commit 976d12b33bc9c4ff3659c40220851e449d2ccb4d Author: ModelHub XC Date: Fri Aug 7 20:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3GRPOReasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e5954de --- /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 +Llama3GRPOReasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3GRPOReasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3GRPOReasoning.IQ4_XS.gguf b/Llama3GRPOReasoning.IQ4_XS.gguf new file mode 100644 index 0000000..f60f1a6 --- /dev/null +++ b/Llama3GRPOReasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0fb3d49fd6bd777f14a8dea70bc8a713cad49fb7127d8bfe52238e34fedcafc +size 4484368320 diff --git a/Llama3GRPOReasoning.Q2_K.gguf b/Llama3GRPOReasoning.Q2_K.gguf new file mode 100644 index 0000000..bd89dfa --- /dev/null +++ b/Llama3GRPOReasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8ecd59e4f2f120cd3db914eb7d74c5dc5ccb7c64e1a5a12fc0ac9f7d67e129 +size 3179136960 diff --git a/Llama3GRPOReasoning.Q3_K_L.gguf b/Llama3GRPOReasoning.Q3_K_L.gguf new file mode 100644 index 0000000..60e8831 --- /dev/null +++ b/Llama3GRPOReasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100ae0b2e8ea5350d08688b9e4b97787943143e17837d361b252cfd6dff1e22a +size 4321961920 diff --git a/Llama3GRPOReasoning.Q3_K_M.gguf b/Llama3GRPOReasoning.Q3_K_M.gguf new file mode 100644 index 0000000..a56b7e6 --- /dev/null +++ b/Llama3GRPOReasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f589c84cdfcfc0bb8d16318de294f71e288afbd4fbffe80ec2fd943bbf650f48 +size 4018923456 diff --git a/Llama3GRPOReasoning.Q3_K_S.gguf b/Llama3GRPOReasoning.Q3_K_S.gguf new file mode 100644 index 0000000..d72d837 --- /dev/null +++ b/Llama3GRPOReasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1222c9ba312bf4ff6f3c6f812ba2dae73c395f0495ad65b8da5416aa962cc3ae +size 3664504768 diff --git a/Llama3GRPOReasoning.Q4_K_M.gguf b/Llama3GRPOReasoning.Q4_K_M.gguf new file mode 100644 index 0000000..6ed3b2f --- /dev/null +++ b/Llama3GRPOReasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d57a86f2b0156e8c6245b2828500ea0bfcb97d476a09bcb3e5edc5350a09938 +size 4920739776 diff --git a/Llama3GRPOReasoning.Q4_K_S.gguf b/Llama3GRPOReasoning.Q4_K_S.gguf new file mode 100644 index 0000000..a275c26 --- /dev/null +++ b/Llama3GRPOReasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc90825b488b585e525d61b944812172c235ff7e1c5e60633ab78e969501ea84 +size 4692674496 diff --git a/Llama3GRPOReasoning.Q5_K_M.gguf b/Llama3GRPOReasoning.Q5_K_M.gguf new file mode 100644 index 0000000..ef28dea --- /dev/null +++ b/Llama3GRPOReasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b1e33a2b078086bb21ea519eb9e375a62e60f941101619bc0ee84dddc11cce +size 5732992960 diff --git a/Llama3GRPOReasoning.Q5_K_S.gguf b/Llama3GRPOReasoning.Q5_K_S.gguf new file mode 100644 index 0000000..9d0d9f2 --- /dev/null +++ b/Llama3GRPOReasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164b8ffe9ee8f16b44a057ce464587a7a548cb09b547ed617f41ec745f30b45e +size 5599299520 diff --git a/Llama3GRPOReasoning.Q6_K.gguf b/Llama3GRPOReasoning.Q6_K.gguf new file mode 100644 index 0000000..ee3da8a --- /dev/null +++ b/Llama3GRPOReasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3856fdd1369138ae4798ea0d5897570de6462bccefd9dc289626e19267114ba0 +size 6596011968 diff --git a/Llama3GRPOReasoning.Q8_0.gguf b/Llama3GRPOReasoning.Q8_0.gguf new file mode 100644 index 0000000..ccfbe73 --- /dev/null +++ b/Llama3GRPOReasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa6cde490ea5c8b95f6295d98fa35d5dc74ce99d62b6a1d66e327d943eb3e10 +size 8540776384 diff --git a/Llama3GRPOReasoning.f16.gguf b/Llama3GRPOReasoning.f16.gguf new file mode 100644 index 0000000..82b4139 --- /dev/null +++ b/Llama3GRPOReasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6249e050ac4ad1a00c10e833ca9cf22b93382ddf0f12275e2b70660e4f9bbe +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bcf3d60 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: lordChipotle/Llama3GRPOReasoning +datasets: +- openai/gsm8k +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lordChipotle/Llama3GRPOReasoning + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3GRPOReasoning-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/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3GRPOReasoning-GGUF/resolve/main/Llama3GRPOReasoning.f16.gguf) | f16 | 16.2 | 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. + +