From 6902a41ad911481af7bdbeb7ee7a43f7db087abb Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 11 Jul 2026 00:28:06 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: QuantFactory/CodeLlama-7B-Kexer-GGUF Source: Original Platform --- .gitattributes | 49 +++++++++++++++++++++++++++ CodeLlama-7B-Kexer.Q2_K.gguf | 3 ++ CodeLlama-7B-Kexer.Q3_K_L.gguf | 3 ++ CodeLlama-7B-Kexer.Q3_K_M.gguf | 3 ++ CodeLlama-7B-Kexer.Q3_K_S.gguf | 3 ++ CodeLlama-7B-Kexer.Q4_0.gguf | 3 ++ CodeLlama-7B-Kexer.Q4_1.gguf | 3 ++ CodeLlama-7B-Kexer.Q4_K_M.gguf | 3 ++ CodeLlama-7B-Kexer.Q4_K_S.gguf | 3 ++ CodeLlama-7B-Kexer.Q5_0.gguf | 3 ++ CodeLlama-7B-Kexer.Q5_1.gguf | 3 ++ CodeLlama-7B-Kexer.Q5_K_M.gguf | 3 ++ CodeLlama-7B-Kexer.Q5_K_S.gguf | 3 ++ CodeLlama-7B-Kexer.Q6_K.gguf | 3 ++ CodeLlama-7B-Kexer.Q8_0.gguf | 3 ++ README.md | 60 ++++++++++++++++++++++++++++++++++ configuration.json | 1 + 17 files changed, 152 insertions(+) create mode 100644 .gitattributes create mode 100644 CodeLlama-7B-Kexer.Q2_K.gguf create mode 100644 CodeLlama-7B-Kexer.Q3_K_L.gguf create mode 100644 CodeLlama-7B-Kexer.Q3_K_M.gguf create mode 100644 CodeLlama-7B-Kexer.Q3_K_S.gguf create mode 100644 CodeLlama-7B-Kexer.Q4_0.gguf create mode 100644 CodeLlama-7B-Kexer.Q4_1.gguf create mode 100644 CodeLlama-7B-Kexer.Q4_K_M.gguf create mode 100644 CodeLlama-7B-Kexer.Q4_K_S.gguf create mode 100644 CodeLlama-7B-Kexer.Q5_0.gguf create mode 100644 CodeLlama-7B-Kexer.Q5_1.gguf create mode 100644 CodeLlama-7B-Kexer.Q5_K_M.gguf create mode 100644 CodeLlama-7B-Kexer.Q5_K_S.gguf create mode 100644 CodeLlama-7B-Kexer.Q6_K.gguf create mode 100644 CodeLlama-7B-Kexer.Q8_0.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..513a8e8 --- /dev/null +++ b/.gitattributes @@ -0,0 +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 +*.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 +CodeLlama-7B-Kexer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeLlama-7B-Kexer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeLlama-7B-Kexer.Q2_K.gguf b/CodeLlama-7B-Kexer.Q2_K.gguf new file mode 100644 index 0000000..fff7e39 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e6c052ad898cae1529a6c3f8e614c3d5eff7d1dc7270203204af507e30ec24 +size 2532939776 diff --git a/CodeLlama-7B-Kexer.Q3_K_L.gguf b/CodeLlama-7B-Kexer.Q3_K_L.gguf new file mode 100644 index 0000000..31a22f6 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ef28db4f099bb8b25bf4b4c7cf3f58fc87bb28d33fe2e14dd47aa4cccfa743 +size 3597193728 diff --git a/CodeLlama-7B-Kexer.Q3_K_M.gguf b/CodeLlama-7B-Kexer.Q3_K_M.gguf new file mode 100644 index 0000000..61723f1 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7b287d20349a206e2013b43a6d02580697e21a6c52021d9c357506c652d7810 +size 3298087424 diff --git a/CodeLlama-7B-Kexer.Q3_K_S.gguf b/CodeLlama-7B-Kexer.Q3_K_S.gguf new file mode 100644 index 0000000..b1883bd --- /dev/null +++ b/CodeLlama-7B-Kexer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b96d4d9b1a7f11df487f4fa7c7f29b84a0684479b898476af28e036059ba53 +size 2948387328 diff --git a/CodeLlama-7B-Kexer.Q4_0.gguf b/CodeLlama-7B-Kexer.Q4_0.gguf new file mode 100644 index 0000000..23a0091 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9a06cb718eb537fa0ce9c51924d3aea5cbe9e05e003a3f231108510329149f +size 3825898496 diff --git a/CodeLlama-7B-Kexer.Q4_1.gguf b/CodeLlama-7B-Kexer.Q4_1.gguf new file mode 100644 index 0000000..9e2db8e --- /dev/null +++ b/CodeLlama-7B-Kexer.