commit c5b0f73045c2fbf4e0dfe458974499781f33dc0c Author: ModelHub XC Date: Tue Jul 21 01:48:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c83de67 --- /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-Think-KTO-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Think-KTO-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Think-KTO-v0.1.IQ4_XS.gguf b/Qwen2.5-7B-Think-KTO-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..8fa6191 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100038f4e7c6e3347760698cf727f422add4222a514996f4a9de37550fc96e14 +size 4250299264 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q2_K.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q2_K.gguf new file mode 100644 index 0000000..f89472a --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40619454b2a936e7b849cfeb5d592a1abb7a0af234e4f31620a51e68bee1aa8 +size 3015940992 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_L.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..00d8432 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9eb405073fe9309867d8a878431b1af1357eb10935e2ddb01bb0188d46fb76c +size 4088460160 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_M.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..a08b47b --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bedb9bdc9eba1c7eb2c581cfb3bbb30b4f3e538024e095caebc49b409f8d6b68 +size 3808392064 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_S.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..8a20307 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f65ef1d723ed73c17b38d2aebd41c06695da11c3892bea609b05a1c6e5001a08 +size 3492369280 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_M.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..3132273 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9123890522ba030d9b383fcdc4c1f6c0c4c3bfe6240e8e8b647cd9cf0cbbf439 +size 4683074432 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_S.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..8c491d5 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb3048f433e72590366849d5bdadd857314e6ae36fd91d1f8f20d7aa8ffe289 +size 4457769856 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_M.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..b1adfbc --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54ba96a40aaf0dac7152740a92fba5757fd332ae18fcb47ec8a986cc14578f74 +size 5444832128 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_S.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..0858362 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d46d0611e9c17261a91ccf85fefa9efbf6e2f04850df1644daa56f83e6bf9c +size 5315177344 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q6_K.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q6_K.gguf new file mode 100644 index 0000000..98d76e8 --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8b2b9d679818c8f069a1e53eea8e9dc5e26ed9b1cd9997031e9bf15e98f582c +size 6254199680 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.Q8_0.gguf b/Qwen2.5-7B-Think-KTO-v0.1.Q8_0.gguf new file mode 100644 index 0000000..44cffab --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6f976a1fb7782491f4e8427219b3c0f6ec88cadd1852ac36f2e4335e3bbb26 +size 8098526080 diff --git a/Qwen2.5-7B-Think-KTO-v0.1.f16.gguf b/Qwen2.5-7B-Think-KTO-v0.1.f16.gguf new file mode 100644 index 0000000..e075b9d --- /dev/null +++ b/Qwen2.5-7B-Think-KTO-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb2984a67835e74623df9661c6308c6374ccdd18576ef6140612885efba54267 +size 15237854080 diff --git a/README.md b/README.md new file mode 100644 index 0000000..84bda5e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: ericflo/Qwen2.5-7B-Think-KTO-v0.1 +datasets: +- ericflo/Qwen2.5-7B-Base-Think-KTO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ericflo/Qwen2.5-7B-Think-KTO-v0.1 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Think-KTO-v0.1-GGUF/resolve/main/Qwen2.5-7B-Think-KTO-v0.1.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +