diff --git a/.gitattributes b/.gitattributes index b7e9e3a..e0ddac8 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,37 +1,49 @@ *.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 +*.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 -*.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 -*.safetensors 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 +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-math-7b-rl.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 20bb33e..55a5c60 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,82 @@ --- -license: Apache License 2.0 - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +license: other +license_name: deepseek +license_link: https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL +pipeline_tag: text-generation +base_model: deepseek-ai/deepseek-math-7b-rl --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` +# QuantFactory/deepseek-math-7b-rl-GGUF +This is quantized version of [deepseek-ai/deepseek-math-7b-rl](https://huggingface.co/deepseek-ai/deepseek-math-7b-rl) created using llama.cpp + +# Model Description + +

+DeepSeek Chat +

+

[🏠Homepage] | [🤖 Chat with DeepSeek LLM] | [Discord] | [Wechat(微信)]

+ +

+ Paper Link👁️ +

+ +
+ + + + + +### 1. Introduction to DeepSeekMath +See the [Introduction](https://github.com/deepseek-ai/DeepSeek-Math) for more details. + +### 2. How to Use +Here give some examples of how to use our model. + +**Chat Completion** + +❗❗❗ **Please use chain-of-thought prompt to test DeepSeekMath-Instruct and DeepSeekMath-RL:** + +- English questions: **{question}\nPlease reason step by step, and put your final answer within \\boxed{}.** + +- Chinese questions: **{question}\n请通过逐步推理来解答问题，并把最终答案放置于\\boxed{}中。** + ```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('QuantFactory/deepseek-math-7b-rl-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/QuantFactory/deepseek-math-7b-rl-GGUF.git +import torch +from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig + +model_name = "deepseek-ai/deepseek-math-7b-instruct" +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto") +model.generation_config = GenerationConfig.from_pretrained(model_name) +model.generation_config.pad_token_id = model.generation_config.eos_token_id + +messages = [ + {"role": "user", "content": "what is the integral of x^2 from 0 to 2?\nPlease reason step by step, and put your final answer within \\boxed{}."} +] +input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt") +outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100) + +result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True) +print(result) ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +Avoiding the use of the provided function `apply_chat_template`, you can also interact with our model following the sample template. Note that `messages` should be replaced by your input. + +``` +User: {messages[0]['content']} + +Assistant: {messages[1]['content']}<｜end▁of▁sentence｜>User: {messages[2]['content']} + +Assistant: +``` + +**Note:** By default (`add_special_tokens=True`), our tokenizer automatically adds a `bos_token` (`<｜begin▁of▁sentence｜>`) before the input text. Additionally, since the system prompt is not compatible with this version of our models, we DO NOT RECOMMEND including the system prompt in your input. + +### 3. License +This code repository is licensed under the MIT License. The use of DeepSeekMath models is subject to the Model License. DeepSeekMath supports commercial use. + +See the [LICENSE-MODEL](https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL) for more details. + +### 4. Contact + +If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com). \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/deepseek-math-7b-rl.Q2_K.gguf b/deepseek-math-7b-rl.Q2_K.gguf new file mode 100644 index 0000000..6152fad --- /dev/null +++ b/deepseek-math-7b-rl.