commit 1e52d7186f21b1b4455a21d8c27f097fb2b1e8c2 Author: ModelHub XC Date: Thu Oct 8 06:25:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLAMA3-ReasoningCOT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..98c2421 --- /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 +LLAMA3-ReasoningCOT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLAMA3-ReasoningCOT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLAMA3-ReasoningCOT.IQ4_XS.gguf b/LLAMA3-ReasoningCOT.IQ4_XS.gguf new file mode 100644 index 0000000..8f15880 --- /dev/null +++ b/LLAMA3-ReasoningCOT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3358e32ed6bbb2c9880ea6e0aa87a858047c9d6ec713d390888ae7f6af36cd30 +size 4484368384 diff --git a/LLAMA3-ReasoningCOT.Q2_K.gguf b/LLAMA3-ReasoningCOT.Q2_K.gguf new file mode 100644 index 0000000..e7acdda --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1718a87fdfba53c8ea1338f20087142c17aae6276ae61b1e0c46893e888fa0e5 +size 3179137024 diff --git a/LLAMA3-ReasoningCOT.Q3_K_L.gguf b/LLAMA3-ReasoningCOT.Q3_K_L.gguf new file mode 100644 index 0000000..e7daac6 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78010562440a3b66a0c8159b5513cef32abd7f9674e59e51096eb1e6f0597e2 +size 4321961984 diff --git a/LLAMA3-ReasoningCOT.Q3_K_M.gguf b/LLAMA3-ReasoningCOT.Q3_K_M.gguf new file mode 100644 index 0000000..0a68d3e --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a82b632af48194a87458232b6e4b671871b8d6637da7c359b3b35d846c4eff +size 4018923520 diff --git a/LLAMA3-ReasoningCOT.Q3_K_S.gguf b/LLAMA3-ReasoningCOT.Q3_K_S.gguf new file mode 100644 index 0000000..c0561da --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd698d6f9cc27338d98b968bb4411455c2a1f60243f9d1b0ac0b9d4e0953624e +size 3664504832 diff --git a/LLAMA3-ReasoningCOT.Q4_K_M.gguf b/LLAMA3-ReasoningCOT.Q4_K_M.gguf new file mode 100644 index 0000000..3206d38 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70712abaea628e2f6ed0f0d3e9244cdd38e6f8a39ac2a37d87ded844fe7069e9 +size 4920739840 diff --git a/LLAMA3-ReasoningCOT.Q4_K_S.gguf b/LLAMA3-ReasoningCOT.Q4_K_S.gguf new file mode 100644 index 0000000..9d8f4c4 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6246760066fc991b66df0afb3dae2a6eb8eda7349aa5a0aed89546eac2de27b9 +size 4692674560 diff --git a/LLAMA3-ReasoningCOT.Q5_K_M.gguf b/LLAMA3-ReasoningCOT.Q5_K_M.gguf new file mode 100644 index 0000000..2809de5 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bdd6be140ab88ad033c1ee535106d1b3f3862857215ddd990ed4098bf349014 +size 5732993024 diff --git a/LLAMA3-ReasoningCOT.Q5_K_S.gguf b/LLAMA3-ReasoningCOT.Q5_K_S.gguf new file mode 100644 index 0000000..99b4ae7 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78736ba049179bbf7f3a61e5fdc49e62fdf15d1bd8d2d498a7be1d1e5fbdcbba +size 5599299584 diff --git a/LLAMA3-ReasoningCOT.Q6_K.gguf b/LLAMA3-ReasoningCOT.Q6_K.gguf new file mode 100644 index 0000000..b4b1890 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5433d1126436d9c50a14273fa222d24934925853674efea617a5e05a924e5534 +size 6596012032 diff --git a/LLAMA3-ReasoningCOT.Q8_0.gguf b/LLAMA3-ReasoningCOT.Q8_0.gguf new file mode 100644 index 0000000..27d37e0 --- /dev/null +++ b/LLAMA3-ReasoningCOT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6ce4f380fd8525a00b9171f05a614454612f095974840451833a5255b468c6 +size 8540776448 diff --git a/LLAMA3-ReasoningCOT.f16.gguf b/LLAMA3-ReasoningCOT.f16.gguf new file mode 100644 index 0000000..6240ae8 --- /dev/null +++ b/LLAMA3-ReasoningCOT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea831370c1210ece3620160cc9f04aa3f6a913a216ace7562f03ffe5c1298422 +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01da4f5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: alibidaran/LLAMA3-ReasoningCOT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/alibidaran/LLAMA3-ReasoningCOT + + +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/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLAMA3-ReasoningCOT-GGUF/resolve/main/LLAMA3-ReasoningCOT.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. + +