commit 69c3d1580927cf4adf16c1f585ae9c6b4cda3621 Author: ModelHub XC Date: Tue Aug 11 07:17:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: hwshhh/deepseek-merged-2 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16332c1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..3cc602a --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +--- +library_name: peft +model_name: deepseek-rjua-qa +tags: +- base_model:adapter:/root/notebook/dataset/deepseek-ai/deepseek-coder-1.3b-base +- lora +- sft +- transformers +- trl +licence: license +pipeline_tag: text-generation +base_model: /root/notebook/dataset/deepseek-ai/deepseek-coder-1.3b-base +--- + +# Model Card for deepseek-rjua-qa + +This model is a fine-tuned version of [None](https://huggingface.co/None). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + +This model was trained with SFT. + +### Framework versions + +- PEFT 0.16.0 +- TRL: 0.19.1 +- Transformers: 4.53.2 +- Pytorch: 2.6.0+metax2.33.0.5 +- Datasets: 3.6.0 +- Tokenizers: 0.21.2 + +## Citations + + + +Cite TRL as: + +```bibtex +@misc{vonwerra2022trl, + title = {{TRL: Transformer Reinforcement Learning}}, + author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, + year = 2020, + journal = {GitHub repository}, + publisher = {GitHub}, + howpublished = {\url{https://github.com/huggingface/trl}} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..b0b16c1 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 32013, + "eos_token_id": 32014, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5504, + "max_position_embeddings": 16384, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 16, + "num_hidden_layers": 24, + "num_key_value_heads": 16, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "rope_type": "linear", + "type": "linear" + }, + "rope_theta": 100000, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.53.2", + "use_cache": true, + "vocab_size": 32256 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..3fc809d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"other"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b7a604d --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 32013, + "eos_token_id": 32014, + "transformers_version": "4.53.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..ffffe14 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0207866c92e3e4ae33046f8b3985e73023f93bad867cc57af44e226c4ab7061 +size 2692968904 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..5ff8f57 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5506328 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5f7a2774c1e5576f3fa3ad0862035b9b70db0368814c59ec260481fbb4b5de +size 2289811 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0fcf9ef --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "32000": { + "content": "õ", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32001": { + "content": "÷", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32002": { + "content": "Á", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32003": { + "content": "ý", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32004": { + "content": "À", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32005": { + "content": "ÿ", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32006": { + "content": "ø", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32007": { + "content": "ú", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32008": { + "content": "þ", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32009": { + "content": "ü", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32010": { + "content": "ù", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32011": { + "content": "ö", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32012": { + "content": "û", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32013": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "32014": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "32015": { + "content": "<｜fim▁hole｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32016": { + "content": "<｜fim▁begin｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32017": { + "content": "<｜fim▁end｜>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32018": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32019": { + "content": "<|User|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32020": { + "content": "<|Assistant|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + }, + "32021": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +}