commit 098d3ee7a588427c06a939ae237d4f3b6d2eb225 Author: ModelHub XC Date: Tue Jul 21 14:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen0.5b-RagSemanticChunker-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75b7b02 --- /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 +Qwen0.5b-RagSemanticChunker.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen0.5b-RagSemanticChunker.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen0.5b-RagSemanticChunker.IQ4_XS.gguf b/Qwen0.5b-RagSemanticChunker.IQ4_XS.gguf new file mode 100644 index 0000000..a95aab2 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ab4e9ca6e21f0d7b57d86fd6521ac472e6aece720574c582063679fab01245 +size 351445760 diff --git a/Qwen0.5b-RagSemanticChunker.Q2_K.gguf b/Qwen0.5b-RagSemanticChunker.Q2_K.gguf new file mode 100644 index 0000000..d1f6ced --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda0f377229df0bfad128ba0891aad1ebb9bbd34826c24a0be8e40a0ec8eceb5 +size 338607872 diff --git a/Qwen0.5b-RagSemanticChunker.Q3_K_L.gguf b/Qwen0.5b-RagSemanticChunker.Q3_K_L.gguf new file mode 100644 index 0000000..4eecdd5 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30dd39e0191d6d7553d2a1d00dc64348dd3c41d5e9a0b2e531210b7ffb7c18d5 +size 369358592 diff --git a/Qwen0.5b-RagSemanticChunker.Q3_K_M.gguf b/Qwen0.5b-RagSemanticChunker.Q3_K_M.gguf new file mode 100644 index 0000000..956d8ac --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc9fbaa08f19ad7b0103d82aa392ae7c536cecf7a2263aba5d3d9757c341e953 +size 355467008 diff --git a/Qwen0.5b-RagSemanticChunker.Q3_K_S.gguf b/Qwen0.5b-RagSemanticChunker.Q3_K_S.gguf new file mode 100644 index 0000000..2d99b6b --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8159325fcfcee9c954bca78d2c08837e418fd9869ff338fd8979caff8f772f +size 338263808 diff --git a/Qwen0.5b-RagSemanticChunker.Q4_K_M.gguf b/Qwen0.5b-RagSemanticChunker.Q4_K_M.gguf new file mode 100644 index 0000000..c1acc5c --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:598186c184ff245d8f575b414bd6a6893042c66eeaac6cd99af1463fdf9ddb7d +size 397808384 diff --git a/Qwen0.5b-RagSemanticChunker.Q4_K_S.gguf b/Qwen0.5b-RagSemanticChunker.Q4_K_S.gguf new file mode 100644 index 0000000..ef2fbe1 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43ef7272d8ca956ed1ad1d5adeb441f965182c4be4d6a8e1e314d0e2f89fc3ea +size 385472256 diff --git a/Qwen0.5b-RagSemanticChunker.Q5_K_M.gguf b/Qwen0.5b-RagSemanticChunker.Q5_K_M.gguf new file mode 100644 index 0000000..f989ca7 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb0fd97779a0172655be8808150fc9415581acc07ca5b76b94712868f00d42f5 +size 420086528 diff --git a/Qwen0.5b-RagSemanticChunker.Q5_K_S.gguf b/Qwen0.5b-RagSemanticChunker.Q5_K_S.gguf new file mode 100644 index 0000000..15b4631 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873526ad414ea850f00959dcdbbe6b01324ff06a9a7784d2963b450fccb1f07e +size 412710656 diff --git a/Qwen0.5b-RagSemanticChunker.Q6_K.gguf b/Qwen0.5b-RagSemanticChunker.Q6_K.gguf new file mode 100644 index 0000000..4777e70 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e51f66f9426d9049120dc93daa5c469824a5af4e56b606a4b24dcf40d1b78e +size 505736960 diff --git a/Qwen0.5b-RagSemanticChunker.Q8_0.gguf b/Qwen0.5b-RagSemanticChunker.Q8_0.gguf new file mode 100644 index 0000000..5b2c4d1 --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd993ccf6cbbad0c4b6e68b9f4ff193c6c3f76ea3281beceac425aa4ba6b208 +size 531068672 diff --git a/Qwen0.5b-RagSemanticChunker.f16.gguf b/Qwen0.5b-RagSemanticChunker.f16.gguf new file mode 100644 index 0000000..8c2ea5b --- /dev/null +++ b/Qwen0.5b-RagSemanticChunker.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50d3e82ff2d853edf3ca5e5ec2ec441690cf9ee5d8043e226d825698a29ee47 +size 994157312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a18fc3 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: cnmoro/Qwen0.5b-RagSemanticChunker +language: +- en +- pt +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- rag +- chunking +--- +## About + + + + + + +static quants of https://huggingface.co/cnmoro/Qwen0.5b-RagSemanticChunker + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-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/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen0.5b-RagSemanticChunker-GGUF/resolve/main/Qwen0.5b-RagSemanticChunker.f16.gguf) | f16 | 1.1 | 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. + +