commit 430233e48a5fc90589ce8114935f27e10c2e49ec Author: ModelHub XC Date: Mon Jul 6 19:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ORANSight_Qwen_7B_Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..492726f --- /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 +*.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 +ORANSight_Qwen_7B_Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ORANSight_Qwen_7B_Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ORANSight_Qwen_7B_Instruct.IQ4_XS.gguf b/ORANSight_Qwen_7B_Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..be046c8 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e583b3d82f445666db066805ba539b9f2f0a24f67f06cb16707f88ccce4495cd +size 4250299328 diff --git a/ORANSight_Qwen_7B_Instruct.Q2_K.gguf b/ORANSight_Qwen_7B_Instruct.Q2_K.gguf new file mode 100644 index 0000000..5c60182 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee9321ec8f7c76a33a4eb840a0ce414fba26a757b0cf9f50d4e1f9d449c560e +size 3015941056 diff --git a/ORANSight_Qwen_7B_Instruct.Q3_K_L.gguf b/ORANSight_Qwen_7B_Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..57ea190 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2f633e04ea44669839568ec3142a418154be672dea7516db1eaecc21f38240 +size 4088460224 diff --git a/ORANSight_Qwen_7B_Instruct.Q3_K_M.gguf b/ORANSight_Qwen_7B_Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..def8172 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7d170ae977f1546c48294f3c0681879a19886e6d234211a11515ab6c61d781a +size 3808392128 diff --git a/ORANSight_Qwen_7B_Instruct.Q3_K_S.gguf b/ORANSight_Qwen_7B_Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..e0afaf1 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22de3fe5d4b786d46cdb52cc82cd90f1a7650d4ef333473377b532eb3f505df +size 3492369344 diff --git a/ORANSight_Qwen_7B_Instruct.Q4_K_M.gguf b/ORANSight_Qwen_7B_Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7af62c0 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295527ec937690b1020c271fa93e86776e6add6f563adb44f0c8f1819a4c74cb +size 4683074496 diff --git a/ORANSight_Qwen_7B_Instruct.Q4_K_S.gguf b/ORANSight_Qwen_7B_Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..2dca0ed --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4e965bb1be958e60a7809064f377f3744c8781d1db52232cc4811392188872c +size 4457769920 diff --git a/ORANSight_Qwen_7B_Instruct.Q5_K_M.gguf b/ORANSight_Qwen_7B_Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..36c460d --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec9c855367020b8ecf489a3892fbad100f60fe665b2b880afab999f9d0610e0 +size 5444832192 diff --git a/ORANSight_Qwen_7B_Instruct.Q5_K_S.gguf b/ORANSight_Qwen_7B_Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..02185dc --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9874c0f6409809f338ed5bcc424323c4272cc836434d312667414738e71389b3 +size 5315177408 diff --git a/ORANSight_Qwen_7B_Instruct.Q6_K.gguf b/ORANSight_Qwen_7B_Instruct.Q6_K.gguf new file mode 100644 index 0000000..b92d54d --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c6ed1c906b8f201d470b9bc4ed08469239c6545443875abe73d6ce17e64b9f +size 6254199744 diff --git a/ORANSight_Qwen_7B_Instruct.Q8_0.gguf b/ORANSight_Qwen_7B_Instruct.Q8_0.gguf new file mode 100644 index 0000000..8718483 --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf26482f9197a90f09fad749138f910f5a0a08b380e5d6308df620637a01048 +size 8098526144 diff --git a/ORANSight_Qwen_7B_Instruct.f16.gguf b/ORANSight_Qwen_7B_Instruct.f16.gguf new file mode 100644 index 0000000..786001e --- /dev/null +++ b/ORANSight_Qwen_7B_Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a703a6b3687a1ffe4d44ffbb07e341aafbb1374db4f4cfa43cf079ab2a612170 +size 15237854144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7c173d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: NextGLab/ORANSight_Qwen_7B_Instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/NextGLab/ORANSight_Qwen_7B_Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ORANSight_Qwen_7B_Instruct-GGUF/resolve/main/ORANSight_Qwen_7B_Instruct.f16.gguf) | f16 | 15.3 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +