commit 58313ee3e8d0656b91b6042c2b52d811c813cfdb Author: ModelHub XC Date: Sat Sep 26 10:25:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d142e3b --- /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 +Self-Certainty-Llama-3.2-3B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Self-Certainty-Llama-3.2-3B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..924153a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-MATH +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TMLR-Group-HF/Self-Certainty-Llama-3.2-3B-Instruct-MATH + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Self-Certainty-Llama-3.2-3B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-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/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Self-Certainty-Llama-3.2-3B-Instruct-GGUF/resolve/main/Self-Certainty-Llama-3.2-3B-Instruct.f16.gguf) | f16 | 7.3 | 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. + + diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.IQ4_XS.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..f3736ae --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34d5fd113c9797bd049fbd4b44b3e0c853dbfa79b0f0c88dcbff6eea0e53aa1 +size 2050220768 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q2_K.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..33103ef --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711a46b650dbd536c74a3b5e9c6d624dcb532de2d4a1629d95a71b373a4bf169 +size 1493218016 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_L.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1c5c169 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17be297c49699ef8dd41fd68d5a4060739b499e218a3129815c4beb6d5046369 +size 1984645856 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..9120a1c --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac99cee9e92d5b375c8b93e11e708a072421c3977d3a7499d5cc18f428add79b +size 1856457440 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8c1efe6 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf608fa63b51e99b642ad6acb88d48c9a947509000e56c0f15143c4fb4d6326b +size 1712147168 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c4d091a --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14dbd0b78a209f13fd725b594c415605c208d40af5d48bf90b5c3cbf1a590405 +size 2241004256 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..85857ea --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f70ad309f3e7c5c033cd9363596e831182bb105f1086d3887d977faa6ef532a6 +size 2149827296 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_M.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..f2e595a --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f5b8bfa27383caf6ee636ff623ee4e55132336964431e3b1b3a88dde033630 +size 2593030880 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_S.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..7eeb112 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2acc74a6da721453cf293ace751521a8603d5f138ecf85d6dc6730eea5fcdf22 +size 2540389088 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q6_K.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c07d856 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a549ca54cde2e38f0e485af06da9987fe09b2e0cbde3f13f98cdc0bcdb3ca5b +size 2967059168 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.Q8_0.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..60e3199 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5cf13ba455cf70cecd833d952f978c445460981a987a7e935915f886aeecb3e +size 3840527072 diff --git a/Self-Certainty-Llama-3.2-3B-Instruct.f16.gguf b/Self-Certainty-Llama-3.2-3B-Instruct.f16.gguf new file mode 100644 index 0000000..51e5915 --- /dev/null +++ b/Self-Certainty-Llama-3.2-3B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9345ff044f09648d6fb52c81ae68cf2539b91757527d875a62093c6c12057365 +size 7221693152