commit 821bfa05b8f04a4287f0920de3cf4a3103a50d18 Author: ModelHub XC Date: Mon Sep 7 01:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PARD-Llama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1419f6f --- /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 +PARD-Llama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PARD-Llama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PARD-Llama-3.2-1B.IQ4_XS.gguf b/PARD-Llama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..cbdb8ca --- /dev/null +++ b/PARD-Llama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfb621af29a6b248927879ec6ae61427aca1e6f58a7050d67fd6366a6a3f1f18 +size 887927008 diff --git a/PARD-Llama-3.2-1B.Q2_K.gguf b/PARD-Llama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..c173e5a --- /dev/null +++ b/PARD-Llama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1477bc77cfa1af6ef09b68c2286b924e20c098688eda163d24defe09a2418fc6 +size 667062496 diff --git a/PARD-Llama-3.2-1B.Q3_K_L.gguf b/PARD-Llama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..9354a92 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37c9e818863d72670e696de094330537172dc5195764f0a1430d8fc3241cb57b +size 845390048 diff --git a/PARD-Llama-3.2-1B.Q3_K_M.gguf b/PARD-Llama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..2b496af --- /dev/null +++ b/PARD-Llama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bec8e148a4b03d0b1e86430f299f8cbf8851bc6ec440455e41d09ea5e6b6d47 +size 803709152 diff --git a/PARD-Llama-3.2-1B.Q3_K_S.gguf b/PARD-Llama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..36e2985 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a95b7d4f7da664bb2c32b54ea2a6033410b54395b0c740d0e95abf8b1383a24a +size 754557152 diff --git a/PARD-Llama-3.2-1B.Q4_K_M.gguf b/PARD-Llama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..e57f993 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b9d7a0da99aa6ac05ee16cdc054cff47ce1e2005e9ea5202a3722a8e8c02d4 +size 955445472 diff --git a/PARD-Llama-3.2-1B.Q4_K_S.gguf b/PARD-Llama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..7525306 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:670f0f3a0fb1109837b033cec435d2ab8af9972460860c7110887b5ccf18a902 +size 923398368 diff --git a/PARD-Llama-3.2-1B.Q5_K_M.gguf b/PARD-Llama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..dc01cf1 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e110fe36268ef617cc4bfc79451fe0160bf7ea45fadb7668010172a0494c0edf +size 1092088032 diff --git a/PARD-Llama-3.2-1B.Q5_K_S.gguf b/PARD-Llama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..018b18e --- /dev/null +++ b/PARD-Llama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01108b490d3f5116cd69f731c52485c9db4478fd3c2358f33b479e00d76663d4 +size 1073148128 diff --git a/PARD-Llama-3.2-1B.Q6_K.gguf b/PARD-Llama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..8f1298a --- /dev/null +++ b/PARD-Llama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29223792107b302ed2f6fac66da4b02143f9d7548a0ec696514bb8b89e49371 +size 1237270752 diff --git a/PARD-Llama-3.2-1B.Q8_0.gguf b/PARD-Llama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..026bd13 --- /dev/null +++ b/PARD-Llama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c350a5c1b1e368f463203ff7997b08c8dbf9284e01de6837675f81208e520926 +size 1600168160 diff --git a/PARD-Llama-3.2-1B.f16.gguf b/PARD-Llama-3.2-1B.f16.gguf new file mode 100644 index 0000000..776d21f --- /dev/null +++ b/PARD-Llama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5fe360ee1707d9e74e3256ec200ce7d9a5a34862cdf757cffdd2370db8a389 +size 3004932320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2629047 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: amd/PARD-Llama-3.2-1B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- vllm_ci +--- +## About + + + + + + + + + +static quants of https://huggingface.co/amd/PARD-Llama-3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PARD-Llama-3.2-1B-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/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PARD-Llama-3.2-1B-GGUF/resolve/main/PARD-Llama-3.2-1B.f16.gguf) | f16 | 3.1 | 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. + +