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e54233abb2c339257ea565681814b45ef7c5c36c2a58ec6476519a7a5070563 +size 4238844928 diff --git a/CodeLlama-7B-Kexer.Q4_K_M.gguf b/CodeLlama-7B-Kexer.Q4_K_M.gguf new file mode 100644 index 0000000..73eeca7 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b2c16ef22da0e51d5f8649095b657b60f7b1d05346cef9adeed3a229064d35 +size 4081095680 diff --git a/CodeLlama-7B-Kexer.Q4_K_S.gguf b/CodeLlama-7B-Kexer.Q4_K_S.gguf new file mode 100644 index 0000000..a6ebc91 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f811e341a48041a669e3216b93a08ecca7c3d34be9314bd2f0a53dfdfa434a5 +size 3856831488 diff --git a/CodeLlama-7B-Kexer.Q5_0.gguf b/CodeLlama-7B-Kexer.Q5_0.gguf new file mode 100644 index 0000000..6843e60 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2374193b56d347f315f8c16e82da82e79aa6982853fd0cb4bd2c452600b29b58 +size 4651791360 diff --git a/CodeLlama-7B-Kexer.Q5_1.gguf b/CodeLlama-7B-Kexer.Q5_1.gguf new file mode 100644 index 0000000..9453b73 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d31d7118bfcf6606e3ce0ac2f569d6ce75a343bedd48e393b3d45278ff6975 +size 5064737792 diff --git a/CodeLlama-7B-Kexer.Q5_K_M.gguf b/CodeLlama-7B-Kexer.Q5_K_M.gguf new file mode 100644 index 0000000..c0cbe3b --- /dev/null +++ b/CodeLlama-7B-Kexer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33fdc13f54f9956057c13aa50937e9b6964416b4e10346627dfd47cfa37da35 +size 4783256576 diff --git a/CodeLlama-7B-Kexer.Q5_K_S.gguf b/CodeLlama-7B-Kexer.Q5_K_S.gguf new file mode 100644 index 0000000..4345e8f --- /dev/null +++ b/CodeLlama-7B-Kexer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f4f26aa56468a58a3a5dbfff3a62c2d0fa2489b0e36a0fa2959f866afe48f66 +size 4651791360 diff --git a/CodeLlama-7B-Kexer.Q6_K.gguf b/CodeLlama-7B-Kexer.Q6_K.gguf new file mode 100644 index 0000000..7029d3c --- /dev/null +++ b/CodeLlama-7B-Kexer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae8eec01c193b5b14927125538b064f5be3023d1139ebf40cfc2947d378c18b +size 5529302528 diff --git a/CodeLlama-7B-Kexer.Q8_0.gguf b/CodeLlama-7B-Kexer.Q8_0.gguf new file mode 100644 index 0000000..3628f15 --- /dev/null +++ b/CodeLlama-7B-Kexer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a1d2c148c5be84f873ee1c8589c57a3e747b36ee8424fe898fe8b26879316e +size 7161229824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0043e6 --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +license: apache-2.0 +datasets: +- JetBrains/KExercises +base_model: JetBrains/CodeLlama-7B-Kexer +results: +- task: + type: text-generation + dataset: + name: MultiPL-HumanEval (Kotlin) + type: openai_humaneval + metrics: + - name: pass@1 + type: pass@1 + value: 42.24 +tags: +- code +--- + +# CodeLlama-7B-Kexer-GGUF +This is quantized version of [JetBrains/CodeLlama-7B-Kexer](https://huggingface.co/JetBrains/CodeLlama-7B-Kexer) created using llama.cpp + +# Model Description + +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 **CodeLlama-7b** model in the *Hugging Face Transformers* format. + + +# Training setup + +The model was trained on one A100 GPU with the 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** | +|:---------------------------:|:----------------------------------------:| +| `CodeLlama-7B` | 26.89 | +| `CodeLlama-7B-Kexer` | **42.24** | + +# Ethical considerations and limitations + +CodeLlama-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, CodeLlama-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 CodeLlama-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..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file