commit d2ed4a60e9865740e00c24f442dbb65276bdd76d Author: ModelHub XC Date: Fri Sep 18 02:48:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b66f902 --- /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 +Jarvis-Qwen2.5-3B-Instruct-20250829.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Jarvis-Qwen2.5-3B-Instruct-20250829.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.IQ4_XS.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.IQ4_XS.gguf new file mode 100644 index 0000000..062cf15 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cae236f67231d302505091eed512dc4f14f694208b933eb0945a2bedf1114a1 +size 1752724096 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q2_K.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q2_K.gguf new file mode 100644 index 0000000..02ae45b --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:871e5888afeda8c5593d2eda6dd9ab3ae7a13884645efaf3c005eae8a9558c17 +size 1274294912 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_L.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_L.gguf new file mode 100644 index 0000000..d06c1a1 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954d5384f925d5b0b4469b88aac8ad2bd27a7710d52dafced1c1e783d6314e2e +size 1706930816 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_M.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_M.gguf new file mode 100644 index 0000000..145f235 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd206e60e8366f3b78c974f21f4fd2fb83d4518df9253ab40c7d5c451fcc017f +size 1590014592 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_S.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_S.gguf new file mode 100644 index 0000000..7ea1dca --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691a5565acd9fb341de81216b45b90f8bf85164d2cea5f2a8a850f5722fd2ac1 +size 1453896320 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_M.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_M.gguf new file mode 100644 index 0000000..d7cb063 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd9382b8133b253be54f915bf0a36e99d595d8af106736735eae151b5427ad9 +size 1929441920 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_S.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_S.gguf new file mode 100644 index 0000000..c4a7ab1 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633ed5e4b3d8e3a69957464fe8dee087c05f72e0d51201e9275b4716a604b6b8 +size 1833923200 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_M.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_M.gguf new file mode 100644 index 0000000..a8f6044 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef2c4966f80947c94791f2a9127d7adcaa1ba8a0c289eca82cc8117b881b087 +size 2224353920 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_S.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_S.gguf new file mode 100644 index 0000000..99a6c8a --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33282d1f86fd88e38e2121c0080a9008e399ba01b88aab77764179d79790c00 +size 2169205376 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q6_K.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q6_K.gguf new file mode 100644 index 0000000..789e432 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824481e3ab05e3759ece60ff9b55f0ce2f9d10e4763d91ca7cc0ea80c958f8c0 +size 2537697920 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.Q8_0.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q8_0.gguf new file mode 100644 index 0000000..c74ffe0 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec6e4c1bf0411690e96dd849053735d590d15cb92eeeb93c2c716252724a8b4b +size 3284880736 diff --git a/Jarvis-Qwen2.5-3B-Instruct-20250829.f16.gguf b/Jarvis-Qwen2.5-3B-Instruct-20250829.f16.gguf new file mode 100644 index 0000000..5cf8143 --- /dev/null +++ b/Jarvis-Qwen2.5-3B-Instruct-20250829.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c014249b6a56917121f7c911fe46b45576657edb5190377acc3097570f70f6e +size 6177201376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d93364 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: johanhan/Jarvis-Qwen2.5-3B-Instruct-20250829 +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- autotrain +- text-generation-inference +- text-generation +- peft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/johanhan/Jarvis-Qwen2.5-3B-Instruct-20250829 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Jarvis-Qwen2.5-3B-Instruct-20250829-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/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Jarvis-Qwen2.5-3B-Instruct-20250829-GGUF/resolve/main/Jarvis-Qwen2.5-3B-Instruct-20250829.f16.gguf) | f16 | 6.3 | 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. + +