commit 095999288a0a98d30efa3b623c1223fdc796c74f Author: ModelHub XC Date: Fri Sep 18 22:04:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2-1.2B-RAG-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e5b458d --- /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 +LFM2-1.2B-RAG.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-1.2B-RAG.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-1.2B-RAG.IQ4_XS.gguf b/LFM2-1.2B-RAG.IQ4_XS.gguf new file mode 100644 index 0000000..6985c77 --- /dev/null +++ b/LFM2-1.2B-RAG.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c3cecddaddbf42fc69b560083679c52493e929df5b3969af289219dd54605b +size 668619488 diff --git a/LFM2-1.2B-RAG.Q2_K.gguf b/LFM2-1.2B-RAG.Q2_K.gguf new file mode 100644 index 0000000..189ed01 --- /dev/null +++ b/LFM2-1.2B-RAG.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edfe093e28619bef27bddcee61a0e42dcc0e22f3f0c9f27c7ed79a5ccd483749 +size 483398368 diff --git a/LFM2-1.2B-RAG.Q3_K_L.gguf b/LFM2-1.2B-RAG.Q3_K_L.gguf new file mode 100644 index 0000000..6fa0b5f --- /dev/null +++ b/LFM2-1.2B-RAG.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e8fbf53d8405e4efc0246937d52bbf324bec5a72c240ef7559ac7d93ef4b17 +size 635474656 diff --git a/LFM2-1.2B-RAG.Q3_K_M.gguf b/LFM2-1.2B-RAG.Q3_K_M.gguf new file mode 100644 index 0000000..30f5018 --- /dev/null +++ b/LFM2-1.2B-RAG.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438626deb8b952b5e6f40032671fa97829daa495fcacb9fe8128592c03df4a5e +size 600347360 diff --git a/LFM2-1.2B-RAG.Q3_K_S.gguf b/LFM2-1.2B-RAG.Q3_K_S.gguf new file mode 100644 index 0000000..564291a --- /dev/null +++ b/LFM2-1.2B-RAG.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccda038232e34da45fb95eae54a99b6d6a54e6f6eb3ef86d685a6e76babcbffe +size 558158560 diff --git a/LFM2-1.2B-RAG.Q4_K_M.gguf b/LFM2-1.2B-RAG.Q4_K_M.gguf new file mode 100644 index 0000000..75cfc31 --- /dev/null +++ b/LFM2-1.2B-RAG.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3197d784dedd44aa204dab7ffcc7fa6ccfc38988bd72ecb7a200f195bd0d6d1 +size 730895072 diff --git a/LFM2-1.2B-RAG.Q4_K_S.gguf b/LFM2-1.2B-RAG.Q4_K_S.gguf new file mode 100644 index 0000000..aa19c4b --- /dev/null +++ b/LFM2-1.2B-RAG.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0bdcd51300a7a57a91fbf1d123ddd9947ed9f4f0fd353992864f6bf344db90 +size 700469984 diff --git a/LFM2-1.2B-RAG.Q5_K_M.gguf b/LFM2-1.2B-RAG.Q5_K_M.gguf new file mode 100644 index 0000000..bfa0cc9 --- /dev/null +++ b/LFM2-1.2B-RAG.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8e32a700e5d4750ec5041fc4fd373868b7ed670c507e2206bd20b9422ba061 +size 843354848 diff --git a/LFM2-1.2B-RAG.Q5_K_S.gguf b/LFM2-1.2B-RAG.Q5_K_S.gguf new file mode 100644 index 0000000..3224e8f --- /dev/null +++ b/LFM2-1.2B-RAG.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61bbe875a5e6806a8a1f4dff779f945643637ed78d3771070fa645be786f52f4 +size 825250528 diff --git a/LFM2-1.2B-RAG.Q6_K.gguf b/LFM2-1.2B-RAG.Q6_K.gguf new file mode 100644 index 0000000..412d400 --- /dev/null +++ b/LFM2-1.2B-RAG.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9de3b058ec4489bf6132b96be81f4f4e410cdeccea9eac77e69f54792891384c +size 962843360 diff --git a/LFM2-1.2B-RAG.Q8_0.gguf b/LFM2-1.2B-RAG.Q8_0.gguf new file mode 100644 index 0000000..cee462b --- /dev/null +++ b/LFM2-1.2B-RAG.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96db5d21a7ef6206766e1fa725c2a5ab9df47c75e41b5d400e0277cfcb7edb91 +size 1246253792 diff --git a/LFM2-1.2B-RAG.f16.gguf b/LFM2-1.2B-RAG.f16.gguf new file mode 100644 index 0000000..e1f34f7 --- /dev/null +++ b/LFM2-1.2B-RAG.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92808db53371eb007d11e3a62c391a410884516b782a7329391912c9bca7ee10 +size 2343326432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..319f636 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: LiquidAI/LFM2-1.2B-RAG +language: +- en +- ar +- zh +- fr +- de +- ja +- ko +- es +library_name: transformers +license: other +license_link: LICENSE +license_name: lfm1.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- liquid +- lfm2 +- edge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/LiquidAI/LFM2-1.2B-RAG + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-1.2B-RAG-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2-1.2B-RAG-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/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q2_K.gguf) | Q2_K | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-1.2B-RAG-GGUF/resolve/main/LFM2-1.2B-RAG.f16.gguf) | f16 | 2.4 | 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. + +