step": 25
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 183123718963200.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35287ef26a7dfcc015e0237824a0fa49982706609ab72610ad14222df433fe99
+size 4859