From ef5f08a51c55f879fa387168625c0936230b9353 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Fri, 13 Sep 2024 00:04:26 +0800 Subject: [PATCH] Upload deepseek-coder-6.7B-kexer.Q2_K.gguf with huggingface_hub --- .gitattributes | 38 ++++++---- README.md | 103 ++++++++++++++++---------- configuration.json | 1 + deepseek-coder-6.7B-kexer.Q2_K.gguf | 3 + deepseek-coder-6.7B-kexer.Q3_K_L.gguf | 3 + deepseek-coder-6.7B-kexer.Q3_K_M.gguf | 3 + deepseek-coder-6.7B-kexer.Q3_K_S.gguf | 3 + deepseek-coder-6.7B-kexer.Q4_0.gguf | 3 + deepseek-coder-6.7B-kexer.Q4_1.gguf | 3 + deepseek-coder-6.7B-kexer.Q4_K_M.gguf | 3 + deepseek-coder-6.7B-kexer.Q4_K_S.gguf | 3 + deepseek-coder-6.7B-kexer.Q5_0.gguf | 3 + deepseek-coder-6.7B-kexer.Q5_1.gguf | 3 + deepseek-coder-6.7B-kexer.Q5_K_M.gguf | 3 + deepseek-coder-6.7B-kexer.Q5_K_S.gguf | 3 + deepseek-coder-6.7B-kexer.Q6_K.gguf | 3 + deepseek-coder-6.7B-kexer.Q8_0.gguf | 3 + 17 files changed, 130 insertions(+), 54 deletions(-) create mode 100644 configuration.json create mode 100644 deepseek-coder-6.7B-kexer.Q2_K.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q3_K_L.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q3_K_M.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q3_K_S.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q4_0.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q4_1.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q4_K_M.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q4_K_S.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q5_0.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q5_1.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q5_K_M.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q5_K_S.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q6_K.gguf create mode 100644 deepseek-coder-6.7B-kexer.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes index b7e9e3a..452849f 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-coder-6.7B-kexer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +deepseek-coder-6.7B-kexer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 29c15f6..5e7bee7 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,68 @@ --- -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: apache-2.0 +datasets: +- JetBrains/KExercises +base_model: JetBrains/deepseek-coder-6.7B-kexer +results: +- task: + type: text-generation + dataset: + name: MultiPL-HumanEval (Kotlin) + type: openai_humaneval + metrics: + - name: pass@1 + type: pass@1 + value: 55.28 +tags: +- code +library_name: transformers +pipeline_tag: text-generation --- -### 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 +# Deepseek-Coder-6.7B-kexer-GGUF +This is quantized version of [JetBrains/deepseek-coder-6.7B-kexer](https://huggingface.co/JetBrains/deepseek-coder-6.7B-kexer) created using llama.cpp + +# Kexer models + +Kexer models are a collection of open-source generative text models fine-tuned on the [Kotlin Exercices](https://huggingface.co/datasets/JetBrains/KExercises) dataset. +This is a repository for the fine-tuned **Deepseek-coder-6.7b** model in the *Hugging Face Transformers* format. + +# How to use + +As with the base model, we can use FIM. To do this, the following format must be used: ``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('QuantFactory/deepseek-coder-6.7B-kexer-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/QuantFactory/deepseek-coder-6.7B-kexer-GGUF.git +'<｜fim▁begin｜>' + prefix + '<｜fim▁hole｜>' + suffix + '<｜fim▁end｜>' ``` -

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 +# Training setup + +The model was trained on one A100 GPU with following hyperparameters: + +| **Hyperparameter** | **Value** | +|:---------------------------:|:----------------------------------------:| +| `warmup` | 10% | +| `max_lr` | 1e-4 | +| `scheduler` | linear | +| `total_batch_size` | 256 (~130K tokens per step) | +| `num_epochs` | 4 | + +More details about fine-tuning can be found in the technical report (coming soon!). + +# Fine-tuning data + +For tuning this model, we used 15K exmaples from the synthetically generated [Kotlin Exercices](https://huggingface.co/datasets/JetBrains/KExercises) dataset. Every example follows the HumanEval format. In total, the dataset contains about 3.5M tokens. + +# Evaluation + +For evaluation, we used the [Kotlin HumanEval](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval) dataset, which contains all 161 tasks from HumanEval translated into Kotlin by human experts. You can find more details about the pre-processing necessary to obtain our results, including the code for running, on the [datasets's page](https://huggingface.co/datasets/JetBrains/Kotlin_HumanEval). + +Here are the results