commit 591f618a8f5687bb6f918780429ba7d7b68d6f24 Author: ModelHub XC Date: Tue Jun 16 10:16:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Falcon-H1-Tiny-R-90M-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6894817 --- /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-H1-Tiny-R-90M.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Falcon-H1-Tiny-R-90M.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Falcon-H1-Tiny-R-90M.IQ4_XS.gguf b/Falcon-H1-Tiny-R-90M.IQ4_XS.gguf new file mode 100644 index 0000000..c10fa88 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a079d69f09bfd0a8517d6591a57244ab4ecf538c5a34ade55bd9da9616bd19ae +size 55291232 diff --git a/Falcon-H1-Tiny-R-90M.Q2_K.gguf b/Falcon-H1-Tiny-R-90M.Q2_K.gguf new file mode 100644 index 0000000..ee58d1f --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9e058a2fd6b624893a2e23794ec1e1834fa0c5437ed1be6760bf7c02811af4 +size 41751392 diff --git a/Falcon-H1-Tiny-R-90M.Q3_K_L.gguf b/Falcon-H1-Tiny-R-90M.Q3_K_L.gguf new file mode 100644 index 0000000..7dc0329 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987e424ff899ec30731cfeb60db8d2f98b0aec3f1299f73cd9efc53a3ec7c385 +size 51783776 diff --git a/Falcon-H1-Tiny-R-90M.Q3_K_M.gguf b/Falcon-H1-Tiny-R-90M.Q3_K_M.gguf new file mode 100644 index 0000000..f3d8be7 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180386f8ca863ac842323302c43b3e6e29513f4af3f1e8169d6807d4a4a7492d +size 49686624 diff --git a/Falcon-H1-Tiny-R-90M.Q3_K_S.gguf b/Falcon-H1-Tiny-R-90M.Q3_K_S.gguf new file mode 100644 index 0000000..a0dd687 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d12fa94ad7de6b2766ac0812d8f0b85bd57b65f89d4331510bd0af25a2782107 +size 47323232 diff --git a/Falcon-H1-Tiny-R-90M.Q4_K_M.gguf b/Falcon-H1-Tiny-R-90M.Q4_K_M.gguf new file mode 100644 index 0000000..b1b9986 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db9cd5a7be30228edc7f7380bb7a3124ad064ba7c1167858ceb3251fddda4b1 +size 58599776 diff --git a/Falcon-H1-Tiny-R-90M.Q4_K_S.gguf b/Falcon-H1-Tiny-R-90M.Q4_K_S.gguf new file mode 100644 index 0000000..5c63daa --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36638e79e7d1fa0d9969fe41763da15487d188589ecd41b655bc2aeaffc3ecc +size 57360736 diff --git a/Falcon-H1-Tiny-R-90M.Q5_K_M.gguf b/Falcon-H1-Tiny-R-90M.Q5_K_M.gguf new file mode 100644 index 0000000..5534912 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49eb975168b8457a0fb18fe2ae3b71ea535c31a06f1d27dc805b826293b64307 +size 67189088 diff --git a/Falcon-H1-Tiny-R-90M.Q5_K_S.gguf b/Falcon-H1-Tiny-R-90M.Q5_K_S.gguf new file mode 100644 index 0000000..63562d8 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbac4de9117d2f10322eb724756faf971b830b60f28cea9c222755f742a01fe4 +size 66457952 diff --git a/Falcon-H1-Tiny-R-90M.Q6_K.gguf b/Falcon-H1-Tiny-R-90M.Q6_K.gguf new file mode 100644 index 0000000..76e7427 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a413ec771784835c2fdf9baf3b3ac5534a004907c251306b3947fa530544bff6 +size 76315232 diff --git a/Falcon-H1-Tiny-R-90M.Q8_0.gguf b/Falcon-H1-Tiny-R-90M.Q8_0.gguf new file mode 100644 index 0000000..b7b921a --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f15d063d15342a559c6ccddcd4c13ef6fa92750d80f94f0da78e1caa6e7767d +size 98353504 diff --git a/Falcon-H1-Tiny-R-90M.f16.gguf b/Falcon-H1-Tiny-R-90M.f16.gguf new file mode 100644 index 0000000..e50a3f1 --- /dev/null +++ b/Falcon-H1-Tiny-R-90M.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e867bd2fc18d042f25b30e99ad88fe56bd017c1381f09252aac9e30609d26da +size 183662944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2e24fcd --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: tiiuae/Falcon-H1-Tiny-R-90M +language: +- en +library_name: transformers +license: other +license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html +license_name: falcon-llm-license +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- falcon-h1 +- edge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tiiuae/Falcon-H1-Tiny-R-90M + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Falcon-H1-Tiny-R-90M-GGUF).*** + +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/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q2_K.gguf) | Q2_K | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q3_K_S.gguf) | Q3_K_S | 0.1 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q3_K_M.gguf) | Q3_K_M | 0.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.Q8_0.gguf) | Q8_0 | 0.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Falcon-H1-Tiny-R-90M-GGUF/resolve/main/Falcon-H1-Tiny-R-90M.f16.gguf) | f16 | 0.3 | 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. + +