commit ac4ce33e605465f4e1ff24b06a0ac178becbc593 Author: ModelHub XC Date: Thu Jul 16 20:07:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Deepsync-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c42f3f --- /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 +Llama-Deepsync-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Deepsync-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Deepsync-1B.IQ4_XS.gguf b/Llama-Deepsync-1B.IQ4_XS.gguf new file mode 100644 index 0000000..881d62c --- /dev/null +++ b/Llama-Deepsync-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2871f874915d4b6289b7d5449834ec5252e8e97d65de4d2f572a39ede2f26c9b +size 748385728 diff --git a/Llama-Deepsync-1B.Q2_K.gguf b/Llama-Deepsync-1B.Q2_K.gguf new file mode 100644 index 0000000..1439c97 --- /dev/null +++ b/Llama-Deepsync-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09297fc876b8127324eb54f074445e50ab004477ec9f72a65e5f9f64088a52a +size 580875712 diff --git a/Llama-Deepsync-1B.Q3_K_L.gguf b/Llama-Deepsync-1B.Q3_K_L.gguf new file mode 100644 index 0000000..bedab99 --- /dev/null +++ b/Llama-Deepsync-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4beb69b59460470f8354e36e44d1f7bb657ef748eb252e893cb29682e50343 +size 732526016 diff --git a/Llama-Deepsync-1B.Q3_K_M.gguf b/Llama-Deepsync-1B.Q3_K_M.gguf new file mode 100644 index 0000000..a42f1b3 --- /dev/null +++ b/Llama-Deepsync-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a01af52d9e2fa61af3c955d0bf87a66dbc0c91aec26bea607137943236079c +size 690845120 diff --git a/Llama-Deepsync-1B.Q3_K_S.gguf b/Llama-Deepsync-1B.Q3_K_S.gguf new file mode 100644 index 0000000..54fa7b5 --- /dev/null +++ b/Llama-Deepsync-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959e1af911f6e9859a7b695604228fe6b1a4720f28d10bbb2d5dd1f401c9dc77 +size 641693120 diff --git a/Llama-Deepsync-1B.Q4_K_M.gguf b/Llama-Deepsync-1B.Q4_K_M.gguf new file mode 100644 index 0000000..93857dd --- /dev/null +++ b/Llama-Deepsync-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9912dcafb1171e2278296b7ddd40d848d834506058436a46fec802c564733e05 +size 807695808 diff --git a/Llama-Deepsync-1B.Q4_K_S.gguf b/Llama-Deepsync-1B.Q4_K_S.gguf new file mode 100644 index 0000000..ff11477 --- /dev/null +++ b/Llama-Deepsync-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6712b4c8f45436c37a9e251d83112f117bcb63ea3264751bac398542d4bd91f +size 775648704 diff --git a/Llama-Deepsync-1B.Q5_K_M.gguf b/Llama-Deepsync-1B.Q5_K_M.gguf new file mode 100644 index 0000000..6ec978e --- /dev/null +++ b/Llama-Deepsync-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760429df2d89937d0798957c5dbd90c2233e63e92f47f364edea60f95a32ea29 +size 911504832 diff --git a/Llama-Deepsync-1B.Q5_K_S.gguf b/Llama-Deepsync-1B.Q5_K_S.gguf new file mode 100644 index 0000000..65aa146 --- /dev/null +++ b/Llama-Deepsync-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f8447bb34e65dbd37544fed017c9207365edbfd82ca0f0cf5781568e081575 +size 892564928 diff --git a/Llama-Deepsync-1B.Q6_K.gguf b/Llama-Deepsync-1B.Q6_K.gguf new file mode 100644 index 0000000..f2758c1 --- /dev/null +++ b/Llama-Deepsync-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68200a53f47ed50e54b23ad79d3062e7fe3f98af729ed289c2d8cd366ff6fe78 +size 1021801920 diff --git a/Llama-Deepsync-1B.Q8_0.gguf b/Llama-Deepsync-1B.Q8_0.gguf new file mode 100644 index 0000000..a3a14fa --- /dev/null +++ b/Llama-Deepsync-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa8e97bbed045934198d101ad2d12e91c531c517905953e2b203d0d60ec6c0f +size 1321084352 diff --git a/Llama-Deepsync-1B.f16.gguf b/Llama-Deepsync-1B.f16.gguf new file mode 100644 index 0000000..829dc8a --- /dev/null +++ b/Llama-Deepsync-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb44b9fa23f6efb79bc149d57d4fd4223bd54cfb487e8c81a46b63d602725586 +size 2479596992 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dde2bdf --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: prithivMLmods/Llama-Deepsync-1B +language: +- en +- de +- fr +- it +- pt +- hi +- es +- th +library_name: transformers +license: creativeml-openrail-m +quantized_by: mradermacher +tags: +- text-generation-inference +- Llama +- Code +- CoT +- Math +- Deepsync +- 3b +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Llama-Deepsync-1B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Deepsync-1B-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/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Deepsync-1B-GGUF/resolve/main/Llama-Deepsync-1B.f16.gguf) | f16 | 2.6 | 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. + +