commit 36d1abeb1f2188cedea931ca33eacc67012eb30e Author: ModelHub XC Date: Sun Jun 21 14:29:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.2-1B-STEM-Full-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7de1414 --- /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 +Llama3.2-1B-STEM-Full.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.2-1B-STEM-Full.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.2-1B-STEM-Full.IQ4_XS.gguf b/Llama3.2-1B-STEM-Full.IQ4_XS.gguf new file mode 100644 index 0000000..195a4d1 --- /dev/null +++ b/Llama3.2-1B-STEM-Full.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd74df96e9e96eb8dcc99bc41c28934c10ae4cdfb5f965c7c1eb6d6de3435d2d +size 748385696 diff --git a/Llama3.2-1B-STEM-Full.Q2_K.gguf b/Llama3.2-1B-STEM-Full.Q2_K.gguf new file mode 100644 index 0000000..7e3a0da --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d10a8db488d7e71cb6412dc653f82820ce00af106f232a3923135d84b4fee3 +size 580875680 diff --git a/Llama3.2-1B-STEM-Full.Q3_K_L.gguf b/Llama3.2-1B-STEM-Full.Q3_K_L.gguf new file mode 100644 index 0000000..d7eb42d --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e9a4fb6c03d6892677ef88af7a915ddbf34aa302cbd83207bab4f1ab3321bce +size 732525984 diff --git a/Llama3.2-1B-STEM-Full.Q3_K_M.gguf b/Llama3.2-1B-STEM-Full.Q3_K_M.gguf new file mode 100644 index 0000000..3a297cd --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a943360970cd1b939853c270e8dc241e262236509d702499868776a6f2c379 +size 690845088 diff --git a/Llama3.2-1B-STEM-Full.Q3_K_S.gguf b/Llama3.2-1B-STEM-Full.Q3_K_S.gguf new file mode 100644 index 0000000..63990ea --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:110b61a61bbcc6e220e16e2efb2a15edeaaeff07a8ce7748dc5819a8cf3e4164 +size 641693088 diff --git a/Llama3.2-1B-STEM-Full.Q4_K_M.gguf b/Llama3.2-1B-STEM-Full.Q4_K_M.gguf new file mode 100644 index 0000000..b6b33a6 --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e4c21d8d19d99ac6ca71247bc952a34c7e7f92c2ba8b5bfabbb714c7c738d3 +size 807695776 diff --git a/Llama3.2-1B-STEM-Full.Q4_K_S.gguf b/Llama3.2-1B-STEM-Full.Q4_K_S.gguf new file mode 100644 index 0000000..3e0b0b5 --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89d46af419e94d12e87dec173f5f6b9f85d1f5730f157d6e3a7729438bdb23f +size 775648672 diff --git a/Llama3.2-1B-STEM-Full.Q5_K_M.gguf b/Llama3.2-1B-STEM-Full.Q5_K_M.gguf new file mode 100644 index 0000000..5363457 --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b743481ed95cfd328950eb69c5fb14022879e9954db6598b17386c670bd169 +size 911504800 diff --git a/Llama3.2-1B-STEM-Full.Q5_K_S.gguf b/Llama3.2-1B-STEM-Full.Q5_K_S.gguf new file mode 100644 index 0000000..2a806c2 --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551b0ddd24f3e3876ddf062baa82b3be21b2dee31cb5e8e37fd2973631866ce1 +size 892564896 diff --git a/Llama3.2-1B-STEM-Full.Q6_K.gguf b/Llama3.2-1B-STEM-Full.Q6_K.gguf new file mode 100644 index 0000000..d206e0b --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2aa63037b01b11507f00efcb8097d03fb5d0fd44e3083fd33b84a7740116942 +size 1021801888 diff --git a/Llama3.2-1B-STEM-Full.Q8_0.gguf b/Llama3.2-1B-STEM-Full.Q8_0.gguf new file mode 100644 index 0000000..959c9ec --- /dev/null +++ b/Llama3.2-1B-STEM-Full.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5147dc32cbb1711c1f8b0d6a617a0a95bfe2d4bcd295cd3df46813dc81d9dd +size 1321084320 diff --git a/Llama3.2-1B-STEM-Full.f16.gguf b/Llama3.2-1B-STEM-Full.f16.gguf new file mode 100644 index 0000000..dd14faf --- /dev/null +++ b/Llama3.2-1B-STEM-Full.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f945228d6d2b58eaa3ecaa93c9187394eb4e98624b3fecaffbd3c4588f1a4d8 +size 2479596960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e2944c5 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: theprint/Llama3.2-1B-STEM-Full +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/theprint/Llama3.2-1B-STEM-Full + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.2-1B-STEM-Full-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-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/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.2-1B-STEM-Full-GGUF/resolve/main/Llama3.2-1B-STEM-Full.f16.gguf) | f16 | 2.6 | 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. + +