commit 9522985149c658d99eef3c0dd2280cabce3e5007 Author: ModelHub XC Date: Sun Apr 12 16:01:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e92c086 --- /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-3.2-3B-Instruct-WriterV2-2E.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-WriterV2-2E.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.IQ4_XS.gguf new file mode 100644 index 0000000..ac3fc0d --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef02394f3ff06cfcda5d01bfa71632f3c5b81905fbb2bf1bd2702a6cd9ec6dd0 +size 1840906848 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q2_K.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q2_K.gguf new file mode 100644 index 0000000..ba9ead0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e60baa958bf17fd1cd23eafe6d2f5c1266dccc88ce92f3fe9f96b0d162b5b9 +size 1363935840 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_L.gguf new file mode 100644 index 0000000..3ab3c4d --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e26e96d449f5eb8708d607eb14f3db925929f63ee565e6cf61989db52d0013 +size 1815347808 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_M.gguf new file mode 100644 index 0000000..b7417ef --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f12c05b01a28681bc5abdadecaf97fb358059f04393d824d795f9142cbacb04 +size 1687159392 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_S.gguf new file mode 100644 index 0000000..1d65605 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894ed3097c9e22b28766667f3cb27042f63b343f2e8d9ca0718da239e89a66d9 +size 1542849120 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_M.gguf new file mode 100644 index 0000000..c0767b6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b765442dc8b883977483cf9ee500904a693ef8f7a7c48dce59ee0037ba64ec +size 2019377760 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_S.gguf new file mode 100644 index 0000000..906af81 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c5f2b789426e65937abba213ab5f8054592fd2dbffeb7a9d4facf205f38e082 +size 1928200800 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_M.gguf new file mode 100644 index 0000000..d78964d --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052cd01f54f6f2e10eff36e8b9a6cce1f02ed2436d2981eb9345ed109553b84a +size 2322154080 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_S.gguf new file mode 100644 index 0000000..09af7a4 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8296a3ab077412db408b529fb4cee38d47ebd0b726c4b98191f22adb7b2756 +size 2269512288 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q6_K.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q6_K.gguf new file mode 100644 index 0000000..bb0f246 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65eb06dee967ed687620156e65463eb0dc796c4d73b1a39908ac1a23a48ad24d +size 2643853920 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.Q8_0.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.Q8_0.gguf new file mode 100644 index 0000000..635b3b7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85d13042c6e04fde6b240ea53957c65a4dfb0fa683ab1257efb47a434c43315 +size 3421899360 diff --git a/Llama-3.2-3B-Instruct-WriterV2-2E.f16.gguf b/Llama-3.2-3B-Instruct-WriterV2-2E.f16.gguf new file mode 100644 index 0000000..fc8da8c --- /dev/null +++ b/Llama-3.2-3B-Instruct-WriterV2-2E.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dd64db755ee42fd31ad5c7c9fa592861a107d698027f484c7af45db8609bbdd +size 6433688160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..72d2903 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Biscotto58/Llama-3.2-3B-Instruct-WriterV2-2E +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Biscotto58/Llama-3.2-3B-Instruct-WriterV2-2E + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-WriterV2-2E-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-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-WriterV2-2E-GGUF/resolve/main/Llama-3.2-3B-Instruct-WriterV2-2E.f16.gguf) | f16 | 6.5 | 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. + +