init

README.md

@@ -0,0 +1,70 @@
+---
+license: apache-2.0
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+language:
+- en
+---
+<div align="center">
+
+# TinyLlama-1.1B
+</div>
+
+https://github.com/jzhang38/TinyLlama
+
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+
+<div align="center">
+  <img src="./TinyLlama_logo.png" width="300"/>
+</div>
+
+We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+
+#### This Model
+This is an intermediate checkpoint with 50K steps and 105B tokens.
+
+#### Releases Schedule
+We will be rolling out intermediate checkpoints following the below schedule. We also include some baseline models for comparison.
+
+| Date       | HF Checkpoint                                   | Tokens | Step | HellaSwag Acc_norm |
+|------------|-------------------------------------------------|--------|------|---------------------|
+| Baseline   | [StableLM-Alpha-3B](https://huggingface.co/stabilityai/stablelm-base-alpha-3b)| 800B   | --   |  38.31            |
+| Baseline   | [Pythia-1B-intermediate-step-50k-105b](https://huggingface.co/EleutherAI/pythia-1b/tree/step50000)             | 105B   | 50k   |  42.04            |
+| Baseline   | [Pythia-1B](https://huggingface.co/EleutherAI/pythia-1b)             | 300B   | 143k   |  47.16            |
+| 2023-09-04 | [TinyLlama-1.1B-intermediate-step-50k-105b](https://huggingface.co/PY007/TinyLlama-1.1B-step-50K-105b) | 105B   | 50k   |  43.50               |
+| 2023-09-16 | --                                             | 500B   | --   |  --               |
+| 2023-10-01 | --                                             | 1T     | --   |  --               |
+| 2023-10-16 | --                                             | 1.5T   | --   |  --               |
+| 2023-10-31 | --                                             | 2T     | --   |  --               |
+| 2023-11-15 | --                                             | 2.5T   | --   |  --               |
+| 2023-12-01 | --                                             | 3T     | --   |  --               |
+
+#### How to use
+You will need the transformers>=4.31
+Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
+```
+from transformers import AutoTokenizer
+import transformers 
+import torch
+model = "PY007/TinyLlama-1.1B-step-50K-105b"
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+sequences = pipeline(
+    'The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01.',
+    do_sample=True,
+    top_k=10,
+    num_return_sequences=1,
+    repetition_penalty=1.5,
+    eos_token_id=tokenizer.eos_token_id,
+    max_length=500,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "max_length": 2048,
+  "transformers_version": "4.31.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}