commit 3222af14d0ad94e463486867312290dccc170ced Author: ModelHub XC Date: Fri Oct 2 22:27:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c358cd --- /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 +Qwen3-4B-GRPO-Indo-Alpaca.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-GRPO-Indo-Alpaca.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.IQ4_XS.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.IQ4_XS.gguf new file mode 100644 index 0000000..8372f47 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4425986890bf8f5ad7b81348d4ff730e4c00dcfd7e57778c00ad5faceb5cfec +size 2286317408 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q2_K.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q2_K.gguf new file mode 100644 index 0000000..2e73801 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:051cf333be52d2bdb636ae474916d04a171e2cfd3e326296028653e9dd13a54a +size 1669500768 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_L.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_L.gguf new file mode 100644 index 0000000..f23659e --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56999ccb4b5b9c18091f8f4e70a2626de51d153b8675e3579b45d7c355d008bc +size 2239786848 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_M.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_M.gguf new file mode 100644 index 0000000..027606f --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d270bcc88bac01d051a00e830d8f01b27201eea6312f1ce17345a169eb7f2de5 +size 2075619168 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_S.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_S.gguf new file mode 100644 index 0000000..f6ac533 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7540248ba885a19a9c21d9c47b0574c447b230344f2a2890a53aa42ceb08bf3 +size 1886998368 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_M.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_M.gguf new file mode 100644 index 0000000..3fc4ccb --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c854b008e7c8f27469aad2786ac7c1c61a7be11154df104224670f33d765956 +size 2497281888 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_S.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_S.gguf new file mode 100644 index 0000000..763ed49 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22c0331780822ae56aba522c2e471c807ed3974616d2146261a2c9396d9bc3a +size 2383310688 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_M.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_M.gguf new file mode 100644 index 0000000..47f6f66 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a89bb8aa03f77ab782e80603e7b8081a4f00c199da213c1dc4d10c6c5d2a394 +size 2889514848 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_S.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_S.gguf new file mode 100644 index 0000000..2a2e7ec --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a2cd44986f03781f46be5784372a14c21cf93ddb1c9db3be484b40a395de0b +size 2823712608 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q6_K.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q6_K.gguf new file mode 100644 index 0000000..e009d29 --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb00af2c202b11fa2745c76ca6567f6c8d0619a4d9d73abc5f278034a12198d4 +size 3306262368 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.Q8_0.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.Q8_0.gguf new file mode 100644 index 0000000..529abce --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2bc7e4a3ba8e486c54debd8e0d00a2d8b1220cf160ba2792ab147fb6ba763bd +size 4280406368 diff --git a/Qwen3-4B-GRPO-Indo-Alpaca.f16.gguf b/Qwen3-4B-GRPO-Indo-Alpaca.f16.gguf new file mode 100644 index 0000000..1e73f6d --- /dev/null +++ b/Qwen3-4B-GRPO-Indo-Alpaca.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:509b53e14ef41ba91f8213db2e3e44904a6b884ea65b212e4fde2f2dcec8f211 +size 8051286368 diff --git a/README.md b/README.md new file mode 100644 index 0000000..587b79f --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: caffeinejunkie1/Qwen3-4B-GRPO-Indo-Alpaca +datasets: +- Ichsan2895/alpaca-gpt4-indonesian +language: +- id +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qwen +- qwen3 +- rlhf +- grpo +- alignment +- indonesian +- alpaca +--- +## About + + + + + + + + + +static quants of https://huggingface.co/caffeinejunkie1/Qwen3-4B-GRPO-Indo-Alpaca + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-GRPO-Indo-Alpaca-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/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-GRPO-Indo-Alpaca-GGUF/resolve/main/Qwen3-4B-GRPO-Indo-Alpaca.f16.gguf) | f16 | 8.2 | 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. + +