of our evaluation: + +| **Model name** | **Kotlin HumanEval Pass Rate** | +|:---------------------------:|:----------------------------------------:| +| `Deepseek-coder-6.7B` | 40.99 | +| `Deepseek-coder-6.7B-kexer` | **55.28** | + +# Ethical considerations and limitations + +Deepseek-coder-6.7B-kexer is a new technology that carries risks with use. The testing conducted to date has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Deepseek-coder-6.7B-kexer's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. The model was fine-tuned on a specific data format (Kotlin tasks), and deviation from this format can also lead to inaccurate or undesirable responses to user queries. Therefore, before deploying any applications of Deepseek-coder-6.7B-kexer, developers should perform safety testing and tuning tailored to their specific applications of the model. \ 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-coder-6.7B-kexer.Q2_K.gguf b/deepseek-coder-6.7B-kexer.Q2_K.gguf new file mode 100644 index 0000000..876f5af --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4db04090300556f0c9bf7a9e16acc8a4b995f96e9b2ebf35e03e0947d672d419 +size 2534500256 diff --git a/deepseek-coder-6.7B-kexer.Q3_K_L.gguf b/deepseek-coder-6.7B-kexer.Q3_K_L.gguf new file mode 100644 index 0000000..8a07053 --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbe1cd2cf018458e05365963a56874a298101ed05f3190238f4826edce1bb9ba +size 3598854048 diff --git a/deepseek-coder-6.7B-kexer.Q3_K_M.gguf b/deepseek-coder-6.7B-kexer.Q3_K_M.gguf new file mode 100644 index 0000000..3a2d6da --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d9b4e45b1cf7b9daf031fd42cbfb15eb04fa3746932d2e131bf4237c6a2462 +size 3299747744 diff --git a/deepseek-coder-6.7B-kexer.Q3_K_S.gguf b/deepseek-coder-6.7B-kexer.Q3_K_S.gguf new file mode 100644 index 0000000..a10336a --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3336ebd9207d4a5a5b898ec4b267937fb1943f43b2936131c7d8f37913d7700c +size 2950047648 diff --git a/deepseek-coder-6.7B-kexer.Q4_0.gguf b/deepseek-coder-6.7B-kexer.Q4_0.gguf new file mode 100644 index 0000000..9aa1947 --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796c6fed4d44e299b65caa0fd102416154980614d8012e13eb800090f8633a6f +size 3827689376 diff --git a/deepseek-coder-6.7B-kexer.Q4_1.gguf b/deepseek-coder-6.7B-kexer.Q4_1.gguf new file mode 100644 index 0000000..dd5f28d --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93bc34f02ee2a05ba3ce0fe375ec88e318e1017c58bc21d93a3b0b4cd607a729 +size 4240697248 diff --git a/deepseek-coder-6.7B-kexer.Q4_K_M.gguf b/deepseek-coder-6.7B-kexer.Q4_K_M.gguf new file mode 100644 index 0000000..c3870ec --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e47428509b77a2a2624b79923e897638aae83e210f60c2081beeef90851bd5 +size 4082886560 diff --git a/deepseek-coder-6.7B-kexer.Q4_K_S.gguf b/deepseek-coder-6.7B-kexer.Q4_K_S.gguf new file mode 100644 index 0000000..24d9afe --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074042e7269fd1d0568ebf5177bfe7b387b50c5731353e4930692e514889c440 +size 3858622368 diff --git a/deepseek-coder-6.7B-kexer.Q5_0.gguf b/deepseek-coder-6.7B-kexer.Q5_0.gguf new file mode 100644 index 0000000..c97484d --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdda4575b1a1fe024d2975163fb94a19e7e02d03f461f774f86ce2cf2de3931 +size 4653705120 diff --git a/deepseek-coder-6.7B-kexer.Q5_1.gguf b/deepseek-coder-6.7B-kexer.Q5_1.gguf new file mode 100644 index 0000000..f14cbc3 --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0999ca0bd1a7cbb280647d432c7db61a4509b79b07ed7c2ed94ffc7a0a71f8a0 +size 5066712992 diff --git a/deepseek-coder-6.7B-kexer.Q5_K_M.gguf b/deepseek-coder-6.7B-kexer.Q5_K_M.gguf new file mode 100644 index 0000000..1dc285d --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce132debfed4911d0db1181f84f972dddf089dff3b781b95ef19f0d6850d38f5 +size 4785170336 diff --git a/deepseek-coder-6.7B-kexer.Q5_K_S.gguf b/deepseek-coder-6.7B-kexer.Q5_K_S.gguf new file mode 100644 index 0000000..7f725a4 --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63abf86af2f190c073854d749dd5f2b87d91e65abb1963de92e471ad02f3654f +size 4653705120 diff --git a/deepseek-coder-6.7B-kexer.Q6_K.gguf b/deepseek-coder-6.7B-kexer.Q6_K.gguf new file mode 100644 index 0000000..e0a8e2c --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88493083350cc9c85c2386e459e058cd77cf7a4ecfefcc8ccb3680f436e910fe +size 5531346848 diff --git a/deepseek-coder-6.7B-kexer.Q8_0.gguf b/deepseek-coder-6.7B-kexer.Q8_0.gguf new file mode 100644 index 0000000..c7df24d --- /dev/null +++ b/deepseek-coder-6.7B-kexer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659673ae84a20b7fdbec8961687dfc311dd0a9d2980f61dcf3bdde3d3a7f1621 +size 7163750304