commit b71da07a843482788cd69d8d4e3f6234e082a873 Author: ModelHub XC Date: Sat May 9 07:45:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1403745 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Falcon3-MoE-2x7B-Insruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-MoE-2x7B-Insruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon3-MoE-2x7B-Insruct.IQ4_XS.gguf b/Falcon3-MoE-2x7B-Insruct.IQ4_XS.gguf new file mode 100644 index 0000000..06c29b7 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f760f21e9314a229ea3c57a87e149c271695a491156c9667616a78af4cecd6b +size 7308061216 diff --git a/Falcon3-MoE-2x7B-Insruct.Q2_K.gguf b/Falcon3-MoE-2x7B-Insruct.Q2_K.gguf new file mode 100644 index 0000000..4679c9b --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c76f51487d10eea8664c0fd88966c54940dc77b8a5287228e73eb115084957 +size 5039794720 diff --git a/Falcon3-MoE-2x7B-Insruct.Q3_K_L.gguf b/Falcon3-MoE-2x7B-Insruct.Q3_K_L.gguf new file mode 100644 index 0000000..afac0da --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50530614889a815c351ca82aa258d106e5d9cc7947215a2c4992a97c152bf41e +size 7034284576 diff --git a/Falcon3-MoE-2x7B-Insruct.Q3_K_M.gguf b/Falcon3-MoE-2x7B-Insruct.Q3_K_M.gguf new file mode 100644 index 0000000..8d4a7a7 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688a2f9e932afb695494f2435cd946e075bb50ffcb10a625cbefcb53647ee293 +size 6513273376 diff --git a/Falcon3-MoE-2x7B-Insruct.Q3_K_S.gguf b/Falcon3-MoE-2x7B-Insruct.Q3_K_S.gguf new file mode 100644 index 0000000..a617640 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c7089e5e7e0519e1a23897b0ddb2dc528eedc0098b355068b67248caf1e9444 +size 5921581600 diff --git a/Falcon3-MoE-2x7B-Insruct.Q4_K_M.gguf b/Falcon3-MoE-2x7B-Insruct.Q4_K_M.gguf new file mode 100644 index 0000000..2055195 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b36c2833deb2c43ae4e3fb571022a91828a994a5f793ad5d08540df5ba225e +size 8170187296 diff --git a/Falcon3-MoE-2x7B-Insruct.Q4_K_S.gguf b/Falcon3-MoE-2x7B-Insruct.Q4_K_S.gguf new file mode 100644 index 0000000..98b5783 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0de56a0f7e2d179e049c653da8843c7c55c1723c8f612a637b87bd0fa987a3 +size 7702555168 diff --git a/Falcon3-MoE-2x7B-Insruct.Q5_K_M.gguf b/Falcon3-MoE-2x7B-Insruct.Q5_K_M.gguf new file mode 100644 index 0000000..381bd19 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fadb38cfa431aab2268320f0f24cb2837c87a29bcc94b2e3bc1caeb06290ffad +size 9541724704 diff --git a/Falcon3-MoE-2x7B-Insruct.Q5_K_S.gguf b/Falcon3-MoE-2x7B-Insruct.Q5_K_S.gguf new file mode 100644 index 0000000..3af11be --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fcdd81aa9684dfeb84f95258ed075639d2ea7b6054864637a6afdad5685ab89 +size 9272666656 diff --git a/Falcon3-MoE-2x7B-Insruct.Q6_K.gguf b/Falcon3-MoE-2x7B-Insruct.Q6_K.gguf new file mode 100644 index 0000000..b910740 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec97c0a2d759ce6bda0c0d40b1afa4388509111058b736889dc7060a05bc871 +size 10998983200 diff --git a/Falcon3-MoE-2x7B-Insruct.Q8_0.gguf b/Falcon3-MoE-2x7B-Insruct.Q8_0.gguf new file mode 100644 index 0000000..9d35be7 --- /dev/null +++ b/Falcon3-MoE-2x7B-Insruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32ae787439db3f53464973e5085bc01bd5903ac94ce8694bafc7a07d529c29c +size 14244489760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8a58aa --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ehristoforu/Falcon3-MoE-2x7B-Insruct +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- falcon3 +- falcon +- falcon-moe +- moe +- llama +--- +## About + + + + + + +static quants of https://huggingface.co/ehristoforu/Falcon3-MoE-2x7B-Insruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-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/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q2_K.gguf) | Q2_K | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q3_K_S.gguf) | Q3_K_S | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q3_K_M.gguf) | Q3_K_M | 6.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q3_K_L.gguf) | Q3_K_L | 7.1 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.IQ4_XS.gguf) | IQ4_XS | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q4_K_S.gguf) | Q4_K_S | 7.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q4_K_M.gguf) | Q4_K_M | 8.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q5_K_S.gguf) | Q5_K_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q5_K_M.gguf) | Q5_K_M | 9.6 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q6_K.gguf) | Q6_K | 11.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-MoE-2x7B-Insruct-GGUF/resolve/main/Falcon3-MoE-2x7B-Insruct.Q8_0.gguf) | Q8_0 | 14.3 | fast, best quality | + +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. + +