commit 63b63b9f47efce00de4a00df2f488cb6309aae23 Author: ModelHub XC Date: Wed Jun 3 03:34:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QVikhr-3-4B-Instruction-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81ab9dc --- /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 +QVikhr-3-4B-Instruction.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QVikhr-3-4B-Instruction.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QVikhr-3-4B-Instruction.IQ4_XS.gguf b/QVikhr-3-4B-Instruction.IQ4_XS.gguf new file mode 100644 index 0000000..135698c --- /dev/null +++ b/QVikhr-3-4B-Instruction.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff46964d8774935f8d386fd0410946cfb4d79b13b10cef8de4dc00fd67b59d71 +size 2286312096 diff --git a/QVikhr-3-4B-Instruction.Q2_K.gguf b/QVikhr-3-4B-Instruction.Q2_K.gguf new file mode 100644 index 0000000..fecd565 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c50af3cd1c1658d249447abe9f45a2a9aa5bf54b24ce6815531eae5886709da +size 1669495456 diff --git a/QVikhr-3-4B-Instruction.Q3_K_L.gguf b/QVikhr-3-4B-Instruction.Q3_K_L.gguf new file mode 100644 index 0000000..9c1ee58 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f6b8dc52eb7f49b7dbf3c23fc4f547072cbdf8531c0ad0d47734052e38ec82c +size 2239781536 diff --git a/QVikhr-3-4B-Instruction.Q3_K_M.gguf b/QVikhr-3-4B-Instruction.Q3_K_M.gguf new file mode 100644 index 0000000..65f465a --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed04cd85adb5c919a180c131de8d1144300e15cc9d420ab9155b78c6bee6c749 +size 2075613856 diff --git a/QVikhr-3-4B-Instruction.Q3_K_S.gguf b/QVikhr-3-4B-Instruction.Q3_K_S.gguf new file mode 100644 index 0000000..3f35b2c --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2537fd0d7571116890dc05f534dfce3532ea7d063b7b3da02010bd98350d20c +size 1886993056 diff --git a/QVikhr-3-4B-Instruction.Q4_K_M.gguf b/QVikhr-3-4B-Instruction.Q4_K_M.gguf new file mode 100644 index 0000000..80f82c1 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa5a71d1faf7fe86dbad99fe298b538d7ebf36acd5d6a7dc3419f550b0464ab0 +size 2497276576 diff --git a/QVikhr-3-4B-Instruction.Q4_K_S.gguf b/QVikhr-3-4B-Instruction.Q4_K_S.gguf new file mode 100644 index 0000000..376fb6a --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b014ad771880782706d2a7704a75d6e69b95c40d6aef78708ee63633739dc02e +size 2383305376 diff --git a/QVikhr-3-4B-Instruction.Q5_K_M.gguf b/QVikhr-3-4B-Instruction.Q5_K_M.gguf new file mode 100644 index 0000000..656a433 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7a483aeadb1ad8c67554b45ad48f9dfa71ff01190204c1f770ae2c20485af2 +size 2889509536 diff --git a/QVikhr-3-4B-Instruction.Q5_K_S.gguf b/QVikhr-3-4B-Instruction.Q5_K_S.gguf new file mode 100644 index 0000000..ac30473 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aae5d5f8c565a7d8d18b75d916d74543a8298cbe5a7b51fb25a60ac82ec5596 +size 2823707296 diff --git a/QVikhr-3-4B-Instruction.Q6_K.gguf b/QVikhr-3-4B-Instruction.Q6_K.gguf new file mode 100644 index 0000000..a80f7b7 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c97b11ada06beb2fdfdfd86364a8dd029cac706937b8dd3881790f3cab15ea0 +size 3306257056 diff --git a/QVikhr-3-4B-Instruction.Q8_0.gguf b/QVikhr-3-4B-Instruction.Q8_0.gguf new file mode 100644 index 0000000..fc11151 --- /dev/null +++ b/QVikhr-3-4B-Instruction.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a4b232acb2ceba3ff9e419fb5d7abcea7ae920c3c0f5ba472474cf1b8346a3 +size 4280401056 diff --git a/QVikhr-3-4B-Instruction.f16.gguf b/QVikhr-3-4B-Instruction.f16.gguf new file mode 100644 index 0000000..6e42878 --- /dev/null +++ b/QVikhr-3-4B-Instruction.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9785afd045d1deb81b6bf38358d0fd5dd4b25a2d07bf6eadddbd53c13af75c56 +size 8051281056 diff --git a/README.md b/README.md new file mode 100644 index 0000000..91c4d7c --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Vikhrmodels/QVikhr-3-4B-Instruction +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Vikhrmodels/QVikhr-3-4B-Instruction + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-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/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QVikhr-3-4B-Instruction-GGUF/resolve/main/QVikhr-3-4B-Instruction.f16.gguf) | f16 | 8.2 | 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. + +