commit 35210970001ed3c3be9b2cd2e4c8de33565b658f Author: ModelHub XC Date: Sat May 9 21:20:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c61fc8 --- /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 +GRPO-VI-Qwen2-1.5B-RAG.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRPO-VI-Qwen2-1.5B-RAG.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRPO-VI-Qwen2-1.5B-RAG.IQ4_XS.gguf b/GRPO-VI-Qwen2-1.5B-RAG.IQ4_XS.gguf new file mode 100644 index 0000000..5de8822 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1be062d276e07c9ad9a67ff679e8d5a5aa0a9063afdcfbd05e1dfa139d293c +size 902182848 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q2_K.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q2_K.gguf new file mode 100644 index 0000000..e032f5e --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff78fc4c8de97cee2c48e329b8ba9c71c22145ce7e657cca046e5f53c71cc88 +size 676304832 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_L.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_L.gguf new file mode 100644 index 0000000..6db569a --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bfcbda5bdfc5df53f0775b705f1c612b716dd251e7c8a2db351e0e81c3fd5a +size 880162752 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_M.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_M.gguf new file mode 100644 index 0000000..0e40e9e --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3f03b53fbd384490584497c2e0413d47c1d3d803c001f972526be92fdc1fed +size 824178624 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_S.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_S.gguf new file mode 100644 index 0000000..06ca818 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc58679e01e320c2a7ef1760f0b0c27daf1d3f3af7458976c4b4cd8e80f3433 +size 760944576 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_M.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_M.gguf new file mode 100644 index 0000000..5e3651d --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18326c886322ec7021a07b88d6d6949ba970e03955d87c9ed70ec53af3683510 +size 986048448 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_S.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_S.gguf new file mode 100644 index 0000000..2d97030 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a61a4b797eed081eb96bfff54ea23c800451285250e54d5b330d811af29572 +size 940312512 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_M.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_M.gguf new file mode 100644 index 0000000..5f83cb5 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afc54963cffdb84328e8326a9afa3646737deb15dbe36fb0a3c62e188c84bf6b +size 1125050304 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_S.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_S.gguf new file mode 100644 index 0000000..84bdd06 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b3eed222a6507cb80b0c40e8f04273ffaf5dfd9cd7ea07f10d508327ed9cdc +size 1098729408 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q6_K.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q6_K.gguf new file mode 100644 index 0000000..122ad2d --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ff9c56be22351e055e0e1d49f8597362a6cb7712027ec94eb45e94d047888f7 +size 1272739776 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.Q8_0.gguf b/GRPO-VI-Qwen2-1.5B-RAG.Q8_0.gguf new file mode 100644 index 0000000..0994607 --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42140ce1fc3dcbc66de683d672cec39b56b9e970dacc0a529b0f75453b000d66 +size 1646572992 diff --git a/GRPO-VI-Qwen2-1.5B-RAG.f16.gguf b/GRPO-VI-Qwen2-1.5B-RAG.f16.gguf new file mode 100644 index 0000000..3136d8b --- /dev/null +++ b/GRPO-VI-Qwen2-1.5B-RAG.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be3a176642762255f14175d3bdcaa5a3cdc963536371549c2c585609d899af13 +size 3093669312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f9e254d --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: AITeamVN/GRPO-VI-Qwen2-1.5B-RAG +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AITeamVN/GRPO-VI-Qwen2-1.5B-RAG + + +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/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRPO-VI-Qwen2-1.5B-RAG-GGUF/resolve/main/GRPO-VI-Qwen2-1.5B-RAG.f16.gguf) | f16 | 3.2 | 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. + +