commit 1aa73c65ee882661fa84b963290c663f84159f65 Author: ModelHub XC Date: Mon Jun 15 03:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..81ca5a4 --- /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-3.2-SUN-2.5B-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-SUN-2.5B-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-SUN-2.5B-chat.IQ4_XS.gguf b/Llama-3.2-SUN-2.5B-chat.IQ4_XS.gguf new file mode 100644 index 0000000..973050a --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3e68505b4be5b6009d8f80160497408f1f4e3d32f5d926569e478f4c96668d +size 1413027936 diff --git a/Llama-3.2-SUN-2.5B-chat.Q2_K.gguf b/Llama-3.2-SUN-2.5B-chat.Q2_K.gguf new file mode 100644 index 0000000..a9f9102 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755a74292bd60ac8ac4c8719564352a1970d3adfedf4c5aca190e6d77c996b28 +size 1024650912 diff --git a/Llama-3.2-SUN-2.5B-chat.Q3_K_L.gguf b/Llama-3.2-SUN-2.5B-chat.Q3_K_L.gguf new file mode 100644 index 0000000..cc2a2ae --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e1fe48268371d7e5c77cc770285948fd1ff1127da424831b69cd9afb5f5b71 +size 1354630016 diff --git a/Llama-3.2-SUN-2.5B-chat.Q3_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.Q3_K_M.gguf new file mode 100644 index 0000000..de94ef1 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d6b04807baaa1a3413815f32f957750035c0e80697e13c96ffcb0b47e79b3e1 +size 1271006080 diff --git a/Llama-3.2-SUN-2.5B-chat.Q3_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.Q3_K_S.gguf new file mode 100644 index 0000000..8cb2397 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c28f01f2b001aa1e5230a4d23ba8bc652e16a7a5216c7ef8dfeba0506ca657 +size 1172964224 diff --git a/Llama-3.2-SUN-2.5B-chat.Q4_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.Q4_K_M.gguf new file mode 100644 index 0000000..eddcbde --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd1796806200662500e1393ae8e0a32306fab2b6679a746ee53ad2130e5f3a2 +size 1539856864 diff --git a/Llama-3.2-SUN-2.5B-chat.Q4_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.Q4_K_S.gguf new file mode 100644 index 0000000..5fd8f52 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fca6c069f20e3451baf5d9d30867f3f0d4345eab26eea1e123999019eda04913 +size 1475238368 diff --git a/Llama-3.2-SUN-2.5B-chat.Q5_K_M.gguf b/Llama-3.2-SUN-2.5B-chat.Q5_K_M.gguf new file mode 100644 index 0000000..5e4579d --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42a4dc45de3075e84af6f82e8299b15b3dbb0149d5e8d45ab857a60828355c08 +size 1780309984 diff --git a/Llama-3.2-SUN-2.5B-chat.Q5_K_S.gguf b/Llama-3.2-SUN-2.5B-chat.Q5_K_S.gguf new file mode 100644 index 0000000..e2adb4f --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03b1a839ec0f1aec1ce1d9809bfd232d284e1f547343135ee564ecd9acee7367 +size 1742430176 diff --git a/Llama-3.2-SUN-2.5B-chat.Q6_K.gguf b/Llama-3.2-SUN-2.5B-chat.Q6_K.gguf new file mode 100644 index 0000000..4c5bc05 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d61f70d46073e67406f12c41483f252c9cd5b03c981a766bc252c280cf505f4c +size 2035791424 diff --git a/Llama-3.2-SUN-2.5B-chat.Q8_0.gguf b/Llama-3.2-SUN-2.5B-chat.Q8_0.gguf new file mode 100644 index 0000000..1174fd3 --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77175182cd9ff93ca322738bc14d119fbd57cd832232c9f20104c079fe0b2c4d +size 2634362240 diff --git a/Llama-3.2-SUN-2.5B-chat.f16.gguf b/Llama-3.2-SUN-2.5B-chat.f16.gguf new file mode 100644 index 0000000..44d2d8d --- /dev/null +++ b/Llama-3.2-SUN-2.5B-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7558245c136876b4c799a70efb3216e5a0c4edd7b4a18d1e3d9a3ba5cc13dc +size 4951410560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3e6194 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: meditsolutions/Llama-3.2-SUN-2.5B-chat +datasets: +- argilla/OpenHermesPreferences +- argilla/magpie-ultra-v0.1 +- argilla/Capybara-Preferences-Filtered +- mlabonne/open-perfectblend +- HuggingFaceTB/everyday-conversations-llama3.1-2k +- WizardLMTeam/WizardLM_evol_instruct_V2_196k +- ProlificAI/social-reasoning-rlhf +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/meditsolutions/Llama-3.2-SUN-2.5B-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-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-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.IQ4_XS.gguf) | IQ4_XS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q4_K_S.gguf) | Q4_K_S | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q4_K_M.gguf) | Q4_K_M | 1.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q5_K_S.gguf) | Q5_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q6_K.gguf) | Q6_K | 2.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.Q8_0.gguf) | Q8_0 | 2.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-SUN-2.5B-chat-GGUF/resolve/main/Llama-3.2-SUN-2.5B-chat.f16.gguf) | f16 | 5.1 | 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. + +