commit e9165cae4437aed3c64d3382d7296d75a8b81295 Author: ModelHub XC Date: Thu Aug 13 11:11:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: IAILabs/Qwen2.5-VL-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..822a9ad --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +placeholder.gguf filter=lfs diff=lfs merge=lfs -text +new-mmproj-Qwen2.5-VL-7B-Instruct-F32.gguf filter=lfs diff=lfs merge=lfs -text +candidate-mmproj-Qwen2.5-VL-7B-Instruct-F32.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Implementing Qwen2.pdf b/Implementing Qwen2.pdf new file mode 100644 index 0000000..3f8fc7e Binary files /dev/null and b/Implementing Qwen2.pdf differ diff --git a/Qwen2.5-VL-7B-Instruct-F16.gguf b/Qwen2.5-VL-7B-Instruct-F16.gguf new file mode 100644 index 0000000..1191337 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b12625ebcc55df52cb42578b6936d85dfd966bb49091a75b4d4d6e305bbd36 +size 15237853088 diff --git a/Qwen2.5-VL-7B-Instruct-IQ1_S.gguf b/Qwen2.5-VL-7B-Instruct-IQ1_S.gguf new file mode 100644 index 0000000..7c088af --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2afe35aef53f68718a7e2f8e025a59c35fd954c820226464254ffde9ff2ab58 +size 1903667392 diff --git a/Qwen2.5-VL-7B-Instruct-IQ2_M.gguf b/Qwen2.5-VL-7B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..20f5758 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6155abd5fbdffc0f0021773229f79f25380e3742f4cb40ce88ad4715b1396ec7 +size 2780342464 diff --git a/Qwen2.5-VL-7B-Instruct-IQ2_S.gguf b/Qwen2.5-VL-7B-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..20d398c --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d8a88751fe08b5eac490000620bdba17ba96eed5a349fd9e5782c76ba6c2ed +size 2595637440 diff --git a/Qwen2.5-VL-7B-Instruct-IQ2_XS.gguf b/Qwen2.5-VL-7B-Instruct-IQ2_XS.gguf new file mode 100644 index 0000000..ee30453 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a89eed6d911c3adc0d4f6fe51251ea376521ae180eb8c3c0acd7b86a8b8289d +size 2469021888 diff --git a/Qwen2.5-VL-7B-Instruct-IQ2_XXS.gguf b/Qwen2.5-VL-7B-Instruct-IQ2_XXS.gguf new file mode 100644 index 0000000..02cc4e0 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a042697d702801eabf98a839b2f0de400dae9e3d40debaf792258838420294d7 +size 2273077440 diff --git a/Qwen2.5-VL-7B-Instruct-IQ3_M.gguf b/Qwen2.5-VL-7B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..0f0ec34 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ee207b4b2b30404df0ec69602369cd3ac0ea78530adcf35f47346a5945cd82 +size 3574012096 diff --git a/Qwen2.5-VL-7B-Instruct-IQ3_S.gguf b/Qwen2.5-VL-7B-Instruct-IQ3_S.gguf new file mode 100644 index 0000000..d63b51a --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdaadd6c3db6811827c4041dcef7c05cbb0e5d4e744e7227aff5e3efc28921e1 +size 3499192512 diff --git a/Qwen2.5-VL-7B-Instruct-IQ3_XS.gguf b/Qwen2.5-VL-7B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..007cddd --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4445f5dc2feed9807d37d18adb8ce011dfe11b707f986731b1d45e4d1536a5d8 +size 3346256064 diff --git a/Qwen2.5-VL-7B-Instruct-IQ3_XXS.gguf b/Qwen2.5-VL-7B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..4fce000 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcab6781cafa659cd6928b6c74e300ea446890693edbf8a6f66534ef8b60094e +size 3114514624 diff --git a/Qwen2.5-VL-7B-Instruct-IQ4_NL.gguf b/Qwen2.5-VL-7B-Instruct-IQ4_NL.gguf new file mode 100644 index 0000000..9742279 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4b4ddb563ab4cbcaceb116196083bd0e989b09afa6c4a71ce5e6da666a4b974 +size 4437813440 diff --git a/Qwen2.5-VL-7B-Instruct-IQ4_XS.gguf b/Qwen2.5-VL-7B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..9c2cda3 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a0f1aa42649b381cd0c4e485a6beb6a7311a897392b56fbec07c2e4eac1e92 +size 4218472640 diff --git a/Qwen2.5-VL-7B-Instruct-Q2_K.gguf b/Qwen2.5-VL-7B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..0cdec73 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87bb440f26aa06d42d7f62b70e70a6556a5054e53d623701509b9c8701b4daf1 +size 3015940288 diff --git a/Qwen2.5-VL-7B-Instruct-Q2_K_S.gguf b/Qwen2.5-VL-7B-Instruct-Q2_K_S.gguf new file mode 100644 index 0000000..17d649d --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194ad279d98fdb833220ad04fbe55ea17e7b0035c76e9d527cd8f9d2c85c1d04 +size 2834073792 diff --git a/Qwen2.5-VL-7B-Instruct-Q3_K.gguf b/Qwen2.5-VL-7B-Instruct-Q3_K.gguf new file mode 100644 index 0000000..43867da --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e54b6e47b7c0985269f85b2573125f7c999523670ce53d620ac33968da818b +size 3808391360 diff --git a/Qwen2.5-VL-7B-Instruct-Q3_K_L.gguf b/Qwen2.5-VL-7B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..b78ef9f --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a63c6006d7d78ee31f2c6a9392d7f958a2a1f3c30506a39b068aa780d4006db +size 4088459456 diff --git a/Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf b/Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..43867da --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e54b6e47b7c0985269f85b2573125f7c999523670ce53d620ac33968da818b +size 3808391360 diff --git a/Qwen2.5-VL-7B-Instruct-Q3_K_S.gguf b/Qwen2.5-VL-7B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..8dae7f2 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3847320546c434b60050292791b3388f1a781a8bb2a6db0f0397db741092fd19 +size 3492368576 diff --git a/Qwen2.5-VL-7B-Instruct-Q4_0.gguf b/Qwen2.5-VL-7B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..35d2d87 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04153e9057bd3aeb3c5441c6c5293c3d232c112743d96f4cde6f9eef746e2853 +size 4444121280 diff --git a/Qwen2.5-VL-7B-Instruct-Q4_1.gguf b/Qwen2.5-VL-7B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..6ecd861 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1301a2254e42cf207049a6001a38fca30fb9fdab59ee7737286e755aef53af87 +size 4873283776 diff --git a/Qwen2.5-VL-7B-Instruct-Q4_K.gguf b/Qwen2.5-VL-7B-Instruct-Q4_K.gguf new file mode 100644 index 0000000..4f8d04a --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be29f69046a52e9eb17a935c35d882ab22efacc2a7495c5b8ef933c81dfc2887 +size 4683073728 diff --git a/Qwen2.5-VL-7B-Instruct-Q4_K_M.gguf b/Qwen2.5-VL-7B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..4f8d04a --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be29f69046a52e9eb17a935c35d882ab22efacc2a7495c5b8ef933c81dfc2887 +size 4683073728 diff --git a/Qwen2.5-VL-7B-Instruct-Q4_K_S.gguf b/Qwen2.5-VL-7B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..f10b5be --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87cd55b141b0a5d666c06d8ce3edd8befc3497106d42e1ad61b6884900caa161 +size 4457769152 diff --git a/Qwen2.5-VL-7B-Instruct-Q5_0.gguf b/Qwen2.5-VL-7B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..91df74d --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033d355941468a374bfdaf83fe6b14f18585c4f5d12e5190553708d47069465d +size 5327907008 diff --git a/Qwen2.5-VL-7B-Instruct-Q5_1.gguf b/Qwen2.5-VL-7B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..897e18e --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed505f4292bdd71a6534361e92dee04e550148c309190cb9eb517dcfe629e9f6 +size 5757069504 diff --git a/Qwen2.5-VL-7B-Instruct-Q5_K.gguf b/Qwen2.5-VL-7B-Instruct-Q5_K.gguf new file mode 100644 index 0000000..abc9fad --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3620279e6b4f085a9a7fa018f8c45f6bc3b86108918ed8290dcc6ed2d70b4ffa +size 5444831424 diff --git a/Qwen2.5-VL-7B-Instruct-Q5_K_M.gguf b/Qwen2.5-VL-7B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..abc9fad --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3620279e6b4f085a9a7fa018f8c45f6bc3b86108918ed8290dcc6ed2d70b4ffa +size 5444831424 diff --git a/Qwen2.5-VL-7B-Instruct-Q5_K_S.gguf b/Qwen2.5-VL-7B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..c451768 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22b3dcf470257d587a90b6afdf194425362649b6e5ac8e9b2eeb10f26ab9628 +size 5315176640 diff --git a/Qwen2.5-VL-7B-Instruct-Q6_K.gguf b/Qwen2.5-VL-7B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..de55145 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca037e4088ba447552c6e696bb0bb4b3d729e85f4644a5b1b38d849db0a7e22 +size 6254198976 diff --git a/Qwen2.5-VL-7B-Instruct-Q8_0.gguf b/Qwen2.5-VL-7B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..f1445d5 --- /dev/null +++ b/Qwen2.5-VL-7B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54f6b95de47b93f7a644538c26f822f0dce8a01d3f6f8071a237096ebcc3380 +size 8098525088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c226775 --- /dev/null +++ b/README.md @@ -0,0 +1,20 @@ +--- +base_model: +- Qwen/Qwen2.5-VL-7B-Instruct +--- +# NOTE: OLDER / OTHER VERSIONS OF THIS MODEL ARE ERRONEOUSLY PRODUCED Qwen2VLxQwen2.5 HYBRIDS!!! + +## Although these models have seemingly better performance than Qwen2VL, they are not the real deal! True Qwen2.5VL GGML support is still being added. + + +![](https://private-user-images.githubusercontent.com/6534243/418389672-10a77230-62b7-4763-84f1-35085eca3b18.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.tuaANrkwXXvZ1pHZ5RHVqhjTzw7HaRLG_7uzKXPYDR8) + +# To test it out: +https://github.com/Independent-AI-Labs/llama.cpp/commits/debug/build/ + +You will have to build llama.cpp with CLIP hardware acceleration enabled to get the new architecture running. + +Monitor our progress in merging this upstream here: +https://github.com/ggml-org/llama.cpp/pull/12119 + +# Official release and benchmarks coming soon! diff --git a/candidate-mmproj-Qwen2.5-VL-7B-Instruct-F32.gguf b/candidate-mmproj-Qwen2.5-VL-7B-Instruct-F32.gguf new file mode 100644 index 0000000..640792a --- /dev/null +++ b/candidate-mmproj-Qwen2.5-VL-7B-Instruct-F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fad7940f2c35a0a618f367ad3834641181dc82c318a6c80490370f1fac8081b2 +size 2714424480 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 diff --git a/res/docs/screens/quantbench_shiny.png b/res/docs/screens/quantbench_shiny.png new file mode 100644 index 0000000..722a81c Binary files /dev/null and b/res/docs/screens/quantbench_shiny.png differ