upload model

README.md

@@ -1,3 +1,39 @@
 ---
 license: gpl-3.0
+language:
+- en
 ---
+# NanoLM-365M-base
+
+English | [简体中文](README_zh-CN.md)
+
+## Introduction
+
+Based on [Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B), the tokenizer has been replaced with [BilingualTokenizer-8K](https://huggingface.co/Mxode/Bilingual-Tokenizer) to reduce the number of parameters. The total parameters have been reduced from 0.5B to 365M.
+
+## Details
+
+To recover some performance and facilitate fine-tuning for downstream tasks, I chose to freeze the backbone parameters and only train the embedding part after replacing the tokenizer. Training was conducted for 40,000 steps on [wikipedia-zh](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered) and [cosmopedia-100k](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia-100k).
+
+|                             |                            Value                             |
+| :-------------------------: | :----------------------------------------------------------: |
+|        Total Params         |                            365 M                             |
+|      Trainable Params       |                            < 10 M                            |
+|       Trainable Parts       |                     `model.embed_tokens`                     |
+|       Training Steps        |                            40,000                            |
+|      Training Dataset       | [wikipedia-zh](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered), [cosmopedia-100k](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia-100k) |
+|          Optimizer          |                         adamw_torch                          |
+|        Learning Rate        |                             2e-4                             |
+|        LR Scheduler         |                            cosine                            |
+|        Weight Decay         |                             0.1                              |
+|        Warm-up Ratio        |                             0.03                             |
+|         Batch Size          |                              16                              |
+| Gradient Accumulation Steps |                              1                               |
+|           Seq Len           |                             4096                             |
+|            Dtype            |                             bf16                             |
+|       Peak GPU Memory       |                           < 48 GB                            |
+|           Device            |                    NVIDIA A100-SXM4-80GB                     |
+
+
+The specific training records are as follows:
+![result](static/results.png)

README_zh-CN.md

@@ -0,0 +1,34 @@
+# NanoLM-365M-base
+
+English | [简体中文](README_zh-CN.md)
+
+## Introduction
+
+在 [Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) 的基础上，将 tokenizer 替换为了 [BilingualTokenizer-8K](https://huggingface.co/Mxode/Bilingual-Tokenizer)，以达到减小参数的目的。总参数从 0.5B 降低到了 365M。
+
+## Details
+
+为了恢复一定的性能，便于下游任务微调，替换 tokenizer 后我选择冻结主干参数，仅训练 embedding 部分，在 [wikipedia-zh](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered) 和 [cosmopedia-100k](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia-100k) 上训练了 40,000 steps。
+
+|                             |                            Value                             |
+| :-------------------------: | :----------------------------------------------------------: |
+|        Total Params         |                            365 M                             |
+|      Trainable Params       |                            < 10 M                            |
+|       Trainable Parts       |                     `model.embed_tokens`                     |
+|       Training Steps        |                            40,000                            |
+|      Training Dataset       | [wikipedia-zh](https://huggingface.co/datasets/pleisto/wikipedia-cn-20230720-filtered), [cosmopedia-100k](https://huggingface.co/datasets/HuggingFaceTB/cosmopedia-100k) |
+|          Optimizer          |                         adamw_torch                          |
+|        Learning Rate        |                             2e-4                             |
+|        LR Scheduler         |                            cosine                            |
+|        Weight Decay         |                             0.1                              |
+|        Warm-up Ratio        |                             0.03                             |
+|         Batch Size          |                              16                              |
+| Gradient Accumulation Steps |                              1                               |
+|           Seq Len           |                             4096                             |
+|            Dtype            |                             bf16                             |
+|       Peak GPU Memory       |                           < 48 GB                            |
+|           Device            |                    NVIDIA A100-SXM4-80GB                     |
+
+
+具体训练记录如下：
+![result](static/results.png)

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Mxode/NanoLM-365M-base",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 8000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 2,
+  "max_new_tokens": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f1d14eb87b662615915bfc3aaa203e5013fe9b184bbabdc41590232e62556b
+size 730164456

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,37 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}