commit 5c71b54e0fd3598ce62500a7a85a31ebef056e6c Author: ModelHub XC Date: Tue Jun 9 18:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Vikhr-7B-instruct_0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..829c02f --- /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 +Vikhr-7B-instruct_0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Vikhr-7B-instruct_0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..542aa4b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Vikhrmodels/Vikhr-7B-instruct_0.2 +datasets: +- zjkarina/Vikhr_instruct +- dichspace/darulm +language: +- ru +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Vikhrmodels/Vikhr-7B-instruct_0.2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Vikhr-7B-instruct_0.2-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-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/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q3_K_S.gguf) | Q3_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Vikhr-7B-instruct_0.2-GGUF/resolve/main/Vikhr-7B-instruct_0.2.f16.gguf) | f16 | 14.0 | 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. + + diff --git a/Vikhr-7B-instruct_0.2.IQ4_XS.gguf b/Vikhr-7B-instruct_0.2.IQ4_XS.gguf new file mode 100644 index 0000000..1063526 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75518bd10bc93147f069ea25b91722b8533b8cdb01d4e5db974bb2cc55ef5f63 +size 3804747520 diff --git a/Vikhr-7B-instruct_0.2.Q2_K.gguf b/Vikhr-7B-instruct_0.2.Q2_K.gguf new file mode 100644 index 0000000..c955342 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8cc472ec43cb70972b2ad55b2bea8f04085fe4354bb68db754d4739d1cf30ba +size 2666585856 diff --git a/Vikhr-7B-instruct_0.2.Q3_K_L.gguf b/Vikhr-7B-instruct_0.2.Q3_K_L.gguf new file mode 100644 index 0000000..9b82285 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:477229cff09d7daf96fa464611109ca7eafa78c2487adab7f3309f3be6b2b8b5 +size 3742587648 diff --git a/Vikhr-7B-instruct_0.2.Q3_K_M.gguf b/Vikhr-7B-instruct_0.2.Q3_K_M.gguf new file mode 100644 index 0000000..1520607 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b8528561421fef4ae0d69d97405f989d41badb5ede9c81c1c3b0e717b895d8 +size 3443481344 diff --git a/Vikhr-7B-instruct_0.2.Q3_K_S.gguf b/Vikhr-7B-instruct_0.2.Q3_K_S.gguf new file mode 100644 index 0000000..20c272e --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4c367094b550abde36607691896938b0921bbbe0735608ae22dba0e08680b39 +size 3093781248 diff --git a/Vikhr-7B-instruct_0.2.Q4_K_M.gguf b/Vikhr-7B-instruct_0.2.Q4_K_M.gguf new file mode 100644 index 0000000..d0a7574 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a552dd376450587933a825ca3a278bc86e352d3fc35802ab635cba84bf3939a6 +size 4241852160 diff --git a/Vikhr-7B-instruct_0.2.Q4_K_S.gguf b/Vikhr-7B-instruct_0.2.Q4_K_S.gguf new file mode 100644 index 0000000..6a07ee0 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2d22e27a708dc569ec3254c44e2336461f153ddfc8e76d7f470e8dba91bf58 +size 4017587968 diff --git a/Vikhr-7B-instruct_0.2.Q5_K_M.gguf b/Vikhr-7B-instruct_0.2.Q5_K_M.gguf new file mode 100644 index 0000000..9d97bed --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40955d189a223d96d39e59079f8aa3f98ac5ed61c6b8d364236682b762d3fc9a +size 4958471936 diff --git a/Vikhr-7B-instruct_0.2.Q5_K_S.gguf b/Vikhr-7B-instruct_0.2.Q5_K_S.gguf new file mode 100644 index 0000000..4e901e9 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489baac56e797481d05bde5af3c675f1f4be4440d29bab9618bc77482ae6550e +size 4827006720 diff --git a/Vikhr-7B-instruct_0.2.Q6_K.gguf b/Vikhr-7B-instruct_0.2.Q6_K.gguf new file mode 100644 index 0000000..3d0d0d8 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e01bd6000a11972016f5df7b5147486ba7248d40bd04e64e68963bcb960de0 +size 5719880448 diff --git a/Vikhr-7B-instruct_0.2.Q8_0.gguf b/Vikhr-7B-instruct_0.2.Q8_0.gguf new file mode 100644 index 0000000..8bd9486 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049068a6be2313cdbb1892cf9f69ba565ee6017e1abeaaa8695a5f1014f6db05 +size 7407835904 diff --git a/Vikhr-7B-instruct_0.2.f16.gguf b/Vikhr-7B-instruct_0.2.f16.gguf new file mode 100644 index 0000000..0ac1d79 --- /dev/null +++ b/Vikhr-7B-instruct_0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b760d21efe2ece006f2b6958b96625d8756860a7db07b43e901aa147476499 +size 13941857024