commit 6fb1123c50dd4c6a18512320739d7e6020b118be Author: ModelHub XC Date: Fri Jul 3 00:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33a20d4 --- /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 +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.IQ4_XS.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.IQ4_XS.gguf new file mode 100644 index 0000000..812b619 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d99972be1c72d0fad00a5ba520f8158e0897c222799326213493b47378f564 +size 1840907200 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q2_K.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q2_K.gguf new file mode 100644 index 0000000..a5f1f48 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0105b98de5aaac926f48a1fab40c29d9122f90725e96640a97184a91700c750a +size 1363936192 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_L.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_L.gguf new file mode 100644 index 0000000..975a8c1 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6145fc942277e389023c511c156cd6f9802cb7691e2d79677d0582fff7eae4c +size 1815348160 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_M.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_M.gguf new file mode 100644 index 0000000..612c4de --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc69eec258424ca0bf850e498d35a2873733b179425b8cf316534749f444e9a8 +size 1687159744 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_S.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_S.gguf new file mode 100644 index 0000000..d450fdc --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b38374b3d51a0a2043526b973b4e16d78b2251734ee15ff9861798add3c5a6ec +size 1542849472 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_M.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_M.gguf new file mode 100644 index 0000000..a119573 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8887701c5e9b1a0d15c79cd5886e4a27667aad244c47b6c7cd6a81a2ef0244ed +size 2019378112 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_S.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_S.gguf new file mode 100644 index 0000000..71a773d --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0c3f7febdb34ea7ba414ebbe9e6b50c9e85c67378c27ff680f0f4d16df3209 +size 1928201152 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_M.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_M.gguf new file mode 100644 index 0000000..65916d3 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1edfc63c157020679365fc766f6b884b94149f308f56cdb02a8935ca335143 +size 2322154432 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_S.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_S.gguf new file mode 100644 index 0000000..1be39c5 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f925048633e0a54a95d62509ce6ee5bcc46afcdfa75d864d421e634516b622d2 +size 2269512640 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q6_K.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q6_K.gguf new file mode 100644 index 0000000..5ba759d --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44564217f6d7e6608ce2164de84db9838c6f0ca07a4584a61280862efa73a64e +size 2643854272 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q8_0.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q8_0.gguf new file mode 100644 index 0000000..65bb536 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52358f961c2a2f4cc25d21c1aabe6f1e46d48c9543e18373f1326155ad90368 +size 3421899712 diff --git a/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.f16.gguf b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.f16.gguf new file mode 100644 index 0000000..62d8154 --- /dev/null +++ b/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ba7ad6640a372fd7a519e763c6b208369d19a6c6091eb6be258096c18ed50c +size 6433688512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..065046c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: DavidAU/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- reasoning +- thinking +- cot +- deepseek +- Llama 3.2 +- 128k context +- fine tune +- llama-3 +- llama-3.2 +--- +## About + + + + + + +static quants of https://huggingface.co/DavidAU/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-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/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III-GGUF/resolve/main/Deep-Reasoning-Llama-3.2-JametMini-3B-MK.III.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. + +