commit d81c55b40e8f78ad13c487f48c1ee9b34547763a Author: ModelHub XC Date: Wed Aug 26 09:37:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Falcon3-10B-Base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..30cc2db --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-10B-Base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon3-10B-Base.i1-IQ1_M.gguf b/Falcon3-10B-Base.i1-IQ1_M.gguf new file mode 100644 index 0000000..354937a --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fdb81d0c218b60f6c9cec1e0508851f969689bdda165f1a766062216857a58 +size 2560053248 diff --git a/Falcon3-10B-Base.i1-IQ1_S.gguf b/Falcon3-10B-Base.i1-IQ1_S.gguf new file mode 100644 index 0000000..db04479 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2c9d74f329657903b20a0f6ee86b529a187fb5ca3849e2999c2b2ea3803ffb +size 2357485568 diff --git a/Falcon3-10B-Base.i1-IQ2_M.gguf b/Falcon3-10B-Base.i1-IQ2_M.gguf new file mode 100644 index 0000000..3ffe669 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1373ee27d37d9b4283a4e75cdfc4ac2f7b667270faf2767ebcae92f80ba921 +size 3592343552 diff --git a/Falcon3-10B-Base.i1-IQ2_S.gguf b/Falcon3-10B-Base.i1-IQ2_S.gguf new file mode 100644 index 0000000..58f3b54 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391b105abb7cb868ed6cddcdde90e8edf2c3da2f6d17f752f435fb3e582a95ea +size 3322253312 diff --git a/Falcon3-10B-Base.i1-IQ2_XS.gguf b/Falcon3-10B-Base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..dbf05a8 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b7dfb5845d98f70e468b9f4b3d64aa284f049eec1f336f7a79f4d7178a22ec +size 3179552768 diff --git a/Falcon3-10B-Base.i1-IQ2_XXS.gguf b/Falcon3-10B-Base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..142c690 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae074c0612372354401f417e0b8ba2e8345f20c37cb28a4b4d706f6ed40e9c06 +size 2897666048 diff --git a/Falcon3-10B-Base.i1-IQ3_M.gguf b/Falcon3-10B-Base.i1-IQ3_M.gguf new file mode 100644 index 0000000..76584dd --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd8d157ca363ae917f337d466375356c1fa70e3aeb6fad2d41d60bb82adbf5b7 +size 4704985088 diff --git a/Falcon3-10B-Base.i1-IQ3_S.gguf b/Falcon3-10B-Base.i1-IQ3_S.gguf new file mode 100644 index 0000000..77ec011 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99a7a3b256baa63c14ec1ca8970a83b8f7267d07c0a71b7ad61eb3f4efc958f +size 4591136768 diff --git a/Falcon3-10B-Base.i1-IQ3_XS.gguf b/Falcon3-10B-Base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c55a0f1 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65660c75e6a60d33320b82831b86f7aec717b3fe92a43799550a3ab24c9031b3 +size 4368478208 diff --git a/Falcon3-10B-Base.i1-IQ3_XXS.gguf b/Falcon3-10B-Base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f95e871 --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2898f25dabc3f17e29b4911bdd475cb95748252d4e505aa26ecaa6bbdf0f2dbc +size 4078579712 diff --git a/Falcon3-10B-Base.i1-IQ4_XS.gguf b/Falcon3-10B-Base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..ee3003e --- /dev/null +++ b/Falcon3-10B-Base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ffb56f1c276220f045ff5fadfc1940f2ed9a792af13b287bad71518208c8ee6 +size 5596884992 diff --git a/Falcon3-10B-Base.i1-Q2_K.gguf b/Falcon3-10B-Base.i1-Q2_K.gguf new file mode 100644 index 0000000..cfa9b48 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4840f99d794a465e54bdef2cb503998fea2ad4c190d279ea0e4a3b246905703 +size 3924045824 diff --git a/Falcon3-10B-Base.i1-Q2_K_S.gguf b/Falcon3-10B-Base.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c264dfc --- /dev/null +++ b/Falcon3-10B-Base.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e02415708eff79cc5378956da41b450734264804e481a3396892ee1557c9ca +size 3668332544 diff --git a/Falcon3-10B-Base.i1-Q3_K_L.gguf b/Falcon3-10B-Base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..b582a1d --- /dev/null +++ b/Falcon3-10B-Base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618e240bb2842d4ed730e5cd505d727e1feaec4f6e4c555ba0f3d4a14223b293 +size 5450805248 diff --git a/Falcon3-10B-Base.i1-Q3_K_M.gguf b/Falcon3-10B-Base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..50c2ef3 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ddddb68d9da6cf86c851a67c3bc4a08d8f06db2e758411692877a4b2ec3cb06 +size 5052477440 diff --git a/Falcon3-10B-Base.i1-Q3_K_S.gguf b/Falcon3-10B-Base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7bd19ef --- /dev/null +++ b/Falcon3-10B-Base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eef724af1512cbbf021446bc2f9f9119ee0ca49dbdb1c2b67590357ed84fe4d +size 4591136768 diff --git a/Falcon3-10B-Base.i1-Q4_0.gguf b/Falcon3-10B-Base.i1-Q4_0.gguf new file mode 100644 index 0000000..c34f175 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd98571c03ac1a910b469fc721a35a69691634926208397e157a04d763b81ecd +size 5928464384 diff --git a/Falcon3-10B-Base.i1-Q4_K_M.gguf b/Falcon3-10B-Base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4a42296 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c87be4a8029cf648a06967a2b13ec8318ad0f89d0dab0c27e4213849e24ec1 +size 6287519744 diff --git a/Falcon3-10B-Base.i1-Q4_K_S.gguf b/Falcon3-10B-Base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d5720be --- /dev/null +++ b/Falcon3-10B-Base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74464b97dcdc07855652ad842ef998a9766886e312531c255628d2eefc83acb4 +size 5952155648 diff --git a/Falcon3-10B-Base.i1-Q5_K_M.gguf b/Falcon3-10B-Base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4934340 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9407d362cff89cbc2c7b5749ee171105b24d962a6105e18cdc18269016caf14 +size 7340552192 diff --git a/Falcon3-10B-Base.i1-Q5_K_S.gguf b/Falcon3-10B-Base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5f41c46 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f425dd857d036e69138fde4cabcc22341ea53857fbdbaaf2b6c0b7c2f509a0 +size 7144189952 diff --git a/Falcon3-10B-Base.i1-Q6_K.gguf b/Falcon3-10B-Base.i1-Q6_K.gguf new file mode 100644 index 0000000..9e5ee89 --- /dev/null +++ b/Falcon3-10B-Base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09e6732de30d9bafe2d5fbc00ff60e8f94ff220e28b3b4a872f396db9e99006d +size 8459399168 diff --git a/README.md b/README.md new file mode 100644 index 0000000..30445ac --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: tiiuae/Falcon3-10B-Base +language: +- en +- fr +- es +- pt +library_name: transformers +license: other +license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html +license_name: falcon-llm-license +quantized_by: mradermacher +tags: +- falcon3 +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/tiiuae/Falcon3-10B-Base + + +static quants are available at https://huggingface.co/mradermacher/Falcon3-10B-Base-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/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q2_K.gguf) | i1-Q2_K | 4.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 4.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.7 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q4_0.gguf) | i1-Q4_0 | 6.0 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.2 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.4 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-10B-Base-i1-GGUF/resolve/main/Falcon3-10B-Base.i1-Q6_K.gguf) | i1-Q6_K | 8.6 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..1f46414 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780d8bcfe8c9219f3a365a8fea2d22aa67eeafa6f688be42194bc2ea6f1c92cd +size 6644805