commit caf6afcbff9c3b1274a93cac94d4d789844e84eb Author: ModelHub XC Date: Tue Jun 23 11:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-8B-Thinking-R1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..451fb09 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Llama3.1-8B-Thinking-R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-8B-Thinking-R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-8B-Thinking-R1.IQ4_XS.gguf b/Llama3.1-8B-Thinking-R1.IQ4_XS.gguf new file mode 100644 index 0000000..89c42ed --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b11b9b8ec70d073eee168c18ebebfe6ef5ca234036bba11ef6c0d98d13568ef0 +size 4484368352 diff --git a/Llama3.1-8B-Thinking-R1.Q2_K.gguf b/Llama3.1-8B-Thinking-R1.Q2_K.gguf new file mode 100644 index 0000000..2dccb8c --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87daa789d83825c50aa82129b3cd98c7c19c3b69e6dc0b76e030a021e3f18b34 +size 3179136992 diff --git a/Llama3.1-8B-Thinking-R1.Q3_K_L.gguf b/Llama3.1-8B-Thinking-R1.Q3_K_L.gguf new file mode 100644 index 0000000..fc938b9 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46fd98cecf49b2bef91652e82628c28224f10bc971dae72d0f4907081095873f +size 4321961952 diff --git a/Llama3.1-8B-Thinking-R1.Q3_K_M.gguf b/Llama3.1-8B-Thinking-R1.Q3_K_M.gguf new file mode 100644 index 0000000..5c0bcbe --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea47084586b6d9ee1aafbbd9fba444ead83ad3667af345d9ac0236a1eacc537b +size 4018923488 diff --git a/Llama3.1-8B-Thinking-R1.Q3_K_S.gguf b/Llama3.1-8B-Thinking-R1.Q3_K_S.gguf new file mode 100644 index 0000000..58544f2 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0945cc4bd5315c86d5278b3e63a300987b3d8054dfc1285d712614ac60695d1d +size 3664504800 diff --git a/Llama3.1-8B-Thinking-R1.Q4_K_M.gguf b/Llama3.1-8B-Thinking-R1.Q4_K_M.gguf new file mode 100644 index 0000000..349b207 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c39757afebac353553ed0637b5bd24e8f89845df7427835f81dfc901a835b0 +size 4920739808 diff --git a/Llama3.1-8B-Thinking-R1.Q4_K_S.gguf b/Llama3.1-8B-Thinking-R1.Q4_K_S.gguf new file mode 100644 index 0000000..3f0e668 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10a80690ba5b0c027b21e763236fe5216e5f37b297c7778a8be7cd06b26079f +size 4692674528 diff --git a/Llama3.1-8B-Thinking-R1.Q5_K_M.gguf b/Llama3.1-8B-Thinking-R1.Q5_K_M.gguf new file mode 100644 index 0000000..b177fea --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09603a719066a9d7fde2468c1a14a42082b16fc6967226d79ab8f9852c90f6b2 +size 5732992992 diff --git a/Llama3.1-8B-Thinking-R1.Q5_K_S.gguf b/Llama3.1-8B-Thinking-R1.Q5_K_S.gguf new file mode 100644 index 0000000..d0ff3cd --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463c808663b2b9e4a991d59f97f173fa28b6ee1b02e024d602a0164fb4028a35 +size 5599299552 diff --git a/Llama3.1-8B-Thinking-R1.Q6_K.gguf b/Llama3.1-8B-Thinking-R1.Q6_K.gguf new file mode 100644 index 0000000..15a98b8 --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fcca813f39d56ab6096347473a5a5848fd4a8bdf68deb862be1d514f6f0705f +size 6596012000 diff --git a/Llama3.1-8B-Thinking-R1.Q8_0.gguf b/Llama3.1-8B-Thinking-R1.Q8_0.gguf new file mode 100644 index 0000000..b37cc8c --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a066b88c1816efaa450021d6403529651989c8cd7da8e79f5b4530065eb77e07 +size 8540776416 diff --git a/Llama3.1-8B-Thinking-R1.f16.gguf b/Llama3.1-8B-Thinking-R1.f16.gguf new file mode 100644 index 0000000..45fea1c --- /dev/null +++ b/Llama3.1-8B-Thinking-R1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b912e8fd44677dbd078c3417c32d7f499c1b11ce973d263ca3be949f78ac198b +size 16068896736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..981e9f7 --- /dev/null +++ b/README.md @@ -0,0 +1,86 @@ +--- +base_model: Jackrong/Llama3.1-8B-Thinking-R1 +datasets: +- unsloth/OpenMathReasoning-mini +- open-r1/DAPO-Math-17k-Processed +- Jackrong/ShareGPT-gpt-oss-120B-reasoning +- Jackrong/Chinese-Qwen3-235B-Thinking-Distill +- Jackrong/MultiReason-ChatAlpaca +language: +- en +- zh +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- thinking +- grpo +- r1 +- llama-cpp +- gguf +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Jackrong/Llama3.1-8B-Thinking-R1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-8B-Thinking-R1-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-i1-GGUF +## 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/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-8B-Thinking-R1-GGUF/resolve/main/Llama3.1-8B-Thinking-R1.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. + +