From fc4ca7307e7d51f80194d9c99a24885edf0d7a64 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 16 Sep 2026 14:28:12 +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: cortexso/qwen2 Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++++++++++++++++ README.md | 40 +++++++++++++++++++++++++++++ configuration.json | 1 + metadata.yml | 5 ++++ model.yml | 17 +++++++++++++ qwen2-7b-instruct-q2_k.gguf | 3 +++ qwen2-7b-instruct-q3_k_l.gguf | 3 +++ qwen2-7b-instruct-q3_k_m.gguf | 3 +++ qwen2-7b-instruct-q3_k_s.gguf | 3 +++ qwen2-7b-instruct-q4_k_m.gguf | 3 +++ qwen2-7b-instruct-q4_k_s.gguf | 3 +++ qwen2-7b-instruct-q5_k_m.gguf | 3 +++ qwen2-7b-instruct-q5_k_s.gguf | 3 +++ qwen2-7b-instruct-q6_k.gguf | 3 +++ qwen2-7b-instruct-q8_0.gguf | 3 +++ 15 files changed, 140 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 configuration.json create mode 100644 metadata.yml create mode 100644 model.yml create mode 100644 qwen2-7b-instruct-q2_k.gguf create mode 100644 qwen2-7b-instruct-q3_k_l.gguf create mode 100644 qwen2-7b-instruct-q3_k_m.gguf create mode 100644 qwen2-7b-instruct-q3_k_s.gguf create mode 100644 qwen2-7b-instruct-q4_k_m.gguf create mode 100644 qwen2-7b-instruct-q4_k_s.gguf create mode 100644 qwen2-7b-instruct-q5_k_m.gguf create mode 100644 qwen2-7b-instruct-q5_k_s.gguf create mode 100644 qwen2-7b-instruct-q6_k.gguf create mode 100644 qwen2-7b-instruct-q8_0.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +*.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 +*.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 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f4c3f72 --- /dev/null +++ b/README.md @@ -0,0 +1,40 @@ +--- +license: other +license_name: tongyi-qianwen +license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE +pipeline_tag: text-generation +tags: +- cortex.cpp +--- + +## Overview + +Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 72B Qwen2 model. + +## Variants + +| No | Variant | Cortex CLI command | +| --- | --- | --- | +| 1 | [Qwen2-7b](https://huggingface.co/cortexso/qwen2/tree/7b) | `cortex run qwen2:7b` | + +## Use it with Jan (UI) + +1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) +2. Use in Jan model Hub: + ```bash + cortexhub/qwen2 + ``` + +## Use it with Cortex (CLI) + +1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) +2. Run the model with command: + ```bash + cortex run qwen2 + ``` + +## Credits + +- **Author:** Qwen +- **Converter:** [Homebrew](https://www.homebrew.ltd/) +- **Original License:** [Licence](https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE) \ 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/metadata.yml b/metadata.yml new file mode 100644 index 0000000..323ffab --- /dev/null +++ b/metadata.yml @@ -0,0 +1,5 @@ +# metadata.yml +version: 1 +name: qwen2 +default: 7b +author: "Qwen" \ No newline at end of file diff --git a/model.yml b/model.yml new file mode 100644 index 0000000..c933d61 --- /dev/null +++ b/model.yml @@ -0,0 +1,17 @@ +name: qwen2 +model: qwen2:7B +version: 1 + +# Results Preferences +top_p: 0.95 +temperature: 0.7 +frequency_penalty: 0 +presence_penalty: 0 +max_tokens: 4096 # Infer from base config.json -> max_position_embeddings +stream: true # true | false + +# Engine / Model Settings +ngl: 33 # Infer from base config.json -> num_attention_heads +ctx_len: 4096 # Infer from base config.json -> max_position_embeddings +engine: llama-cpp +prompt_template: "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant" diff --git a/qwen2-7b-instruct-q2_k.gguf b/qwen2-7b-instruct-q2_k.gguf new file mode 100644 index 0000000..eef2ff7 --- /dev/null +++ b/qwen2-7b-instruct-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5abea67cb916e475b873318c6b8bb921eca8c3d64bcf29c0ab978c2f0d4864 +size 3015938016 diff --git a/qwen2-7b-instruct-q3_k_l.gguf b/qwen2-7b-instruct-q3_k_l.gguf new file mode 100644 index 0000000..66d82a3 --- /dev/null +++ b/qwen2-7b-instruct-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14939c3944324ab3e619e82be88de177d436cb772c58ea82c91c7915a8bd57c +size 4088457184 diff --git a/qwen2-7b-instruct-q3_k_m.gguf b/qwen2-7b-instruct-q3_k_m.gguf new file mode 100644 index 0000000..effecc9 --- /dev/null +++ b/qwen2-7b-instruct-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e62707f8b22c1a14311b3dd5d6127354ab8be78ba86f9a3e0130a922f7169be0 +size 3808389088 diff --git a/qwen2-7b-instruct-q3_k_s.gguf b/qwen2-7b-instruct-q3_k_s.gguf new file mode 100644 index 0000000..3a808b5 --- /dev/null +++ b/qwen2-7b-instruct-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a598c6910ded80c350b988c0a602e2c1236d981e62dd7968e3e53f052957be0b +size 3492366304 diff --git a/qwen2-7b-instruct-q4_k_m.gguf b/qwen2-7b-instruct-q4_k_m.gguf new file mode 100644 index 0000000..361ae73 --- /dev/null +++ b/qwen2-7b-instruct-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25467f3f8d092e51e6a1ae669cf16ef58f12e38555de2ce017b3ecde07ef9b5f +size 4683071456 diff --git a/qwen2-7b-instruct-q4_k_s.gguf b/qwen2-7b-instruct-q4_k_s.gguf new file mode 100644 index 0000000..9fcf585 --- /dev/null +++ b/qwen2-7b-instruct-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5964cc3ef2746dd492a409f0a8964922c4b5c685eb0fce5716c2f61ac62ed93 +size 4457766880 diff --git a/qwen2-7b-instruct-q5_k_m.gguf b/qwen2-7b-instruct-q5_k_m.gguf new file mode 100644 index 0000000..7de958d --- /dev/null +++ b/qwen2-7b-instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:326ca2b41c6b695fc7c29d99ed50b9e55a4e766b4e3164ad4d9bc7041f4591ae +size 5444829152 diff --git a/qwen2-7b-instruct-q5_k_s.gguf b/qwen2-7b-instruct-q5_k_s.gguf new file mode 100644 index 0000000..b12014d --- /dev/null +++ b/qwen2-7b-instruct-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70038070d33cce658f03b14fc0778bb14ad4947fc624ed418fca5abaf0f9c610 +size 5315174368 diff --git a/qwen2-7b-instruct-q6_k.gguf b/qwen2-7b-instruct-q6_k.gguf new file mode 100644 index 0000000..07f992e --- /dev/null +++ b/qwen2-7b-instruct-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7674fe2716418744be2772890fa25bbf43decea3a3491f2dc0a489f21a6812 +size 6254196704 diff --git a/qwen2-7b-instruct-q8_0.gguf b/qwen2-7b-instruct-q8_0.gguf new file mode 100644 index 0000000..a2108b2 --- /dev/null +++ b/qwen2-7b-instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f43ac62a14e71aefec9bc6f62df1b25aa7bb7385ad5cd6d6edc4cd9f9acfe3 +size 8098523104