commit 230d015600e2bd05a88177e71c1f48d299dcb774 Author: ModelHub XC Date: Thu Sep 17 14:12:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-0.6b-nepali-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..86e7e9a --- /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 +Qwen-0.6b-nepali-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-0.6b-nepali-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-0.6b-nepali-instruct.IQ4_XS.gguf b/Qwen-0.6b-nepali-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..b069b53 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2655d4bf491f2a9731dce61bc5f7a551f0b0602eb3cff540c376672146b9c17 +size 369274880 diff --git a/Qwen-0.6b-nepali-instruct.Q2_K.gguf b/Qwen-0.6b-nepali-instruct.Q2_K.gguf new file mode 100644 index 0000000..32c7256 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19d43f17e1d3f91c96be7bafd696a2e6edc45416415ac4b6f75fc18560e726a +size 296235008 diff --git a/Qwen-0.6b-nepali-instruct.Q3_K_L.gguf b/Qwen-0.6b-nepali-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9c79b44 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f26df6c6159bcb538ebb06cd105bd38b58936bc01df0f31e0d840b1cf5bf39f +size 368488448 diff --git a/Qwen-0.6b-nepali-instruct.Q3_K_M.gguf b/Qwen-0.6b-nepali-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b16ff75 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a16a60d8e9de342bbaf3c07def30fa4bec48db82ba54651b568bea2dbb2680 +size 347123712 diff --git a/Qwen-0.6b-nepali-instruct.Q3_K_S.gguf b/Qwen-0.6b-nepali-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..ba8b09d --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4da28f25273299572dccf852f9227cfb306b49badc96fef9ab4398adf0bea5b +size 323072000 diff --git a/Qwen-0.6b-nepali-instruct.Q4_K_M.gguf b/Qwen-0.6b-nepali-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..6cee5a6 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77b03e3aff3881d7e66e3d4d6bd15644bf3ae807c84b43350989b6b66c0c637 +size 396701696 diff --git a/Qwen-0.6b-nepali-instruct.Q4_K_S.gguf b/Qwen-0.6b-nepali-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..8c218f6 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dcddfb01606d032e831fcab01a9f68402dc32df44c509d28094a0144c48c521 +size 383266816 diff --git a/Qwen-0.6b-nepali-instruct.Q5_K_M.gguf b/Qwen-0.6b-nepali-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..295c1f0 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565008dbc1dcf384460cb5502c8cfb442aa3ca8af2cff18701f777c8e83bd14f +size 444411904 diff --git a/Qwen-0.6b-nepali-instruct.Q5_K_S.gguf b/Qwen-0.6b-nepali-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..5173117 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847ff560563d50a5de1a66b4b65e72137a60c3385e3d70e82df22f9d56e4f982 +size 436613120 diff --git a/Qwen-0.6b-nepali-instruct.Q6_K.gguf b/Qwen-0.6b-nepali-instruct.Q6_K.gguf new file mode 100644 index 0000000..885b5b6 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a73e3be043d5a0ec41aba541c31a05213e5735602609e0ceb22e1199686c50d +size 495104000 diff --git a/Qwen-0.6b-nepali-instruct.Q8_0.gguf b/Qwen-0.6b-nepali-instruct.Q8_0.gguf new file mode 100644 index 0000000..0425f85 --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9145b0e4d13948c2c63dc2a465986e6a83c541d3924fbc33bf37a80ec76a68f1 +size 639443968 diff --git a/Qwen-0.6b-nepali-instruct.f16.gguf b/Qwen-0.6b-nepali-instruct.f16.gguf new file mode 100644 index 0000000..105ef1a --- /dev/null +++ b/Qwen-0.6b-nepali-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2156a2a839ff2be623bbbb5d3016b6c94dd663df00c13f33a53d36bf14ddb4 +size 1198179328 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6b8dc19 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: praful1/Qwen-0.6b-nepali-instruct +datasets: +- praful1/NepaliQA-alpaca_chat-load_qa2 +language: +- en +library_name: transformers +model_name: Qwen-0.6b-nepali-instruct +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/praful1/Qwen-0.6b-nepali-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-0.6b-nepali-instruct-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/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-0.6b-nepali-instruct-GGUF/resolve/main/Qwen-0.6b-nepali-instruct.f16.gguf) | f16 | 1.3 | 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. + +