commit a8a791f4000f7b2c9d63aeb8ed2acfa4ce7f7779 Author: ModelHub XC Date: Fri Aug 28 00:44:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: tiiuae/Falcon-H1-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c141618 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,82 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-BF16.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-F32.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q3_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-3B-Instruct-TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon-H1-3B-Instruct-BF16.gguf b/Falcon-H1-3B-Instruct-BF16.gguf new file mode 100644 index 0000000..37713dd --- /dev/null +++ b/Falcon-H1-3B-Instruct-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abab9eaec749f8793462d6f764931e72b51db1e3db6e2c44be27b9dbfc9ca6e +size 6303533632 diff --git a/Falcon-H1-3B-Instruct-F16.gguf b/Falcon-H1-3B-Instruct-F16.gguf new file mode 100644 index 0000000..79de9b5 --- /dev/null +++ b/Falcon-H1-3B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09af68bc63cd5b82846c96109a7180285e19e1ce3d74a3681bf3a0087100ebb3 +size 6303533632 diff --git a/Falcon-H1-3B-Instruct-F32.gguf b/Falcon-H1-3B-Instruct-F32.gguf new file mode 100644 index 0000000..2ac930a --- /dev/null +++ b/Falcon-H1-3B-Instruct-F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7bc597609b728c74445f09902acb8110b0367c30b2341d91d202247ff37f65 +size 12600243008 diff --git a/Falcon-H1-3B-Instruct-IQ1_M.gguf b/Falcon-H1-3B-Instruct-IQ1_M.gguf new file mode 100644 index 0000000..68d8985 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe323e68ebda0c2234bad6cf94d2cdb3955e6e4efab223ff70d3d91c11c028b +size 810708384 diff --git a/Falcon-H1-3B-Instruct-IQ2_M.gguf b/Falcon-H1-3B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..6aec436 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bf0109b6dade31f90f8e4d46cb43689397e7d48b066de267690d57bfbe26441 +size 1118666400 diff --git a/Falcon-H1-3B-Instruct-IQ2_S.gguf b/Falcon-H1-3B-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..5e5f328 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8065a7fc0dde5324ed27493dbf046cbd8684a5105128a5187bb81d0930b90642 +size 1036664480 diff --git a/Falcon-H1-3B-Instruct-IQ2_XS.gguf b/Falcon-H1-3B-Instruct-IQ2_XS.gguf new file mode 100644 index 0000000..2266511 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61131811f5392c96d3e9036690d8fbe0450ca3a9610c81939cfbe8fe67586db +size 998489504 diff --git a/Falcon-H1-3B-Instruct-IQ2_XXS.gguf b/Falcon-H1-3B-Instruct-IQ2_XXS.gguf new file mode 100644 index 0000000..138a87e --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f26e6ad586753f1d36128b5c3c9815aeed74c029570b65d9b5fa06b5c11c018 +size 913210784 diff --git a/Falcon-H1-3B-Instruct-IQ3_M.gguf b/Falcon-H1-3B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..148936a --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c979521ee5be8a22b2cdc0b87cb92ece21af74c91f566bc1d89a4fe417f0369 +size 1450237952 diff --git a/Falcon-H1-3B-Instruct-IQ3_S.gguf b/Falcon-H1-3B-Instruct-IQ3_S.gguf new file mode 100644 index 0000000..fa66c17 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef124848fd0b79820eab1cf1fcdb80e8c227b355a5f2a9858d8626cf7cde80c +size 1427955712 diff --git a/Falcon-H1-3B-Instruct-IQ3_XS.gguf b/Falcon-H1-3B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..5efc89f --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3fcfe6b7b2eedf02750159911fef7a67acc5d5bb0c768844eac2ad3132eaeb +size 1386668032 diff --git a/Falcon-H1-3B-Instruct-IQ3_XXS.gguf b/Falcon-H1-3B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..fb5873a --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c181be6f522e7ab58faa55447e5158f09c644a3ab6c3b63faf687549757716e6 +size 1271856800 diff --git