commit 2e5400c1f8fbd93d9aefbf337d56ae27120a9404 Author: ModelHub XC Date: Sun Jul 12 01:04:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2.5-8B-A1B-Coder-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5aedddd --- /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 +LFM2.5-8B-A1B-Coder.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.f16.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2.5-8B-A1B-Coder.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2.5-8B-A1B-Coder.IQ4_XS.gguf b/LFM2.5-8B-A1B-Coder.IQ4_XS.gguf new file mode 100644 index 0000000..8bef065 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e73d6cea7be80c541a3ac85708cfd7ca88ea7e66a31cf1c90e47344af9f031d5 +size 4611239104 diff --git a/LFM2.5-8B-A1B-Coder.Q2_K.gguf b/LFM2.5-8B-A1B-Coder.Q2_K.gguf new file mode 100644 index 0000000..a254e12 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4429f4ca7ce0395a759183a7df2abe1b00dad020b703b6b95a88d3bac234ba76 +size 3190435008 diff --git a/LFM2.5-8B-A1B-Coder.Q3_K_L.gguf b/LFM2.5-8B-A1B-Coder.Q3_K_L.gguf new file mode 100644 index 0000000..1026ee3 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edec34fe70dbeb51e33d0e4c5774116b19701d6fc2f8e04ae25c963e30dbbf4e +size 4436864192 diff --git a/LFM2.5-8B-A1B-Coder.Q3_K_M.gguf b/LFM2.5-8B-A1B-Coder.Q3_K_M.gguf new file mode 100644 index 0000000..763b254 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96a4512584e6fdd760b242105a40e09921b63fbe3932cea5c8242ac1ebe91f8 +size 4108397760 diff --git a/LFM2.5-8B-A1B-Coder.Q3_K_S.gguf b/LFM2.5-8B-A1B-Coder.Q3_K_S.gguf new file mode 100644 index 0000000..da2a523 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da869b47a7c8181a8c25bb6288672a2afd91231a1b948057c12ac86feba74f52 +size 3755076800 diff --git a/LFM2.5-8B-A1B-Coder.Q4_K_M.gguf b/LFM2.5-8B-A1B-Coder.Q4_K_M.gguf new file mode 100644 index 0000000..a10c3a4 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5acdd0c9da866a037804ca6dcb0419eb46ef1bf7b572ed785dfb157d00aac17 +size 5155564736 diff --git a/LFM2.5-8B-A1B-Coder.Q4_K_S.gguf b/LFM2.5-8B-A1B-Coder.Q4_K_S.gguf new file mode 100644 index 0000000..8b0f14e --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d8f27e0cf4d362668f970d3c12fef580dd3da0edb3149177a4ea6c42379a15 +size 4863552704 diff --git a/LFM2.5-8B-A1B-Coder.Q5_K_M.gguf b/LFM2.5-8B-A1B-Coder.Q5_K_M.gguf new file mode 100644 index 0000000..e0f7511 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be515f9c6bc2f1a9ace3d4cd7fccbbe7b50bf160a71eb75f8ede45308312ec0d +size 6030339264 diff --git a/LFM2.5-8B-A1B-Coder.Q5_K_S.gguf b/LFM2.5-8B-A1B-Coder.Q5_K_S.gguf new file mode 100644 index 0000000..1283afa --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d66313477b2d9822b4298196e7a006e6cb2ddced4bf4dba35fe28ca2141c4ed4 +size 5870185664 diff --git a/LFM2.5-8B-A1B-Coder.Q6_K.gguf b/LFM2.5-8B-A1B-Coder.Q6_K.gguf new file mode 100644 index 0000000..8a49bed --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5fff4f91149f4c64ee5abaead502d7ce708a652846afb4693a7d8ded579cc1c +size 6959787200 diff --git a/LFM2.5-8B-A1B-Coder.Q8_0.gguf b/LFM2.5-8B-A1B-Coder.Q8_0.gguf new file mode 100644 index 0000000..5b64782 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a1bfbf4d5117220298d31ccdb0323d559ca37ec6016cdc3c6e8eec57ab472f6 +size 9010195648 diff --git a/LFM2.5-8B-A1B-Coder.f16.gguf b/LFM2.5-8B-A1B-Coder.f16.gguf new file mode 100644 index 0000000..36e83e0 --- /dev/null +++ b/LFM2.5-8B-A1B-Coder.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5511f9041d1e53ac84650ec875b24b45537fc2ccc0d0068c70cdd4cc5aa07f87 +size 16947260608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..932647c --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: josephmayo/LFM2.5-8B-A1B-Coder +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- transformers +- code +- real-world-coding +- multilingual +- lfm2_moe +--- +## About + + + + + + + + + +static quants of https://huggingface.co/josephmayo/LFM2.5-8B-A1B-Coder + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-8B-A1B-Coder-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-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/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q4_K_S.gguf) | Q4_K_S | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q4_K_M.gguf) | Q4_K_M | 5.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q5_K_S.gguf) | Q5_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q5_K_M.gguf) | Q5_K_M | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.Q8_0.gguf) | Q8_0 | 9.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.f16.gguf) | f16 | 17.0 | 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. + +