commit 7dd6334cf0d4131bf36d8bdabafd6c0a4f47cbb1 Author: ModelHub XC Date: Sat Aug 8 18:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..993a29a --- /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-3.1-Minitron-4B-Depth-Neo-10w.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-Minitron-4B-Depth-Neo-10w.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.IQ4_XS.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.IQ4_XS.gguf new file mode 100644 index 0000000..f8408c2 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c653fe0bc92d6378690a616b40b94fe5d616a703769fc320cc609d45cfa73b33 +size 2601112544 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q2_K.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q2_K.gguf new file mode 100644 index 0000000..7004e82 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb30c2135093bcae8cdada1a97acfb76d247e1b89b3b55948866820e80beeaf +size 1895142368 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_L.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_L.gguf new file mode 100644 index 0000000..d436080 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bde16e7a82c3d0da331e0741a68d7af71d0cd083ec2ae044c2b98eb5785f5c86 +size 2493232096 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_M.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_M.gguf new file mode 100644 index 0000000..1fe5066 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a6d66ea0038161ea338c9b045afb7c05c76feebd7f8513fc320668f444522d +size 2342237152 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_S.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_S.gguf new file mode 100644 index 0000000..972a95c --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2061d46bde817fc45e8ec1db909ad92527314452e0ef1829f9bbf14a8b707e8 +size 2164503520 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_M.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_M.gguf new file mode 100644 index 0000000..6aa1ddc --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab76cbe04df8f55c2d3232517dd519b7d872299dee08b81e855cfe375842e971 +size 2827506656 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_S.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_S.gguf new file mode 100644 index 0000000..8c0165a --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a607f26b79b0dd08c18f649d6c575769f41a9ccc00eb5a65c4fecbf6672f342 +size 2714522592 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_M.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_M.gguf new file mode 100644 index 0000000..1de8632 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc5137cb8e2f50b6b9bef4dbb2f871e02dadf17b98af21b3202e3e24c0d8a43 +size 3266466784 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_S.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_S.gguf new file mode 100644 index 0000000..305e472 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a450f32f3d2be81271e4f825df68aaabdc550d0bcc73559ddfd76645f7452599 +size 3199620064 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q6_K.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q6_K.gguf new file mode 100644 index 0000000..ce28d56 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6e12363cc6f01e175b7e33c87a883b95cbcb4a240d543483944a545a314831 +size 3732861920 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q8_0.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q8_0.gguf new file mode 100644 index 0000000..2d43d27 --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8ecd6ea9809c0bc6b11ba393bc1fa56e1ae658ec7900e173706226d23a88b2 +size 4832474080 diff --git a/Llama-3.1-Minitron-4B-Depth-Neo-10w.f16.gguf b/Llama-3.1-Minitron-4B-Depth-Neo-10w.f16.gguf new file mode 100644 index 0000000..e8e002f --- /dev/null +++ b/Llama-3.1-Minitron-4B-Depth-Neo-10w.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:452a8ca0d71d95055318922f588b93e7a5be29e976e666f2372864d98886890c +size 9089037280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b12aa6b --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: yang31210999/Llama-3.1-Minitron-4B-Depth-Neo-BAAI-100k +datasets: +- BAAI/Infinity-Instruct +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yang31210999/Llama-3.1-Minitron-4B-Depth-Neo-BAAI-100k + + +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/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q2_K.gguf) | Q2_K | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_S.gguf) | Q3_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q5_K_M.gguf) | Q5_K_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-Minitron-4B-Depth-Neo-10w-GGUF/resolve/main/Llama-3.1-Minitron-4B-Depth-Neo-10w.f16.gguf) | f16 | 9.2 | 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. + +