commit 48f88f7f179c59a0e7efc10d48fb3d19ebb7962e Author: ModelHub XC Date: Tue Aug 4 17:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c615d37 --- /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 +Llama-3.2-1B-FC-v1.4-think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-FC-v1.4-think.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-FC-v1.4-think.IQ4_XS.gguf b/Llama-3.2-1B-FC-v1.4-think.IQ4_XS.gguf new file mode 100644 index 0000000..9e11dea --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec4b9c6330f97b84a41d0939d99cf2304a087171b9630fac6fb6ce498ed80768 +size 748384544 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q2_K.gguf b/Llama-3.2-1B-FC-v1.4-think.Q2_K.gguf new file mode 100644 index 0000000..7cdac26 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43dacc22a039dd2e9fbe6c7471ca62b4b8e47890a1eed055859b0025182f79c +size 580874528 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q3_K_L.gguf b/Llama-3.2-1B-FC-v1.4-think.Q3_K_L.gguf new file mode 100644 index 0000000..423c87b --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ea9ccfc4206bee3ff9680943de2c5a1276a258576fff3f4d98b46410fd35c8 +size 732524832 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q3_K_M.gguf b/Llama-3.2-1B-FC-v1.4-think.Q3_K_M.gguf new file mode 100644 index 0000000..dc70138 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0324487f1456aff81ddbaef81e87d13d7cc670e2b14cf7807bb1caf12cb68553 +size 690843936 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q3_K_S.gguf b/Llama-3.2-1B-FC-v1.4-think.Q3_K_S.gguf new file mode 100644 index 0000000..43edbd0 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4ecf9fe6bc0dc6e876470312ca5896b7597c7e6ff5c0ce43d3159a27a5863d +size 641691936 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q4_K_M.gguf b/Llama-3.2-1B-FC-v1.4-think.Q4_K_M.gguf new file mode 100644 index 0000000..a2aea00 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45c62e79376fe68961727ec2401d42b2cb149d06f27abe3c64ce0c49d610270 +size 807694624 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q4_K_S.gguf b/Llama-3.2-1B-FC-v1.4-think.Q4_K_S.gguf new file mode 100644 index 0000000..3b62a6a --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9071da653b9a6ac6e28e2a7a2e3275c44b2097a2adac9f2d2a181f1b7142e15 +size 775647520 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q5_K_M.gguf b/Llama-3.2-1B-FC-v1.4-think.Q5_K_M.gguf new file mode 100644 index 0000000..81d5cf1 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c976235f365b1e23a5418712c26e39e801e0f19966e1437706054b6459ba454 +size 911503648 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q5_K_S.gguf b/Llama-3.2-1B-FC-v1.4-think.Q5_K_S.gguf new file mode 100644 index 0000000..c91f7ca --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea82a0dbe90b3a7d2d55433740301bb4b5a388803901cbae98d5d751d34645c +size 892563744 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q6_K.gguf b/Llama-3.2-1B-FC-v1.4-think.Q6_K.gguf new file mode 100644 index 0000000..43e99a5 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3ac4ba2bb0bae4ce9438892dd27a62cf9bd107a3173c2ef60981591a11ce14 +size 1021800736 diff --git a/Llama-3.2-1B-FC-v1.4-think.Q8_0.gguf b/Llama-3.2-1B-FC-v1.4-think.Q8_0.gguf new file mode 100644 index 0000000..2f2ec1b --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8176b303a7bf0309616f896b0015ddb288c69539e1a47b0a0551680422882a +size 1321083168 diff --git a/Llama-3.2-1B-FC-v1.4-think.f16.gguf b/Llama-3.2-1B-FC-v1.4-think.f16.gguf new file mode 100644 index 0000000..c6011f0 --- /dev/null +++ b/Llama-3.2-1B-FC-v1.4-think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c46eb0ee5a15d91aa5c245b5ad6bc89ab82d30aadbc2917e3b109f91150e52c +size 2479595808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6a4116f --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: AymanTarig/Llama-3.2-1B-FC-v1.4-think +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AymanTarig/Llama-3.2-1B-FC-v1.4-think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-1B-FC-v1.4-think-GGUF).*** + +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/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-FC-v1.4-think-GGUF/resolve/main/Llama-3.2-1B-FC-v1.4-think.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. + +