commit 789e63159108ff022f6a9bb9d37bde67d70d5248 Author: ModelHub XC Date: Fri May 8 16:35:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b30b9bb --- /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-Instruct-HardLambda0.1-220.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-HardLambda0.1-220.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.IQ4_XS.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.IQ4_XS.gguf new file mode 100644 index 0000000..0b23f3a --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04dc2e2c745af6221077bb7cda48f463fd2e45ec4e064ff59ffed801b0f9a281 +size 4250298816 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q2_K.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q2_K.gguf new file mode 100644 index 0000000..bae8720 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8da9535bb490383d05d32ba698aa62cda50467d334bab606b93d09df116829 +size 3015940544 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_L.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_L.gguf new file mode 100644 index 0000000..a756417 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ebc2c11c5010d1387a0fecc8d20107b307e9edd93063c4c09c14cd96947e3c +size 4088459712 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_M.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_M.gguf new file mode 100644 index 0000000..baa42f4 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f4e335a12965d93f81e40d1829037210bb0bfec1d65c39c2f8f43bba8c7955b +size 3808391616 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_S.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_S.gguf new file mode 100644 index 0000000..4293cbd --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf26fec9b8cbd017ff6b37e558c52991234ebb92313499efdd61169e6db2298f +size 3492368832 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_M.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_M.gguf new file mode 100644 index 0000000..8991882 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a133fbdd590839f081a71dce071473a2c35da1d357e46511c0680134fec0aa00 +size 4683073984 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_S.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_S.gguf new file mode 100644 index 0000000..1d782f6 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8faf72e30626a00085031bc3d3b507276390160763e0e5d20daedf2cf1f544b8 +size 4457769408 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_M.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_M.gguf new file mode 100644 index 0000000..7a0fc21 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d317b4a456d2277ee1c96afa46ac75e58127585a1e28084d98d968e4e08c722 +size 5444831680 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_S.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_S.gguf new file mode 100644 index 0000000..887ef95 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3844e211b21ae920ccc3fec0ae240540257f9a2b76851f8bf0ba68d847542674 +size 5315176896 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q6_K.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q6_K.gguf new file mode 100644 index 0000000..08bab39 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4a0553be2cd4ee49f0d035bd1b509b9768bb889661773e0ecebc70bb8a2a11 +size 6254199232 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q8_0.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q8_0.gguf new file mode 100644 index 0000000..20d4020 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f749c457403deea23c70ffd965f592f1c22fa897d4cc3c3e4773363b06f48e8 +size 8098525632 diff --git a/Qwen2.5-7B-Instruct-HardLambda0.1-220.f16.gguf b/Qwen2.5-7B-Instruct-HardLambda0.1-220.f16.gguf new file mode 100644 index 0000000..3e6cc17 --- /dev/null +++ b/Qwen2.5-7B-Instruct-HardLambda0.1-220.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86da2d21a3211931a526aec6e27ca9623aa605b91f9be4249a2a0be4293e7e35 +size 15237853632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01f9102 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: rd211/Qwen2.5-7B-Instruct-HardLambda0.1-220 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/rd211/Qwen2.5-7B-Instruct-HardLambda0.1-220 + + +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-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-HardLambda0.1-220-GGUF/resolve/main/Qwen2.5-7B-Instruct-HardLambda0.1-220.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. + +