commit da106f89ee52d570c8af43cffa831af5b4aa4111 Author: ModelHub XC Date: Tue Jul 21 02:05:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-olm-v1.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74fbc03 --- /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 +Qwen2.5-7B-olm-v1.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-olm-v1.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-olm-v1.2.IQ4_XS.gguf b/Qwen2.5-7B-olm-v1.2.IQ4_XS.gguf new file mode 100644 index 0000000..a5f0232 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152e5012d3faa488f7727fcfce627c01f67aa3c4995e6ee67804b78654b1dc16 +size 4250297472 diff --git a/Qwen2.5-7B-olm-v1.2.Q2_K.gguf b/Qwen2.5-7B-olm-v1.2.Q2_K.gguf new file mode 100644 index 0000000..1597555 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3055761ae43ee935f8babcb15370b1f4f962d1711920a2ca8caf20119a0e1ed +size 3015939200 diff --git a/Qwen2.5-7B-olm-v1.2.Q3_K_L.gguf b/Qwen2.5-7B-olm-v1.2.Q3_K_L.gguf new file mode 100644 index 0000000..07a1669 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f88067a539f22c756eba3c6937ec54789f1ece6b7d494583af224af449069c +size 4088458368 diff --git a/Qwen2.5-7B-olm-v1.2.Q3_K_M.gguf b/Qwen2.5-7B-olm-v1.2.Q3_K_M.gguf new file mode 100644 index 0000000..277f34e --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df6d3a0641ae67b49c4855caf4d23b7814e1a02d17c77a25aba5bb0e7c9a91d +size 3808390272 diff --git a/Qwen2.5-7B-olm-v1.2.Q3_K_S.gguf b/Qwen2.5-7B-olm-v1.2.Q3_K_S.gguf new file mode 100644 index 0000000..c727a4d --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9442beead667822eb7b8cc38b6d86eaf745e3ca1ad35954fd4cb2d9711b03a92 +size 3492367488 diff --git a/Qwen2.5-7B-olm-v1.2.Q4_K_M.gguf b/Qwen2.5-7B-olm-v1.2.Q4_K_M.gguf new file mode 100644 index 0000000..5dc23de --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554caeac77d1d1289f5104f2c87f3b1185f66920841acf69083afd8025cdbe74 +size 4683072640 diff --git a/Qwen2.5-7B-olm-v1.2.Q4_K_S.gguf b/Qwen2.5-7B-olm-v1.2.Q4_K_S.gguf new file mode 100644 index 0000000..02645f4 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a67013b52bf2b46be000443f194e24a3389fd8d6126cbf3ed9d3506b5b802a +size 4457768064 diff --git a/Qwen2.5-7B-olm-v1.2.Q5_K_M.gguf b/Qwen2.5-7B-olm-v1.2.Q5_K_M.gguf new file mode 100644 index 0000000..2847501 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c692eee0ce5f4191fe8dd55455e9d462a5d32fe7775720859b167cc8595eea06 +size 5444830336 diff --git a/Qwen2.5-7B-olm-v1.2.Q5_K_S.gguf b/Qwen2.5-7B-olm-v1.2.Q5_K_S.gguf new file mode 100644 index 0000000..8879993 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d31796ba1f00dae6bd7d944085b834dc3b08a48fd888268ed6b8337264771d1 +size 5315175552 diff --git a/Qwen2.5-7B-olm-v1.2.Q6_K.gguf b/Qwen2.5-7B-olm-v1.2.Q6_K.gguf new file mode 100644 index 0000000..32f0e68 --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7cb725610a00386bb1a83cd5ccdaf89656a9c4b693ef4ff45747d824f3d835 +size 6254197888 diff --git a/Qwen2.5-7B-olm-v1.2.Q8_0.gguf b/Qwen2.5-7B-olm-v1.2.Q8_0.gguf new file mode 100644 index 0000000..aa9b67f --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77fce69f9d7bbacf212bf3782e30a82d3981a14d39322104991a4682efffa793 +size 8098524288 diff --git a/Qwen2.5-7B-olm-v1.2.f16.gguf b/Qwen2.5-7B-olm-v1.2.f16.gguf new file mode 100644 index 0000000..ecb876a --- /dev/null +++ b/Qwen2.5-7B-olm-v1.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49936b232b7a826354929d6ebccc2ded3525ba4d6f8ecb8fbc3b5cfaa7f84b24 +size 15237852288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c4aff36 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jeffmeloy/Qwen2.5-7B-olm-v1.2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/jeffmeloy/Qwen2.5-7B-olm-v1.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-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/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-olm-v1.2-GGUF/resolve/main/Qwen2.5-7B-olm-v1.2.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. + +