a/Falcon-H1-3B-Instruct-IQ4_NL.gguf b/Falcon-H1-3B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..32b5e34 --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711bb15542ed54b1fed7eed9be5103c8c5fb8cb5f175ad3757a1209811ab5892 +size 1823650112 diff --git a/Falcon-H1-3B-Instruct-IQ4_XS.gguf b/Falcon-H1-3B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..e0fd33f --- /dev/null +++ b/Falcon-H1-3B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed70ea18f1368e9e2ebc438ccb85473f5a3721b69bbebad13b6b69a0bf6a116a +size 1731162368 diff --git a/Falcon-H1-3B-Instruct-Q2_K.gguf b/Falcon-H1-3B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..5114e88 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3974c1470b2a922a2664aa990d89227588c69b6af1c3b7ca6388dd5acf7941 +size 1189138176 diff --git a/Falcon-H1-3B-Instruct-Q2_K_S.gguf b/Falcon-H1-3B-Instruct-Q2_K_S.gguf new file mode 100644 index 0000000..64ba7b9 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c83dad0b7e807124dff68f0cb079ddffbfbf5bac5dd7cf73682565954ff92f9 +size 1142116096 diff --git a/Falcon-H1-3B-Instruct-Q3_K.gguf b/Falcon-H1-3B-Instruct-Q3_K.gguf new file mode 100644 index 0000000..8c0b01a --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a9bf2c56493ab6fcef9e048a6884195169d383fe96e17af445e3c2544e7b04 +size 1512824832 diff --git a/Falcon-H1-3B-Instruct-Q3_K_L.gguf b/Falcon-H1-3B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..21e0989 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:226cd2213c7ffbf78a0cb3c1281f51bde899b0124bf725b1bd8cd500349de6fb +size 1587372032 diff --git a/Falcon-H1-3B-Instruct-Q3_K_M.gguf b/Falcon-H1-3B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..8c0b01a --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a9bf2c56493ab6fcef9e048a6884195169d383fe96e17af445e3c2544e7b04 +size 1512824832 diff --git a/Falcon-H1-3B-Instruct-Q3_K_S.gguf b/Falcon-H1-3B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..27df36e --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70102dcd283538d4577579f05616ef05910a055dcf6a6177dadf0bee193b0d68 +size 1425170432 diff --git a/Falcon-H1-3B-Instruct-Q4_0.gguf b/Falcon-H1-3B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..18af1ec --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3724d593ab73d399afe7d4b53478181a7f111405c5f5e07ae35611ae80070e0 +size 1821028384 diff --git a/Falcon-H1-3B-Instruct-Q4_1.gguf b/Falcon-H1-3B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..b034352 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79211fb16fd4fc5502fdb034893c1924bd35cdf4eef6d6882fdbc9e1be3fc74c +size 2007314624 diff --git a/Falcon-H1-3B-Instruct-Q4_K.gguf b/Falcon-H1-3B-Instruct-Q4_K.gguf new file mode 100644 index 0000000..cda812d --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1926265eab19b0e47f0c2739e499a18e388373a616d71a218b924d5b95bdf702 +size 1888612384 diff --git a/Falcon-H1-3B-Instruct-Q4_K_M.gguf b/Falcon-H1-3B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..cda812d --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1926265eab19b0e47f0c2739e499a18e388373a616d71a218b924d5b95bdf702 +size 1888612384 diff --git a/Falcon-H1-3B-Instruct-Q4_K_S.gguf b/Falcon-H1-3B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..5329b35 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb0948fb0878ddf8059147f452015adbb9fc0f7236ddbbc063364e0701d470b +size 1829220384 diff --git a/Falcon-H1-3B-Instruct-Q5_0.gguf b/Falcon-H1-3B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..c5b0407 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4180f09f52603f29e4b4b34c874a7437a1469c6dcdaba8e03d567d378b25a606 +size 2193600864 diff --git a/Falcon-H1-3B-Instruct-Q5_1.gguf b/Falcon-H1-3B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..872b75d --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06a6649b32f5099396e77a3a9505f536a777cef42e6fd95d52f19a985714eb2 +size 2379887104 diff --git a/Falcon-H1-3B-Instruct-Q5_K.gguf b/Falcon-H1-3B-Instruct-Q5_K.gguf new file mode 100644 index 0000000..792adec --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fd3cc48e3fad069686799189b00ea08a6d599c47aa57f12ed38e835fedc459 +size 2228416864 diff --git a/Falcon-H1-3B-Instruct-Q5_K_M.gguf b/Falcon-H1-3B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..792adec --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fd3cc48e3fad069686799189b00ea08a6d599c47aa57f12ed38e835fedc459 +size 2228416864 diff --git a/Falcon-H1-3B-Instruct-Q5_K_S.gguf b/Falcon-H1-3B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..98df708 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954a2fde292c96b6c4e0f9710b94ac7d293280a4bd4ca6b568af729a645e83f1 +size 2193600864 diff --git a/Falcon-H1-3B-Instruct-Q6_K.gguf b/Falcon-H1-3B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..cc86fe9 --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:685b280dfd187e22b42816f8cfd73821570b3c9a4cca2e45c78951165f482d81 +size 2589459136 diff --git a/Falcon-H1-3B-Instruct-Q8_0.gguf b/Falcon-H1-3B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..e62f04a --- /dev/null +++ b/Falcon-H1-3B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b69da4470f067d38faf05e838bdb2cde099dbc7c812507e538e83132d3a0f2f +size 3351951232 diff --git a/Falcon-H1-3B-Instruct-TQ1_0.gguf b/Falcon-H1-3B-Instruct-TQ1_0.gguf new file mode 100644 index 0000000..343011e --- /dev/null +++ b/Falcon-H1-3B-Instruct-TQ1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f96984fbdf81775c08205574f26a5902383fcba20f0ec0ee7fd3be92ee94b08 +size 832151872 diff --git a/Falcon-H1-3B-Instruct-TQ2_0.gguf b/Falcon-H1-3B-Instruct-TQ2_0.gguf new file mode 100644 index 0000000..f61d897 --- /dev/null +++ b/Falcon-H1-3B-Instruct-TQ2_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32577de0d0210b433b8aea976ac98237a32360f2b6525246ca90f7d28edaac8 +size 964002112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bbe144f --- /dev/null +++ b/README.md @@ -0,0 +1,159 @@ +--- +library_name: transformers +language: +- ar +- cs +- de +- en +- es +- fr +- hi +- it +- ja +- ko +- nl +- pl +- pt +- ro +- ru +- sv +- ur +- zh +tags: +- falcon-h1 +license: other +license_name: falcon-llm-license +license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html +base_model: tiiuae/Falcon-H1-3B-Base +inference: true +--- + +drawing + +# Table of Contents + +0. [TL;DR](#TL;DR) +1. [Model Details](#model-details) +2. [Training Details](#training-details) +3. [Usage](#usage) +4. [Evaluation](#evaluation) +5. [Citation](#citation) + +# TL;DR + +# Model Details + +## Model Description + +- **Developed by:** [https://www.tii.ae](https://www.tii.ae) +- **Model type:** Causal decoder-only +- **Architecture:** Hybrid Transformers + Mamba architecture +- **Language(s) (NLP):** English, Multilingual +- **License:** Falcon-LLM License + +# Training details + +For more details about the training protocol of this model, please refer to the [Falcon-H1 technical blogpost](https://falcon-lm.github.io/blog/falcon-h1/) and [Technical Report](https://arxiv.org/abs/2507.22448). + +# Usage + +Currently to use this model you can either rely on Hugging Face `transformers`, `vLLM` or our custom fork of `llama.cpp` library. + +## Inference + +Make sure to install the latest version of `transformers` or `vllm`, eventually install these packages from source: + +```bash +pip install git+https://github.com/huggingface/transformers.git +``` + +Refer to [the official vLLM documentation for more details on building vLLM from source](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#build-wheel-from-source). + +### 🤗 transformers + +Refer to the snippet below to run