commit 17ca9a745119604aa6e08cff91e95991dad32c43 Author: ModelHub XC Date: Mon May 18 17:33:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40f06ce --- /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 +ALLaM-7B-Instruct-preview-reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ALLaM-7B-Instruct-preview-reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ALLaM-7B-Instruct-preview-reasoning.IQ4_XS.gguf b/ALLaM-7B-Instruct-preview-reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..fbf3cb4 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3479cd401ec78f162be6c05f73487492298cef2d7449ae64543a02c9569d87da +size 3825611232 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q2_K.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q2_K.gguf new file mode 100644 index 0000000..d056957 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a621ecffc306e78ca2d8ed3be54a177512614e616a09a13049fc1e4983ec329 +size 2684334560 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q3_K_L.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..aae58d1 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ffed7b44a81cc52705ea21acf5d6ffcec08017aef624b1d1dd85806caa318a +size 3761893856 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q3_K_M.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..bdeadd3 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917c361873412eb7cc6096134c1ff78dd44eff79b419a4aeb1998a3d37da960c +size 3462787552 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q3_K_S.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..4bb8945 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3be01e2271295c99075d4d52208090ed893a0496005df0ac87f05162271f49 +size 3113087456 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q4_K_M.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..e6e6aca --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3466fe7c4c07efdac25442b2e9d505093688935fe5e611e83581c6ce26eb27ac +size 4263195104 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q4_K_S.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..2181c65 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bab2860cdfe3d01f97b7f2e0edbacc88caad57bf37790e7d82a6b262cb873a0 +size 4038930912 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q5_K_M.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..c4dc3dc --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cceacb8026a638314192389ea46b128195cbb08fa86df71f0b57782391fad4a +size 4981731808 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q5_K_S.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..ae8caee --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1578a2a113c865d4cf28507e32688c542a92138345f32069ef15dd643f26170d +size 4850266592 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q6_K.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q6_K.gguf new file mode 100644 index 0000000..5d5bafe --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49fa084028f5530feb78a39d790a3c42bd8b063809682c6f2c4e86c85063720 +size 5745177056 diff --git a/ALLaM-7B-Instruct-preview-reasoning.Q8_0.gguf b/ALLaM-7B-Instruct-preview-reasoning.Q8_0.gguf new file mode 100644 index 0000000..8edc267 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75cc8e84f030dbaacebed0f0b8d0b921f0ea4c84fc9ce259a1a4ab4d68cce19e +size 7440560608 diff --git a/ALLaM-7B-Instruct-preview-reasoning.f16.gguf b/ALLaM-7B-Instruct-preview-reasoning.f16.gguf new file mode 100644 index 0000000..2895842 --- /dev/null +++ b/ALLaM-7B-Instruct-preview-reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ddadcfeaff83f4639deda8ccdc9a4f00fe7019681a85c706d6548e061f1cf4 +size 14003335648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5a20e45 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: adeebaldkheel/ALLaM-7B-Instruct-preview-reasoning +language: +- ar +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- GGUF +- transformers +--- +## About + + + + + + +static quants of https://huggingface.co/adeebaldkheel/ALLaM-7B-Instruct-preview-reasoning + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q3_K_S.gguf) | Q3_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q4_K_M.gguf) | Q4_K_M | 4.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q5_K_S.gguf) | Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q5_K_M.gguf) | Q5_K_M | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ALLaM-7B-Instruct-preview-reasoning-GGUF/resolve/main/ALLaM-7B-Instruct-preview-reasoning.f16.gguf) | f16 | 14.1 | 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. + +