commit e3ef7c70b971659e93bd6bf6cc67326288370134 Author: ModelHub XC Date: Tue Jun 16 02:41:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Tom-Qwen-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..39e0c1e --- /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 +Tom-Qwen-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Tom-Qwen-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c72b3f --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: theprint/Tom-Qwen-7B-Instruct +datasets: +- theprint/Tom-4.2k-alpaca +language: en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- lora +- sft +- transformers +- trl +- unsloth +- fine-tuned +--- +## About + + + + + + +static quants of https://huggingface.co/theprint/Tom-Qwen-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Tom-Qwen-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Tom-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/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-Qwen-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Tom-Qwen-7B-Instruct-GGUF/resolve/main/Tom-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. + + diff --git a/Tom-Qwen-7B-Instruct.IQ4_XS.gguf b/Tom-Qwen-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..4093c68 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457c896c922ac1eb8d958f99acab201ee0a10f301594d04c8eea06ab87619572 +size 4250299520 diff --git a/Tom-Qwen-7B-Instruct.Q2_K.gguf b/Tom-Qwen-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..7ce2750 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afde61c3b9c8946c69f975649750d5558dc17bf487d77915c4fadca7cce2258 +size 3015941248 diff --git a/Tom-Qwen-7B-Instruct.Q3_K_L.gguf b/Tom-Qwen-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..152962e --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8299337f38f2f2444f8dfb9de4b1b6c787f19ad68dbc5ea181b149c68e93f331 +size 4088460416 diff --git a/Tom-Qwen-7B-Instruct.Q3_K_M.gguf b/Tom-Qwen-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..80bf7b9 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fdbfa072cec00e48acbe56b5fc92f687bbafb123a2b9d0d78c1bbf2ffdfb2ba +size 3808392320 diff --git a/Tom-Qwen-7B-Instruct.Q3_K_S.gguf b/Tom-Qwen-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c5558bb --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f061836d55d5e809695037f93c4af8760ddd1410898fcb6deec0f9f64af83ac +size 3492369536 diff --git a/Tom-Qwen-7B-Instruct.Q4_K_M.gguf b/Tom-Qwen-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..614489e --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:053ce92ab95a5d5bba8d35d5a18741b452fd7681af1e8455e6b917a0b1d475d0 +size 4683074688 diff --git a/Tom-Qwen-7B-Instruct.Q4_K_S.gguf b/Tom-Qwen-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..53dbb9c --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae755f8f3ae4e1a912939927bbed7385caa7610bc45d3993b18a7e224a6115ee +size 4457770112 diff --git a/Tom-Qwen-7B-Instruct.Q5_K_M.gguf b/Tom-Qwen-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..62990e1 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d166decf803583adf67d536c99f012fb51015c981108bc4a9861af3e29e3d10 +size 5444832384 diff --git a/Tom-Qwen-7B-Instruct.Q5_K_S.gguf b/Tom-Qwen-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1f34239 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100400303f16197bbcd53e90f58f6313d2d9f7bca2f60450696a6ef213b6f64f +size 5315177600 diff --git a/Tom-Qwen-7B-Instruct.Q6_K.gguf b/Tom-Qwen-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c5775c1 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f155a67f31f27c69a9634d58e3c24eca99dea1126b7ece72ae3e5a4c7fc531 +size 6254199936 diff --git a/Tom-Qwen-7B-Instruct.Q8_0.gguf b/Tom-Qwen-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..5cc56ba --- /dev/null +++ b/Tom-Qwen-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfca0cbf9a17fb82fa23ac4f84a8d7c201cf665a043073cd4465a287be4280a0 +size 8098526336 diff --git a/Tom-Qwen-7B-Instruct.f16.gguf b/Tom-Qwen-7B-Instruct.f16.gguf new file mode 100644 index 0000000..99dce59 --- /dev/null +++ b/Tom-Qwen-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3086f7746c82469a10c9c9ca38adca5a33b76f113b44eb517e187830ecd4c2f7 +size 15237854336