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4716c91832cb273216cce50241de998502f2ce31a88752aca79175a222cb8a53 +size 3179131200 diff --git a/deepseek-math-7b-rl.Q3_K_L.gguf b/deepseek-math-7b-rl.Q3_K_L.gguf new file mode 100644 index 0000000..9ddd27b --- /dev/null +++ b/deepseek-math-7b-rl.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57539f544986ac7bf0bfcc26f2bc763614a23abb896393f9d29745d600a5844a +size 4321956160 diff --git a/deepseek-math-7b-rl.Q3_K_M.gguf b/deepseek-math-7b-rl.Q3_K_M.gguf new file mode 100644 index 0000000..a36fb45 --- /dev/null +++ b/deepseek-math-7b-rl.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf213d41cc2427318be85502ce000bfb63c3251026d0ab638daf65d23503bf2d +size 4018917696 diff --git a/deepseek-math-7b-rl.Q3_K_S.gguf b/deepseek-math-7b-rl.Q3_K_S.gguf new file mode 100644 index 0000000..4eaf13e --- /dev/null +++ b/deepseek-math-7b-rl.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113ae80bd706fda14d1dfc971b7a0c557a51960e85e9f21472ae84c95cc6c291 +size 3664499008 diff --git a/deepseek-math-7b-rl.Q4_0.gguf b/deepseek-math-7b-rl.Q4_0.gguf new file mode 100644 index 0000000..76ba905 --- /dev/null +++ b/deepseek-math-7b-rl.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199c6e42dce41b8c63c928283ddef7f96aaff042c612bead7a93b0256b9135a2 +size 4661211456 diff --git a/deepseek-math-7b-rl.Q4_1.gguf b/deepseek-math-7b-rl.Q4_1.gguf new file mode 100644 index 0000000..f5dfdb4 --- /dev/null +++ b/deepseek-math-7b-rl.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3b576343ecafd09d38d451feb0392044813ae704efd680820cb0a670c62615 +size 5130252608 diff --git a/deepseek-math-7b-rl.Q4_K_M.gguf b/deepseek-math-7b-rl.Q4_K_M.gguf new file mode 100644 index 0000000..8aa3ff1 --- /dev/null +++ b/deepseek-math-7b-rl.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510c6caa0afa89cde22688d9987b6dc555d54529771797e4ad0500408c16681a +size 4920734016 diff --git a/deepseek-math-7b-rl.Q4_K_S.gguf b/deepseek-math-7b-rl.Q4_K_S.gguf new file mode 100644 index 0000000..4868a04 --- /dev/null +++ b/deepseek-math-7b-rl.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a213713aca5f3b2b46cc00d895df04543287543198c70ae61842334e597d22bf +size 4692668736 diff --git a/deepseek-math-7b-rl.Q5_0.gguf b/deepseek-math-7b-rl.Q5_0.gguf new file mode 100644 index 0000000..62c5639 --- /dev/null +++ b/deepseek-math-7b-rl.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc78aadcfb9a65f31c19adae511bfd6be5cc7e80bbf4f1efbf8b252939b5c0aa +size 5599293760 diff --git a/deepseek-math-7b-rl.Q5_1.gguf b/deepseek-math-7b-rl.Q5_1.gguf new file mode 100644 index 0000000..478f347 --- /dev/null +++ b/deepseek-math-7b-rl.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19af84d06f4dcc06d6dd59125591f9dfcb6ea8244ef0dab4bca551316e8e06ca +size 6068334912 diff --git a/deepseek-math-7b-rl.Q5_K_M.gguf b/deepseek-math-7b-rl.Q5_K_M.gguf new file mode 100644 index 0000000..5602510 --- /dev/null +++ b/deepseek-math-7b-rl.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3421856e3da4a5174149312c0f21f71ba13baa645e30e20a20a183d0f2073556 +size 5732987200 diff --git a/deepseek-math-7b-rl.Q5_K_S.gguf b/deepseek-math-7b-rl.Q5_K_S.gguf new file mode 100644 index 0000000..ec46301 --- /dev/null +++ b/deepseek-math-7b-rl.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98d45f62b0fa59d221545fad62ee2cf99e6dae8c270e5002bbb690a8ae999c1 +size 5599293760 diff --git a/deepseek-math-7b-rl.Q6_K.gguf b/deepseek-math-7b-rl.Q6_K.gguf new file mode 100644 index 0000000..74e946f --- /dev/null +++ b/deepseek-math-7b-rl.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098ab16fd8cfbc0d6bd89bacc081010ebd7abec6b108790cc43883f7f331e065 +size 6596006208 diff --git a/deepseek-math-7b-rl.Q8_0.gguf b/deepseek-math-7b-rl.Q8_0.gguf new file mode 100644 index 0000000..d4bb127 --- /dev/null +++ b/deepseek-math-7b-rl.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab70413347cb868f24c07435233841e51d88186cc3ddf65851f0b49f305ce0f +size 8540770624