commit b98a1c280e2040d1ce21b9d63373aec0d69a6fe9 Author: ModelHub XC Date: Fri Oct 9 07:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QwenAlesya-1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c7efd7d --- /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 +QwenAlesya-1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwenAlesya-1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwenAlesya-1-8B.IQ4_XS.gguf b/QwenAlesya-1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..07c15bc --- /dev/null +++ b/QwenAlesya-1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f57883d3fcadae2390ebdc6c032b23f0117d2ad2d04bc6e47bda07612dc22a4f +size 4593292832 diff --git a/QwenAlesya-1-8B.Q2_K.gguf b/QwenAlesya-1-8B.Q2_K.gguf new file mode 100644 index 0000000..bb360cc --- /dev/null +++ b/QwenAlesya-1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd8a1337dae958bf9d4ece5ba37f7d7e06a2bf4e0a1742278a3833c572fafed +size 3281729056 diff --git a/QwenAlesya-1-8B.Q3_K_L.gguf b/QwenAlesya-1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..68ff8d0 --- /dev/null +++ b/QwenAlesya-1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f2cf2f23be5b8593516f283e90e8fa638618e53eec5b0bf3ca18399c74b18d +size 4431390240 diff --git a/QwenAlesya-1-8B.Q3_K_M.gguf b/QwenAlesya-1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..045aa7b --- /dev/null +++ b/QwenAlesya-1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc962436d1d54d549b6bb25403af232ef427e2edcf0fa741178d95126ee0c624 +size 4124157472 diff --git a/QwenAlesya-1-8B.Q3_K_S.gguf b/QwenAlesya-1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..8fb1130 --- /dev/null +++ b/QwenAlesya-1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1539c3f17ef1af9586656476037e4f64496d42eb50b7edd2217039a124584533 +size 3769607712 diff --git a/QwenAlesya-1-8B.Q4_K_M.gguf b/QwenAlesya-1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..0bc9676 --- /dev/null +++ b/QwenAlesya-1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c274d3c9b023474a1b51f8d08bcbffa707b1e3daae00f80e8e1ebe0a7ec87a +size 5027780128 diff --git a/QwenAlesya-1-8B.Q4_K_S.gguf b/QwenAlesya-1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..a72062a --- /dev/null +++ b/QwenAlesya-1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9adaebb0a085c202b76eb92b0c016b383efc03722ce4d23c3b40351473804910 +size 4802008608 diff --git a/QwenAlesya-1-8B.Q5_K_M.gguf b/QwenAlesya-1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..7ed2221 --- /dev/null +++ b/QwenAlesya-1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ab96bfe9eb8ab75855ed8f49438ca5356dcf80687c03d02cb157ae66af669b +size 5851108896 diff --git a/QwenAlesya-1-8B.Q5_K_S.gguf b/QwenAlesya-1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..5661aec --- /dev/null +++ b/QwenAlesya-1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef923521e8425ccc5577895ae7d53f8e29635008e4f0867eba30dda77623ffc7 +size 5720757792 diff --git a/QwenAlesya-1-8B.Q6_K.gguf b/QwenAlesya-1-8B.Q6_K.gguf new file mode 100644 index 0000000..878a15f --- /dev/null +++ b/QwenAlesya-1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c126521fc2b36ebb0cd6967acaefbf05e16b69ad68a727d638eaf67a5bc87469 +size 6725895712 diff --git a/QwenAlesya-1-8B.Q8_0.gguf b/QwenAlesya-1-8B.Q8_0.gguf new file mode 100644 index 0000000..7e9afd9 --- /dev/null +++ b/QwenAlesya-1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ace6861de883e9d6a5a6127a4814b294091e12c3e5a071e08fb61bad2b7ad7d +size 8709514784 diff --git a/QwenAlesya-1-8B.f16.gguf b/QwenAlesya-1-8B.f16.gguf new file mode 100644 index 0000000..8c6f6fd --- /dev/null +++ b/QwenAlesya-1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41fe4328b669ccbdd80597745d3d16e66611f6ef38eb674fabd37604a9255de0 +size 16388040224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..21b1a19 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ArtemkaT08/QwenAlesya-1-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + +static quants of https://huggingface.co/ArtemkaT08/QwenAlesya-1-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QwenAlesya-1-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/QwenAlesya-1-8B-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/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwenAlesya-1-8B-GGUF/resolve/main/QwenAlesya-1-8B.f16.gguf) | f16 | 16.5 | 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. + +