commit 78e903aac59abcb181bef1d73b9d531835908a9a Author: ModelHub XC Date: Wed Jun 17 23:30:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CodeThink-8B-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..79e0c8c --- /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 +CodeThink-8B-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CodeThink-8B-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CodeThink-8B-GRPO.IQ4_XS.gguf b/CodeThink-8B-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..d6df4d2 --- /dev/null +++ b/CodeThink-8B-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea86e72ff0a98821c89d20ea297cf239b21aaa0894583cab73152c8202f0ea3 +size 4484368320 diff --git a/CodeThink-8B-GRPO.Q2_K.gguf b/CodeThink-8B-GRPO.Q2_K.gguf new file mode 100644 index 0000000..d58d75a --- /dev/null +++ b/CodeThink-8B-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e22e5d99a17a1d5d7548c6c0f2c85f34b1435897383059911dc20d247327dbc +size 3179136960 diff --git a/CodeThink-8B-GRPO.Q3_K_L.gguf b/CodeThink-8B-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..89a347c --- /dev/null +++ b/CodeThink-8B-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bda02e273d921c4eb38d961fec96f6d2d3ec41f943538c3ebb0f207f396397e +size 4321961920 diff --git a/CodeThink-8B-GRPO.Q3_K_M.gguf b/CodeThink-8B-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..c17c065 --- /dev/null +++ b/CodeThink-8B-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c7a66d4ee196676e8e7ac8884bea4727dc3b86d49170d2e06c59ef856115c4 +size 4018923456 diff --git a/CodeThink-8B-GRPO.Q3_K_S.gguf b/CodeThink-8B-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..3a01776 --- /dev/null +++ b/CodeThink-8B-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c70bd8b1ddd0980161b4ca5d4a4edcc700ac0568210023dd9a7e7a29f0ed5f +size 3664504768 diff --git a/CodeThink-8B-GRPO.Q4_K_M.gguf b/CodeThink-8B-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..edfc49a --- /dev/null +++ b/CodeThink-8B-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9c8bb7d3982f797178327f06681ad29f2d11652400658de2789a4e48a7532c4 +size 4920739776 diff --git a/CodeThink-8B-GRPO.Q4_K_S.gguf b/CodeThink-8B-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..784b90d --- /dev/null +++ b/CodeThink-8B-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62a67ccf45654825f35a67311b6bd328961175f3ff212f90305e695f4d7e6b87 +size 4692674496 diff --git a/CodeThink-8B-GRPO.Q5_K_M.gguf b/CodeThink-8B-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..c1ede9c --- /dev/null +++ b/CodeThink-8B-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d013e360ee3c9cdeacfa701c2a3b827e245164d4a17b85564704ca223fe0b68e +size 5732992960 diff --git a/CodeThink-8B-GRPO.Q5_K_S.gguf b/CodeThink-8B-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..031d13f --- /dev/null +++ b/CodeThink-8B-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f463ecc0334e224df3fdd99398b8ee9b62ebe33be60071a49590395d00d0ae2 +size 5599299520 diff --git a/CodeThink-8B-GRPO.Q6_K.gguf b/CodeThink-8B-GRPO.Q6_K.gguf new file mode 100644 index 0000000..8c36488 --- /dev/null +++ b/CodeThink-8B-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7acc9aa216c4060c9db6444df168a614593368ece530031bea07302f6ee5b48f +size 6596011968 diff --git a/CodeThink-8B-GRPO.Q8_0.gguf b/CodeThink-8B-GRPO.Q8_0.gguf new file mode 100644 index 0000000..194dcae --- /dev/null +++ b/CodeThink-8B-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614a2afb80c4085fd4599c53ac2afe2c9e0bea0b0964eadeb17091d7f09c6eff +size 8540776384 diff --git a/CodeThink-8B-GRPO.f16.gguf b/CodeThink-8B-GRPO.f16.gguf new file mode 100644 index 0000000..4fcbe14 --- /dev/null +++ b/CodeThink-8B-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa3686c188a154c431a064a3f11aef27a54a3d745b3d27550b089284da6e0e7 +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..41dce7e --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: theprint/CodeThink-8B-GRPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/theprint/CodeThink-8B-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CodeThink-8B-GRPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeThink-8B-GRPO-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/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CodeThink-8B-GRPO-GGUF/resolve/main/CodeThink-8B-GRPO.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. + +