commit cfc24fdd37ebab08b4986cb93b713c5edc9d26b7 Author: ModelHub XC Date: Sat Jun 13 19:26:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/falcon-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b534d3 --- /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 +falcon-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +falcon-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6fb789a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: tiiuae/falcon-7b +datasets: +- tiiuae/falcon-refinedweb +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tiiuae/falcon-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/falcon-7b-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/falcon-7b-GGUF/resolve/main/falcon-7b.Q2_K.gguf) | Q2_K | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q3_K_S.gguf) | Q3_K_S | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/falcon-7b-GGUF/resolve/main/falcon-7b.f16.gguf) | f16 | 14.5 | 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. + + diff --git a/falcon-7b.IQ4_XS.gguf b/falcon-7b.IQ4_XS.gguf new file mode 100644 index 0000000..6953a20 --- /dev/null +++ b/falcon-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69db4ffbb0c647496545128e34a42c72c31b96d721e5254fe07d633987bffc17 +size 4179763040 diff --git a/falcon-7b.Q2_K.gguf b/falcon-7b.Q2_K.gguf new file mode 100644 index 0000000..8b94bce --- /dev/null +++ b/falcon-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff75e9630bf174386c40512c62f77f377873baa1fdfa612abb3d2aedc490e28 +size 3859720032 diff --git a/falcon-7b.Q3_K_L.gguf b/falcon-7b.Q3_K_L.gguf new file mode 100644 index 0000000..f4f3b8e --- /dev/null +++ b/falcon-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:765c7c1ba650d35a6e70439628e45eb9ec92763d7af3b03ed93f66efdcf88a4f +size 4378244960 diff --git a/falcon-7b.Q3_K_M.gguf b/falcon-7b.Q3_K_M.gguf new file mode 100644 index 0000000..8e5d7ca --- /dev/null +++ b/falcon-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b1b6989d0a39292ca28cf67d576dc057721068797d1cf0df483471a3a441ff +size 4140793696 diff --git a/falcon-7b.Q3_K_S.gguf b/falcon-7b.Q3_K_S.gguf new file mode 100644 index 0000000..9424489 --- /dev/null +++ b/falcon-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f4101290505ac74a979987f40025b1e9a506cf9b7c5bee0f7cdb8ff64260546 +size 3859720032 diff --git a/falcon-7b.Q4_K_M.gguf b/falcon-7b.Q4_K_M.gguf new file mode 100644 index 0000000..1af83f1 --- /dev/null +++ b/falcon-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6dc1df82f21258965226313bb3e2189c96517e69fec1bc49530bf3154201576 +size 4975126624 diff --git a/falcon-7b.Q4_K_S.gguf b/falcon-7b.Q4_K_S.gguf new file mode 100644 index 0000000..1e5edab --- /dev/null +++ b/falcon-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76eab50f71247654fb09b1a4b237dbd6737908b1da732814ea67cf4d6b6d201d +size 4745545568 diff --git a/falcon-7b.Q5_K_M.gguf b/falcon-7b.Q5_K_M.gguf new file mode 100644 index 0000000..b945fba --- /dev/null +++ b/falcon-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd5d6b2b90f90ebc043cbc10eec789d1b0e199b012a59172b5dd372c11c6eb5 +size 5731120992 diff --git a/falcon-7b.Q5_K_S.gguf b/falcon-7b.Q5_K_S.gguf new file mode 100644 index 0000000..6806084 --- /dev/null +++ b/falcon-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392ff843cc07fd3455d2de7b16f9347a8c47422f1f33fff92f4f1849133dfb26 +size 5343317856 diff --git a/falcon-7b.Q6_K.gguf b/falcon-7b.Q6_K.gguf new file mode 100644 index 0000000..3659c69 --- /dev/null +++ b/falcon-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8330acdd4e512df41d7b71698776b2129ceca79155f3c84ce4b1bee49f6dc73d +size 7031359328 diff --git a/falcon-7b.Q8_0.gguf b/falcon-7b.Q8_0.gguf new file mode 100644 index 0000000..7eea75b --- /dev/null +++ b/falcon-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c966e0ea0b97f96bb7e2ba49c8b23f2a5016fee57e4f0cd40eaded1752c2489 +size 7671445344 diff --git a/falcon-7b.f16.gguf b/falcon-7b.f16.gguf new file mode 100644 index 0000000..2b6553c --- /dev/null +++ b/falcon-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e885dbde802fc5de97d5658955a7b3e775a3b782eda6d7852199a4dbcf52d11 +size 14437279584