commit c0ba8c9c1fdded9a648c7540b714c928c60a090d Author: ModelHub XC Date: Tue Jun 16 02:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a99ce17 --- /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 +meditsolutions_Llama-3.2-SUN-1B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +meditsolutions_Llama-3.2-SUN-1B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..80c18fe --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Nexesenex/meditsolutions_Llama-3.2-SUN-1B-Instruct +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 +- allenai/tulu-3-sft-mixture +- allenai/llama-3.1-tulu-3-8b-preference-mixture +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/meditsolutions_Llama-3.2-SUN-1B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-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/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/meditsolutions_Llama-3.2-SUN-1B-Instruct-GGUF/resolve/main/meditsolutions_Llama-3.2-SUN-1B-Instruct.f16.gguf) | f16 | 3.1 | 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. + + diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.IQ4_XS.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..e4834e8 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7807a5ff1f8c5209f2e0ed5593d937972e28b00f7e141c6e074760e51085d9a4 +size 887929600 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q2_K.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..ddec968 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac722d46afeb212aa9f97d284d0dce3aef59313983768a2604190363a5938743 +size 667065088 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_L.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..413a4fd --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d349f30a7d0aaa26968276d75b081af2384f5c5ed33987c66bef560c22b884 +size 845392640 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_M.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..cb7d1bb --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6591cfed535c92d15a3ea048b309a7e18d6b28ce1d085cdc0bb1f57ee02ca678 +size 803711744 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_S.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..7e641fe --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5bce9c2daae1e1ca59368e45e03b9a707d842e79ed148c23fd3b1758c873d8 +size 754559744 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_M.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..7f900f1 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6acb23b401f7921e271be72a33d79efd7a128b346fb12a33ba24122d2285e5 +size 955448064 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_S.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..947ad83 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c6a70f24f86b9681f320f21b3f0862da933849e2f315c346ce73252039082c2 +size 923400960 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_M.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..324e082 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf442a8b9fa30bba7b3500ef74c3932c2f6c9bf30f23a13ab1f5a465786a0b7 +size 1092090624 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_S.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..bfb7973 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3576d597ea83635b1e8efd11368a90452699cc4a2e5446ca7afd9a96b54bd9 +size 1073150720 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q6_K.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..907d147 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ad4c477b2b9ba09ef1c759f13bfcce8264d5d84e841dfdbc1e67c72beb093f +size 1237273344 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q8_0.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..be9ab91 --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c6bce98a164f5f9e5cf3ba1e21afd22b550ce97174257b7f5ac642237007c3 +size 1600170752 diff --git a/meditsolutions_Llama-3.2-SUN-1B-Instruct.f16.gguf b/meditsolutions_Llama-3.2-SUN-1B-Instruct.f16.gguf new file mode 100644 index 0000000..7b7bd1c --- /dev/null +++ b/meditsolutions_Llama-3.2-SUN-1B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26eab7faed902370603e5140c62c7381e393582372a652341d3d682d586ad850 +size 3004934912