commit eb4601747afba508f3409ab99d2bf6d5f1a71166 Author: ModelHub XC Date: Mon Apr 20 03:11:06 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Falcon3-1B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..58444a9 --- /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 +Falcon3-1B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon3-1B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon3-1B-Instruct.i1-IQ1_M.gguf b/Falcon3-1B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..d19ab7c --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c228862b22c0172929e8b8b22c338275aafb54eb77a2090cf3cb8e356a9b91b +size 536147168 diff --git a/Falcon3-1B-Instruct.i1-IQ1_S.gguf b/Falcon3-1B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..953c5d5 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507464a5533982b43ea6c2194a2fa1bf2e02531833b69f37d0540d2166a82c21 +size 513045728 diff --git a/Falcon3-1B-Instruct.i1-IQ2_M.gguf b/Falcon3-1B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..6d02d78 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f3327490c97423825e02955224d05b497fb743648aa8104175805421a4ff7d +size 683734240 diff --git a/Falcon3-1B-Instruct.i1-IQ2_S.gguf b/Falcon3-1B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..5055f4a --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61de8181c11a66d98e8a6648795c542dd1f2dccdfdbf189b98aa4e0d488f52b6 +size 652932320 diff --git a/Falcon3-1B-Instruct.i1-IQ2_XS.gguf b/Falcon3-1B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..f5c472f --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c90f3c08e040749248309f48a6122f710a14c65597917dfd7cb0ca0baf49a3d0 +size 607810784 diff --git a/Falcon3-1B-Instruct.i1-IQ2_XXS.gguf b/Falcon3-1B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..06ae80c --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cb4184e9f295dfef75314fd6e305ebbcc96356a11956b9535d1c6fd076b25e8 +size 574649568 diff --git a/Falcon3-1B-Instruct.i1-IQ3_M.gguf b/Falcon3-1B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..d399044 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c084699c842b84909f19adca8efa02cf6cf3ad2f524ac161044ac7787515bd3c +size 846689504 diff --git a/Falcon3-1B-Instruct.i1-IQ3_S.gguf b/Falcon3-1B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..342c6ca --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dfb45ae448ba3b227270f45d964463a751ed59041fbe62723b3d191a8206012 +size 827192544 diff --git a/Falcon3-1B-Instruct.i1-IQ3_XS.gguf b/Falcon3-1B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..851b2a3 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d0cda51d2a4ee29130e4677c4c52d27adbe64a99fdc3b53d45b52c66cb6966 +size 801436896 diff --git a/Falcon3-1B-Instruct.i1-IQ3_XXS.gguf b/Falcon3-1B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..312be26 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60923ebcfec0def061439814ccd836f190cc77b2d84a5feecbfa7857d79be35 +size 734917856 diff --git a/Falcon3-1B-Instruct.i1-IQ4_XS.gguf b/Falcon3-1B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..01ab542 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d88b7a12b8fb929a9097d80411340f995c293a445d7d3fd3f9e9e5af72b8d54 +size 969471200 diff --git a/Falcon3-1B-Instruct.i1-Q2_K.gguf b/Falcon3-1B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..489a6b5 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6086021f8acee696ed52e5d3ddec8ce337af2ce65d627ac01889a426c36d750d +size 727086304 diff --git a/Falcon3-1B-Instruct.i1-Q2_K_S.gguf b/Falcon3-1B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..c7abfae --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f34601dc43bae5da4a49028a6ade5f72f313682e41e53125f18ba0214dbf4b19 +size 692778208 diff --git a/Falcon3-1B-Instruct.i1-Q3_K_L.gguf b/Falcon3-1B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7f422e6 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728ea85e20ce0614271a6e652c3711b24213a3bf39e3b45dcd795d2cab92f6d1 +size 934245600 diff --git a/Falcon3-1B-Instruct.i1-Q3_K_M.gguf b/Falcon3-1B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..65968d3 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02ab3f94ce9b0f9590c62dbb282ac45487283c14127e5d58f14cbb0b1130021a +size 884962528 diff --git a/Falcon3-1B-Instruct.i1-Q3_K_S.gguf b/Falcon3-1B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c317787 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6dba9330df5caf0447f0ed364463b2b46488ec25004e91933cd622dc91f815 +size 827192544 diff --git a/Falcon3-1B-Instruct.i1-Q4_0.gguf b/Falcon3-1B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..c9ff85a --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a043c5413881afd5fc707f14cbe66f9f526fcffc03dde4677074c17e1239fa +size 1015346400 diff --git a/Falcon3-1B-Instruct.i1-Q4_K_M.gguf b/Falcon3-1B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c533349 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41bac764a47a78fd456072a02b9fdd96f4d96cf4a028f103bbe22a8857336bf0 +size 1057043680 diff --git a/Falcon3-1B-Instruct.i1-Q4_K_S.gguf b/Falcon3-1B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..45cc92a --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7168761a20fa27cf5e4d597d02e0dd4e381f467f12dbbf1ba8b72e00b47bab8 +size 1018492128 diff --git a/Falcon3-1B-Instruct.i1-Q5_K_M.gguf b/Falcon3-1B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a3dfb93 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c1393f0e68fdbdde04ee55c144b8924d723f757bf8fc1b1bb09a0e1d79216ef +size 1210922208 diff --git a/Falcon3-1B-Instruct.i1-Q5_K_S.gguf b/Falcon3-1B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a55a817 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc126a6f78ba92a99823ef1ee403cadbfd7cce9356db8eaf2f0428145fa25ae5 +size 1188361440 diff --git a/Falcon3-1B-Instruct.i1-Q6_K.gguf b/Falcon3-1B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..b641a94 --- /dev/null +++ b/Falcon3-1B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8a1399177631f5225f72f3227f0395370bdf45302ce83e86e852571e3e6c8a +size 1374418144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..08bb836 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: tiiuae/Falcon3-1B-Instruct +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/Falcon3-1B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/Falcon3-1B-Instruct-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/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 0.6 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 0.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 0.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 0.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 1.1 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.1 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon3-1B-Instruct-i1-GGUF/resolve/main/Falcon3-1B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 1.5 | 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..4ed1277 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02c6cf07de7d75363706722b555c96cc3f325a14df49b7e7d51b3b5364a4b38 +size 1478719