commit f8993f2f22e66a9e7c7b68f50ec3048a575de56c Author: ModelHub XC Date: Thu May 14 19:19:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: benchang1110/Taiwan-tinyllama-v1.1-base Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5c59dd0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +image.png filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1c7bb21 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: +- TinyLlama/TinyLlama_v1.1 +datasets: +- benchang1110/Taiwan-pretrain-9B +- benchang1110/Taiwan-book-1B +language: +- zh +library_name: transformers +license: apache-2.0 +--- + +# Model Card for Model ID + +![image](image.png) +This is a continue-pretrained version of [Tinyllama-v1.1](TinyLlama/TinyLlama_v1.1) tailored for traditional Chinese. The continue-pretraining dataset contains over 10B tokens. Using bfloat16, the VRAM required during inference is only around 3GB!!! + +# Usage +**This is a causal language model not a chat model !** It is not designed to generate human-like responses. It is designed to generate text based on previous text. + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig +import torch +from transformers import TextStreamer + +def generate_response(input): + ''' + simple test for the model + ''' + # tokenzize the input + tokenized_input = tokenizer.encode_plus(input, return_tensors='pt').to(device) + print(tokenized_input['input_ids']) + # generate the response + _ = model.generate( + input_ids=tokenized_input['input_ids'], + attention_mask=tokenized_input['attention_mask'], + pad_token_id=tokenizer.pad_token_id, + do_sample=True, + repetition_penalty=1.0, + max_length=2048, + streamer=streamer, + ) + + +if __name__ == '__main__': + device = 'cuda' if torch.cuda.is_available() else 'cpu' + model = AutoModelForCausalLM.from_pretrained("benchang1110/Taiwan-tinyllama-v1.1-base",attn_implementation="flash_attention_2",device_map=device,torch_dtype=torch.bfloat16) + tokenizer = AutoTokenizer.from_pretrained("benchang1110/Taiwan-tinyllama-v1.1-base",use_fast=True) + streamer = TextStreamer(tokenizer) + while(True): + text = input("input a simple prompt:") + generate_response(text) +``` + +### Training Procedure + +The following training hyperparameters are used: + +| Data size | Global Batch Size | Learning Rate | Epochs | Max Length | Weight Decay | +|--------------|-------------------|---------------|--------|------------|--------------| +| 10B | 32 | 5e-5 | 1 | 2048 | 1e-4 | + +![loss](loss.png) +### Compute Infrastructure +1xA100(80GB), took approximately 200 GPU hours. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..49be037 --- /dev/null +++ b/config.json @@ -0,0 +1,30 @@ +{ + "_name_or_path": "./checkpoint/checkpoint-80000", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 2048, + "mlp_bias": false, + "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": "bfloat16", + "transformers_version": "4.48.0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..eeb5afd --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "attn_implementation": "flash_attention_2", + "bos_token_id": 1, + "eos_token_id": 2, + "max_length": 2048, + "pad_token_id": 0, + "transformers_version": "4.48.0" +} diff --git a/image.png b/image.png new file mode 100644 index 0000000..1a38c32 --- /dev/null +++ b/image.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05b2d7eb99135708832e0a691e8c870baec69df74cd83594df360730fbc8e45c +size 8487229 diff --git a/loss.png b/loss.png new file mode 100644 index 0000000..19b3de5 Binary files /dev/null and b/loss.png differ diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..21437fd --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b442eb620531d6568e291458cf5fa7dd4b55a342d6ead6a0279b2378e3c3b77 +size 2200119864 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..e6b9de8 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": {}, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": false +}