H1 models using 🤗 transformers: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "tiiuae/Falcon-H1-1B-Base" + +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +# Perform text generation +``` + +### vLLM + +For vLLM, simply start a server by executing the command below: + +``` +# pip install vllm +vllm serve tiiuae/Falcon-H1-1B-Instruct --tensor-parallel-size 2 --data-parallel-size 1 +``` + +### 🦙 llama.cpp + +Our architecture is integrated into the latest versions of `llama.cpp`: https://github.com/ggml-org/llama.cpp - you can use the our official GGUF files directly with llama.cpp + + +# Evaluation + +Falcon-H1 series perform very well on a variety of tasks, including reasoning tasks. + +| Tasks | Falcon-H1-3B | Qwen3-4B | Qwen2.5-3B | Gemma3-4B | Llama3.2-3B | Falcon3-3B | +| --- | --- | --- | --- | --- | --- | --- | +| **General** | | | | | | +| BBH | **53.69** | 51.07 | 46.55 | 50.01 | 41.47 | 45.02 | +| ARC-C | **49.57** | 37.71 | 43.77 | 44.88 | 44.88 | 48.21 | +| TruthfulQA | 53.19 | 51.75 | **58.11** | 51.68 | 50.27 | 50.06 | +| HellaSwag | **69.85** | 55.31 | 64.21 | 47.68 | 63.74 | 64.24 | +| MMLU | **68.3** | 67.01 | 65.09 | 59.53 | 61.74 | 56.76 | +| **Math** | | | | | | +| GSM8k | **84.76** | 80.44 | 57.54 | 77.41 | 77.26 | 74.68 | +| MATH-500 | 74.2 | **85.0** | 64.2 | 76.4 | 41.2 | 54.2 | +| AMC-23 | 55.63 | **66.88** | 39.84 | 48.12 | 22.66 | 29.69 | +| AIME-24 | 11.88 | **22.29** | 6.25 | 6.67 | 11.67 | 3.96 | +| AIME-25 | 13.33 | **18.96** | 3.96 | 13.33 | 0.21 | 2.29 | +| **Science** | | | | | | +| GPQA | **33.89** | 28.02 | 28.69 | 29.19 | 28.94 | 28.69 | +| GPQA_Diamond | 38.72 | **40.74** | 35.69 | 28.62 | 29.97 | 29.29 | +| MMLU-Pro | **43.69** | 29.75 | 32.76 | 29.71 | 27.44 | 29.71 | +| MMLU-stem | **69.93** | 67.46 | 59.78 | 52.17 | 51.92 | 56.11 | +| **Code** | | | | | | +| HumanEval | 76.83 | **84.15** | 73.78 | 67.07 | 54.27 | 52.44 | +| HumanEval+ | 70.73 | **76.83** | 68.29 | 61.59 | 50.0 | 45.73 | +| MBPP | **79.63** | 68.78 | 72.75 | 77.78 | 62.17 | 61.9 | +| MBPP+ | **67.46** | 59.79 | 60.85 | 66.93 | 50.53 | 55.29 | +| LiveCodeBench | 26.81 | **39.92** | 11.74 | 21.14 | 2.74 | 3.13 | +| CRUXEval | 56.25 | **69.63** | 43.26 | 52.13 | 17.75 | 44.38 | +| **Instruction Following** | | | | | | +| IFEval | **85.05** | 84.01 | 64.26 | 77.01 | 74.0 | 69.1 | +| Alpaca-Eval | 31.09 | 36.51 | 17.37 | **39.64** | 19.69 | 14.82 | +| MTBench | **8.72** | 8.45 | 7.79 | 8.24 | 7.96 | 7.79 | +| LiveBench | 36.86 | **51.34** | 27.32 | 36.7 | 26.37 | 26.01 | + +You can check more in detail on our [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/), detailed benchmarks. + +# Useful links + +- View [our release blogpost](https://falcon-lm.github.io/blog/falcon-h1/). +- View [our technical report](https://arxiv.org/abs/2507.22448). +- Feel free to join [our discord server](https://discord.gg/trwMYP9PYm) if you have any questions or to interact with our researchers and developers. + +# Citation + +If the Falcon-H1 family of models were helpful to your work, feel free to give us a cite. + +``` +@article{falconh1, + title={Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance}, + author={Jingwei Zuo and Maksim Velikanov and Ilyas Chahed and Younes Belkada and Dhia Eddine Rhayem and Guillaume Kunsch and Hakim Hacid and Hamza Yous and Brahim Farhat and Ibrahim Khadraoui and Mugariya Farooq and Giulia Campesan and Ruxandra Cojocaru and Yasser Djilali and Shi Hu and Iheb Chaabane and Puneesh Khanna and Mohamed El Amine Seddik and Ngoc Dung Huynh and Phuc Le Khac and Leen AlQadi and Billel Mokeddem and Mohamed Chami and Abdalgader Abubaker and Mikhail Lubinets and Kacper Piskorski and Slim Frikha}, + journal = {arXiv preprint arXiv:2507.22448}, + year={2025} +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file