From fff98acb030297860954260b3d7a44ca2e05ef7c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 8 Oct 2026 23:43:13 +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: DevQuasar/Qwen2-7B-Instruct-GGUF Source: Original Platform --- .gitattributes | 41 +++++++++++++++++++++++++++++ Qwen2-7B-Instruct.Q2_K.gguf | 3 +++ Qwen2-7B-Instruct.Q3_K_M.gguf | 3 +++ Qwen2-7B-Instruct.Q4_0.gguf | 3 +++ Qwen2-7B-Instruct.Q5_K_M.gguf | 3 +++ Qwen2-7B-Instruct.Q6_K.gguf | 3 +++ Qwen2-7B-Instruct.Q8_0.gguf | 3 +++ README.md | 14 ++++++++++ configuration.json | 1 + qwen2.preset.json | 49 +++++++++++++++++++++++++++++++++++ 10 files changed, 123 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2-7B-Instruct.Q2_K.gguf create mode 100644 Qwen2-7B-Instruct.Q3_K_M.gguf create mode 100644 Qwen2-7B-Instruct.Q4_0.gguf create mode 100644 Qwen2-7B-Instruct.Q5_K_M.gguf create mode 100644 Qwen2-7B-Instruct.Q6_K.gguf create mode 100644 Qwen2-7B-Instruct.Q8_0.gguf create mode 100644 README.md create mode 100644 configuration.json create mode 100644 qwen2.preset.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d8e0d67 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.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 +Qwen2-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-Instruct.Q2_K.gguf b/Qwen2-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..9805208 --- /dev/null +++ b/Qwen2-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c33a1a828e6b7b3acedd15eb8acce0eea447c7b9e2e4579cbb571c3bd6dfd01 +size 3015937600 diff --git a/Qwen2-7B-Instruct.Q3_K_M.gguf b/Qwen2-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..711f976 --- /dev/null +++ b/Qwen2-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6f0a0f0efc26df877e6c59f8e37de9bf6434244958c78f68399f3c7137250d5 +size 3808388672 diff --git a/Qwen2-7B-Instruct.Q4_0.gguf b/Qwen2-7B-Instruct.Q4_0.gguf new file mode 100644 index 0000000..f2bacff --- /dev/null +++ b/Qwen2-7B-Instruct.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822c0c2d16296d44946006a8e9f201977f66040049347fd39ab1af8ef0109fca +size 4431388224 diff --git a/Qwen2-7B-Instruct.Q5_K_M.gguf b/Qwen2-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a790cc5 --- /dev/null +++ b/Qwen2-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edcfdfba7ea24285343bce6d4b36f9c2446f5a9056b96592be3566855a705ea1 +size 5444828736 diff --git a/Qwen2-7B-Instruct.Q6_K.gguf b/Qwen2-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..017385d --- /dev/null +++ b/Qwen2-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5137b2326c7851b8a5668694603662978beeefdd35650b11ced791186eda658e +size 6254196288 diff --git a/Qwen2-7B-Instruct.Q8_0.gguf b/Qwen2-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..2167150 --- /dev/null +++ b/Qwen2-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c9bb3a081c293311e6ae3030dd9f5189c6d61f488928ae98d9f4509a10c9a88 +size 8098522688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8f7d4bf --- /dev/null +++ b/README.md @@ -0,0 +1,14 @@ +--- +license: apache-2.0 +pipeline_tag: text-generation +base_model: +- Qwen/Qwen2-7B-Instruct +--- +Quantized version of [Qwen/Qwen2-7B-Instruct](https://huggingface.co/Qwen/Qwen2-7B-Instruct) + + +I'm doing this to 'Make knowledge free for everyone', using my personal time and resources. + +If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar + +Also feel free to visit my website https://devquasar.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/qwen2.preset.json b/qwen2.preset.json new file mode 100644 index 0000000..f08f9fc --- /dev/null +++ b/qwen2.preset.json @@ -0,0 +1,49 @@ +{ + "name": "qwen2", + "load_params": { + "n_ctx": 1500, + "n_batch": 512, + "rope_freq_base": 0, + "rope_freq_scale": 0, + "n_gpu_layers": -1, + "use_mlock": true, + "main_gpu": 0, + "tensor_split": [ + 0 + ], + "seed": -1, + "f16_kv": true, + "use_mmap": true + }, + "inference_params": { + "n_threads": 4, + "n_predict": -1, + "top_k": 40, + "top_p": 0.95, + "temp": 0.1, + "repeat_penalty": 1.1, + "input_prefix": "### Instruction:\\n", + "input_suffix": "\\n### Response:\\n", + "antiprompt": [ + "### Instruction:" + ], + "pre_prompt": "", + "pre_prompt_suffix": "\\n", + "pre_prompt_prefix": "", + "seed": -1, + "tfs_z": 1, + "typical_p": 1, + "repeat_last_n": 64, + "frequency_penalty": 0, + "presence_penalty": 0, + "n_keep": 0, + "logit_bias": {}, + "mirostat": 0, + "mirostat_tau": 5, + "mirostat_eta": 0.1, + "memory_f16": true, + "multiline_input": false, + "penalize_nl": true, + "min_p": 0.05 + } +}