commit 3b986168e2e01b0423af9924c0708a2779d8c9b1 Author: ModelHub XC Date: Thu Oct 15 03:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Sarva0.1-Qwen7B-Final-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..381a4f2 --- /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 +Sarva0.1-Qwen7B-Final.f16.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Sarva0.1-Qwen7B-Final.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..11e460e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: revianoo/Sarva0.1-Qwen7B-Final +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/revianoo/Sarva0.1-Qwen7B-Final + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Sarva0.1-Qwen7B-Final-GGUF).*** + +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/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Sarva0.1-Qwen7B-Final-GGUF/resolve/main/Sarva0.1-Qwen7B-Final.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. + + diff --git a/Sarva0.1-Qwen7B-Final.IQ4_XS.gguf b/Sarva0.1-Qwen7B-Final.IQ4_XS.gguf new file mode 100644 index 0000000..b60ef90 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af50d3e4c2c5397259b6605d49380bfad4dc8118a82281635ccf91c613d213c8 +size 4250298592 diff --git a/Sarva0.1-Qwen7B-Final.Q2_K.gguf b/Sarva0.1-Qwen7B-Final.Q2_K.gguf new file mode 100644 index 0000000..58b7e4a --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eaa332906ea4aa28e19e1c71156c41d90967a6aa8feced229281a67cdf668fc +size 3015940320 diff --git a/Sarva0.1-Qwen7B-Final.Q3_K_L.gguf b/Sarva0.1-Qwen7B-Final.Q3_K_L.gguf new file mode 100644 index 0000000..aee232f --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d670de3821da9dada71e71894a3facfe260c690a55f1f94476ce5b53c1d3046 +size 4088459488 diff --git a/Sarva0.1-Qwen7B-Final.Q3_K_M.gguf b/Sarva0.1-Qwen7B-Final.Q3_K_M.gguf new file mode 100644 index 0000000..f4886b5 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81dc30fb7961c591deb57e540ff3cd653c7946530a9180d62afc6778a667b6a0 +size 3808391392 diff --git a/Sarva0.1-Qwen7B-Final.Q3_K_S.gguf b/Sarva0.1-Qwen7B-Final.Q3_K_S.gguf new file mode 100644 index 0000000..530f542 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88b2807b277a1cd7b861d191ca0e01e8251514f4e9ae247ecb6a03c63724ae5 +size 3492368608 diff --git a/Sarva0.1-Qwen7B-Final.Q4_K_M.gguf b/Sarva0.1-Qwen7B-Final.Q4_K_M.gguf new file mode 100644 index 0000000..1730600 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2445943f6447082c271e371c95a6b4e53ed855fbc492e7f9974eb7a7310030f +size 4683073760 diff --git a/Sarva0.1-Qwen7B-Final.Q4_K_S.gguf b/Sarva0.1-Qwen7B-Final.Q4_K_S.gguf new file mode 100644 index 0000000..c8341e6 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb60c9b66e0dacb690f26c44743d8490dd1ea012459401e4376bd35031152461 +size 4457769184 diff --git a/Sarva0.1-Qwen7B-Final.Q5_K_M.gguf b/Sarva0.1-Qwen7B-Final.Q5_K_M.gguf new file mode 100644 index 0000000..aa9df7c --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9149940193df6e42d94bd921881518f228346932cb24adebbe89ac4058164c17 +size 5444831456 diff --git a/Sarva0.1-Qwen7B-Final.Q5_K_S.gguf b/Sarva0.1-Qwen7B-Final.Q5_K_S.gguf new file mode 100644 index 0000000..9607629 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3433fb9c01e6eddaff4123582c853537be65bdb4e86dee9bd9aa6956a50c31 +size 5315176672 diff --git a/Sarva0.1-Qwen7B-Final.Q6_K.gguf b/Sarva0.1-Qwen7B-Final.Q6_K.gguf new file mode 100644 index 0000000..70a3c12 --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10edde4c7b77ba39d1dcd84d84a74eb609b1047737e69077b5699d3a1bb97518 +size 6254199008 diff --git a/Sarva0.1-Qwen7B-Final.Q8_0.gguf b/Sarva0.1-Qwen7B-Final.Q8_0.gguf new file mode 100644 index 0000000..7cbd06c --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13388b72aac4eeefcd27de20414ed011ac00db8346b117a668ea812cbd337bdc +size 8098525408 diff --git a/Sarva0.1-Qwen7B-Final.f16.gguf b/Sarva0.1-Qwen7B-Final.f16.gguf new file mode 100644 index 0000000..97de4dc --- /dev/null +++ b/Sarva0.1-Qwen7B-Final.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3030732a9bf464f81dca2737ebaf922cc69382d580d1dc8bc9f04387e7d7418 +size 15237853408