commit c4945db87871a3dbd6732551ab3244da02b4dddb Author: ModelHub XC Date: Mon Aug 17 03:41:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3633c1 --- /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-Bespoke-Thought.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Bespoke-Thought.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Bespoke-Thought.IQ4_XS.gguf b/Llama-3.2-3B-Bespoke-Thought.IQ4_XS.gguf new file mode 100644 index 0000000..95b94b2 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:080fd7c9360efe68cdd2c2549bf0a20a4558ab61ea4128c162121fb4254116f8 +size 1840907392 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q2_K.gguf b/Llama-3.2-3B-Bespoke-Thought.Q2_K.gguf new file mode 100644 index 0000000..9ff872d --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad36da291493ccf0cfea489c72780c67559cc6ada79f95d6ab9d67d96d941cf8 +size 1363936384 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q3_K_L.gguf b/Llama-3.2-3B-Bespoke-Thought.Q3_K_L.gguf new file mode 100644 index 0000000..f74d3cf --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1405aa040fe417f36ac7698371334a78ae330a2be41db8ffaf88601b769a40f +size 1815348352 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q3_K_M.gguf b/Llama-3.2-3B-Bespoke-Thought.Q3_K_M.gguf new file mode 100644 index 0000000..020462f --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4335561324c523bb858248039e094b1976f4dc43682f124ed8de48292116c6a +size 1687159936 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q3_K_S.gguf b/Llama-3.2-3B-Bespoke-Thought.Q3_K_S.gguf new file mode 100644 index 0000000..10ca63a --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c143cdf1079fa78601a81e6f19959b3550d1fbde87b6a4bcf76084159e3f4cd6 +size 1542849664 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q4_K_M.gguf b/Llama-3.2-3B-Bespoke-Thought.Q4_K_M.gguf new file mode 100644 index 0000000..b733d5f --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c03dcc9fbc2d5e7125965ce77ecb302bcaa6f598349f98b0d14d362c632514e +size 2019378304 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q4_K_S.gguf b/Llama-3.2-3B-Bespoke-Thought.Q4_K_S.gguf new file mode 100644 index 0000000..326eb38 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becd51e9516ef6b57cabc038202e39e7dbb338f467128ce5b564618761d879b8 +size 1928201344 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q5_K_M.gguf b/Llama-3.2-3B-Bespoke-Thought.Q5_K_M.gguf new file mode 100644 index 0000000..cc4b9f5 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ce4cd0f58cf7ff8129675ad5be2f9f381190b3dc7121119236e4a1110ed1d40 +size 2322154624 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q5_K_S.gguf b/Llama-3.2-3B-Bespoke-Thought.Q5_K_S.gguf new file mode 100644 index 0000000..650c492 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51bc4466eb0576a9844d07c7e8b3e6cb42786658955f721fdcd6945daac471eb +size 2269512832 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q6_K.gguf b/Llama-3.2-3B-Bespoke-Thought.Q6_K.gguf new file mode 100644 index 0000000..e4173f2 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be71b2fa4d523c195d113c69009d011b78fba82c9911e309f9c1391cffc3d93 +size 2643854464 diff --git a/Llama-3.2-3B-Bespoke-Thought.Q8_0.gguf b/Llama-3.2-3B-Bespoke-Thought.Q8_0.gguf new file mode 100644 index 0000000..8f695d4 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8411fbeb8cb345e95a5a50f41d5d81be2c581df8dc025f480f5a980645c126e +size 3421899904 diff --git a/Llama-3.2-3B-Bespoke-Thought.f16.gguf b/Llama-3.2-3B-Bespoke-Thought.f16.gguf new file mode 100644 index 0000000..235b182 --- /dev/null +++ b/Llama-3.2-3B-Bespoke-Thought.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c827918d3a6506f42b5407223e7117f9bf502fa645b8f49db03452c8c9139f89 +size 6433688704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..456314e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: bunnycore/Llama-3.2-3B-Bespoke-Thought +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/Llama-3.2-3B-Bespoke-Thought + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-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/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Bespoke-Thought-GGUF/resolve/main/Llama-3.2-3B-Bespoke-Thought.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. + +