commit 17e1e19dceeb738b52942ca25e835024b98c8095 Author: ModelHub XC Date: Tue Jun 2 06:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..564b1bf --- /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 +Aiya-Qwen1.5-1.8B-Chat-finetuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aiya-Qwen1.5-1.8B-Chat-finetuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.IQ4_XS.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.IQ4_XS.gguf new file mode 100644 index 0000000..7adf05f --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd173168966bd8a0aee4f026ee34b35f6f239bdb41040bd76a0cad5717738b5 +size 1087361664 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q2_K.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q2_K.gguf new file mode 100644 index 0000000..dcbf8e6 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a56a9e415f0420a44b22f7c608e3f5971259b709770ec5df6ce7685ae6afe2f +size 846570112 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_L.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_L.gguf new file mode 100644 index 0000000..d74bad9 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737520e8e697501c194ef5d4ec62f131d978b191e3951c697dea3915e19f0253 +size 1056201344 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_M.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_M.gguf new file mode 100644 index 0000000..17aeba9 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c04ee8d900769fd1db58ff24559d230cf94c112deb7395b9d30e70bd1be16d46 +size 1015880320 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_S.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_S.gguf new file mode 100644 index 0000000..6c2ba8d --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b4385726be86be1b035a9f90ee61d05938441e6529b8979499f982c082751c +size 953571968 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_M.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_M.gguf new file mode 100644 index 0000000..12fe5db --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d91684c0ad8c53d3a85e7fd21393306e6d628df03fba7d7e65b8f3b0938d83 +size 1217753728 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_S.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_S.gguf new file mode 100644 index 0000000..940bb1a --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:007d15c20d8958ce4896b73c8ab4def3912d79671b6d0b9d1dfd49603dc775e4 +size 1158263424 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_M.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_M.gguf new file mode 100644 index 0000000..b8df071 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c553cce8500be5cacc04e9ef52541a43e8243f2887edbbd2669872ae6a12da +size 1376776832 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_S.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_S.gguf new file mode 100644 index 0000000..bbfa843 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f5fde77264a5047ee90a371b7c7b32922c188c5ec16cd4798969e7768764e5a +size 1327821440 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q6_K.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q6_K.gguf new file mode 100644 index 0000000..91f91bd --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa313bf0468501136d7f40e0fe25eb7b885c8dd5d26d8c21f718f02204e8463 +size 1579027072 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q8_0.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q8_0.gguf new file mode 100644 index 0000000..42256d5 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d7527f8246e4be38850ff1867971702048467549cf3714fad8c05fa33667f61 +size 1958304384 diff --git a/Aiya-Qwen1.5-1.8B-Chat-finetuned.f16.gguf b/Aiya-Qwen1.5-1.8B-Chat-finetuned.f16.gguf new file mode 100644 index 0000000..d14c1e3 --- /dev/null +++ b/Aiya-Qwen1.5-1.8B-Chat-finetuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5c23e42b6cfe0c87c32fafde8782b44930275b07665fc0ce9fbe6120b254be +size 3680098944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dbe13cc --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: akshitsrivastava04/Aiya-Qwen1.5-1.8B-Chat-finetuned +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/akshitsrivastava04/Aiya-Qwen1.5-1.8B-Chat-finetuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Aiya-Qwen1.5-1.8B-Chat-finetuned-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/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_S.gguf) | Q3_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_M.gguf) | Q3_K_M | 1.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q3_K_L.gguf) | Q3_K_L | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.IQ4_XS.gguf) | IQ4_XS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_S.gguf) | Q4_K_S | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q4_K_M.gguf) | Q4_K_M | 1.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q5_K_M.gguf) | Q5_K_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q6_K.gguf) | Q6_K | 1.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.Q8_0.gguf) | Q8_0 | 2.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aiya-Qwen1.5-1.8B-Chat-finetuned-GGUF/resolve/main/Aiya-Qwen1.5-1.8B-Chat-finetuned.f16.gguf) | f16 | 3.8 | 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. + +