commit 12c945c8f3c0d2def5c1c209b36dc6d6961977b9 Author: ModelHub XC Date: Mon Jun 1 12:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/voice_3b_llama3.2_instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba433c6 --- /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 +voice_3b_llama3.2_instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +voice_3b_llama3.2_instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2852487 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: lm2445/PVminerLLM_3b_llama3.2_instruct +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lm2445/PVminerLLM_3b_llama3.2_instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#voice_3b_llama3.2_instruct-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/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/voice_3b_llama3.2_instruct-GGUF/resolve/main/voice_3b_llama3.2_instruct.f16.gguf) | f16 | 6.5 | 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/voice_3b_llama3.2_instruct.IQ4_XS.gguf b/voice_3b_llama3.2_instruct.IQ4_XS.gguf new file mode 100644 index 0000000..8f40058 --- /dev/null +++ b/voice_3b_llama3.2_instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06373f3945ce367cc62a9da1928f2678577bf3efce48130be3f285142a72f760 +size 1840906752 diff --git a/voice_3b_llama3.2_instruct.Q2_K.gguf b/voice_3b_llama3.2_instruct.Q2_K.gguf new file mode 100644 index 0000000..5ff5745 --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b982a6c5e2affbb1e12e44d978d4fa8ee4a61fc9e1f86efa0bf087e9f0f72505 +size 1363935744 diff --git a/voice_3b_llama3.2_instruct.Q3_K_L.gguf b/voice_3b_llama3.2_instruct.Q3_K_L.gguf new file mode 100644 index 0000000..d3288e5 --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cfea82d00d9252a96cb3c4e573321a82458e65df1b3bcb18ccb0555384aceb3 +size 1815347712 diff --git a/voice_3b_llama3.2_instruct.Q3_K_M.gguf b/voice_3b_llama3.2_instruct.Q3_K_M.gguf new file mode 100644 index 0000000..87b8c5b --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a5a9d8267e6e0c9a7a9bf51f9b36b70844e08944a037f0b37dbdbef7b9de1d +size 1687159296 diff --git a/voice_3b_llama3.2_instruct.Q3_K_S.gguf b/voice_3b_llama3.2_instruct.Q3_K_S.gguf new file mode 100644 index 0000000..e3ecb7a --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731dff4172b56faee54810ace93e4e4106f27c7ed89e1425b314e7eb7905ac6c +size 1542849024 diff --git a/voice_3b_llama3.2_instruct.Q4_K_M.gguf b/voice_3b_llama3.2_instruct.Q4_K_M.gguf new file mode 100644 index 0000000..25f851f --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6be457b17a1031501219a04e2ae2331c4760569d160e1f38daf9ad39f1a476 +size 2019377664 diff --git a/voice_3b_llama3.2_instruct.Q4_K_S.gguf b/voice_3b_llama3.2_instruct.Q4_K_S.gguf new file mode 100644 index 0000000..778f17e --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5029d68ea8717939be8e814d6a565232eb0e792a1716e61690ad08a68e43eb16 +size 1928200704 diff --git a/voice_3b_llama3.2_instruct.Q5_K_M.gguf b/voice_3b_llama3.2_instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a1c94c1 --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315903df675238fd3872d41770814b9a894352117153abbee59f7cfe75a7f709 +size 2322153984 diff --git a/voice_3b_llama3.2_instruct.Q5_K_S.gguf b/voice_3b_llama3.2_instruct.Q5_K_S.gguf new file mode 100644 index 0000000..2d41cc7 --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbfd7cda488cd77b72122ba0ac37341c06f2976ade4d0a515a1509f6b64a18c +size 2269512192 diff --git a/voice_3b_llama3.2_instruct.Q6_K.gguf b/voice_3b_llama3.2_instruct.Q6_K.gguf new file mode 100644 index 0000000..67e6ebe --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb416fd8cbf6faca7a102d5f5566597def31ac3fbb9f1bbd76b1b1d3c7263ce1 +size 2643853824 diff --git a/voice_3b_llama3.2_instruct.Q8_0.gguf b/voice_3b_llama3.2_instruct.Q8_0.gguf new file mode 100644 index 0000000..825ea65 --- /dev/null +++ b/voice_3b_llama3.2_instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599d630b3eb02b4ee46db2048793022c10379c0ea87992d829c4d9eb768eac88 +size 3421899264 diff --git a/voice_3b_llama3.2_instruct.f16.gguf b/voice_3b_llama3.2_instruct.f16.gguf new file mode 100644 index 0000000..3cc799c --- /dev/null +++ b/voice_3b_llama3.2_instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc1b6604b72eb60d320723a76fc917b8a16435dc48b9309c17282cf8a2795eb +size 6433688064