Upload 9 files

LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2024 SB Intuitions.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the “Software”), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,3 +1,40 @@
----
-license: mit
----
+---
+license: mit
+datasets:
+- wikipedia
+- llm-jp/oasst1-21k-ja
+- llm-jp/oasst1-21k-en
+language:
+- ja
+- en
+---
+
+# tiny-lm
+
+This repository provides a tiny 16M parameters language model for debugging and testing purposes.
+This is created by tuning [sbintuitions/tiny-lm](https://huggingface.co/sbintuitions) with oasset1 datasets in Japanese and English.
+
+## How to use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+ 
+model = AutoModelForCausalLM.from_pretrained("sbintuitions/tiny-lm-chat", torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained("sbintuitions/tiny-lm-chat", use_fast=False)
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+prompt = tokenizer.apply_chat_template([{"role": "user", "content": "Hello!"}], add_generation_prompt=True, tokenize=False)
+print(generator(prompt, max_length=30, do_sample=True, top_k=100))
+```
+
+## Model architecture
+A 4-layer, 512-hidden-size transformer-based language model.
+
+## Training
+The model was first pre-trained on English Wikipedia and Japanese Wikipedia to optimize a traditional language modelling objective for 25B tokens.
+And then it was fine-tuned on oasst1 datasets in Japanese and English for 15 epochs.
+
+## License
+[MIT License](https://huggingface.co/sbintuitions/tiny-lm-chat/resolve/main/LICENSE)
+
+

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|assistant|>": 51201,
+  "<|system|>": 51200,
+  "<|user|>": 51202
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "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": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 51203
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f5d796774360efdda5a4ee04740fd2e09d8001d15b3c66f0d4ce4e64b96dcfb
+size 58478499

special_tokens_map.json

@@ -0,0 +1,56 @@
+{
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|assistant|>",
+    "<|user|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362dfed338d41958f7c4dcefcf997ecf7cb9a6d67b6146347d3cafd59339cc94
+size 1117982

tokenizer_config.json

@@ -0,0 +1,107 @@
+{
+  "add_prefix_space": true,
+  "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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51200": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51201": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "51202": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|system|>",
+    "<|assistant|>",
+    "<|user|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{%- for message in messages -%}\n{%- if message['role'] == 'assistant' -%}\n{{ '<|assistant|>' + message['content'] + eos_token }}\n{%- elif message['role'] == 'system' -%}\n{{ '<|system|>' + message['content'] + eos_token }}\n{%- elif message['role'] == 'user' -%}\n{{ '<|user|>' + message['content'] + eos_token }}\n{%- endif -%}\n{%- if loop.last and add_generation_prompt -%}\n{{ '<|assistant|>' }}\n{%- endif -%}\n{%- endfor -%}",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "keep_accents": true,
+  "legacy": true,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}