commit 18091b3b678d859eacdeca2a7c6f09a7b996350a Author: ModelHub XC Date: Mon Aug 10 11:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Khaosara-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f91d35 --- /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 +Khaosara-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Khaosara-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Khaosara-7B-Instruct.IQ4_XS.gguf b/Khaosara-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b113a6f --- /dev/null +++ b/Khaosara-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd58adfb35ee94435f6741f8c88be646e966efd34c0fc7f49817dcfb01f9ee32 +size 3948664096 diff --git a/Khaosara-7B-Instruct.Q2_K.gguf b/Khaosara-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..87db7c5 --- /dev/null +++ b/Khaosara-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3df40960552fa0bfc12e89e054869adb6b35d21554897ca01bf1d4db17de0e7 +size 2722878752 diff --git a/Khaosara-7B-Instruct.Q3_K_L.gguf b/Khaosara-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..d7fdef8 --- /dev/null +++ b/Khaosara-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7952bb7655a96cfb1de9210069959dcfa69d99be92511b6d3332f3c2567324b9 +size 3825980704 diff --git a/Khaosara-7B-Instruct.Q3_K_M.gguf b/Khaosara-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..04d9c53 --- /dev/null +++ b/Khaosara-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b368544213b8f2731bb051ff1c9614918ca06038d7dcfceec36a88b612f555 +size 3522942240 diff --git a/Khaosara-7B-Instruct.Q3_K_S.gguf b/Khaosara-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..ab7f7ff --- /dev/null +++ b/Khaosara-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d588b4671a43c59ed6ab5fee2783c958ed2e6f5e3d134943adb792060fe4db +size 3168523552 diff --git a/Khaosara-7B-Instruct.Q4_K_M.gguf b/Khaosara-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..1f931bd --- /dev/null +++ b/Khaosara-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee1508dd206ced71674635a740b02c8844fc5a5ab78089636ba6e0c1d43bb4e +size 4372813088 diff --git a/Khaosara-7B-Instruct.Q4_K_S.gguf b/Khaosara-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..ec3ac3f --- /dev/null +++ b/Khaosara-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6722aa328231df95c1c450b285f7b6cf4fb6fc7e0cdf37858a294c9340235cf7 +size 4144747808 diff --git a/Khaosara-7B-Instruct.Q5_K_M.gguf b/Khaosara-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..bf758ba --- /dev/null +++ b/Khaosara-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7029ad87b1bbe1ca427bca816455e06af2774e39ce723f83247e7216265f4e3a +size 5136176416 diff --git a/Khaosara-7B-Instruct.Q5_K_S.gguf b/Khaosara-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..ac49e7b --- /dev/null +++ b/Khaosara-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00e27e3f6e076476de49d3023325412096535b1025ba3a693fa7c5c68bd54329 +size 5002482976 diff --git a/Khaosara-7B-Instruct.Q6_K.gguf b/Khaosara-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..2f0287b --- /dev/null +++ b/Khaosara-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d18ce3146eee13c6ca7df1ed8f133815631d6cde127f080faf12e4e0ada457 +size 5947249952 diff --git a/Khaosara-7B-Instruct.Q8_0.gguf b/Khaosara-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..06e0883 --- /dev/null +++ b/Khaosara-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa636b70021f53ffebad7cee829ae5de62c6431919307e53161a12ab7c52fec +size 7702566176 diff --git a/Khaosara-7B-Instruct.f16.gguf b/Khaosara-7B-Instruct.f16.gguf new file mode 100644 index 0000000..1d3cd32 --- /dev/null +++ b/Khaosara-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de063e6c9f20bc82f4d4d9bf91e7bd4b7d54e8b0c79116d4de121da1841eb921 +size 14497338656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..844359a --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: c4tdr0ut/Khaosara-7B-Instruct +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- mistral +- mistral-7b +- khaosara +- axolotl +- unhinged +- x.ai +- sota +- liger +- sft +- continual-pretraining +- factual +- domain-expert +- conversational +- research +--- +## About + + + + + + + + + +static quants of https://huggingface.co/c4tdr0ut/Khaosara-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Khaosara-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Khaosara-7B-Instruct-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/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Khaosara-7B-Instruct-GGUF/resolve/main/Khaosara-7B-Instruct.f16.gguf) | f16 | 14.6 | 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. + +