commit cbc43e327f24d555eaaf150e2315d13e97e2302b Author: ModelHub XC Date: Thu Jun 11 11:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1629ec4 --- /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-3.2-1B-Instruct-NL2SH.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-Instruct-NL2SH.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-Instruct-NL2SH.IQ4_XS.gguf b/Llama-3.2-1B-Instruct-NL2SH.IQ4_XS.gguf new file mode 100644 index 0000000..f396122 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04ba753dfd1beb6029fb5bfed03e59722b298c13d8f5885de8d63ed3881e120e +size 748384352 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q2_K.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q2_K.gguf new file mode 100644 index 0000000..5e589dd --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b37e428429443b42c0f6697ac44137f35ea887b74c7eaba235490de13c20b25 +size 580874336 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q3_K_L.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_L.gguf new file mode 100644 index 0000000..cd34d98 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ce6c458b433cc105928cd2d6e74216aeed7a5f6a5f7e95d119c2d634141e26 +size 732524640 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q3_K_M.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_M.gguf new file mode 100644 index 0000000..5b91670 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e108022ef307cea34586ba1b2b87ec0e50a1c798a3b335527c6efb7400db376f +size 690843744 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q3_K_S.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_S.gguf new file mode 100644 index 0000000..d1e1d6a --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753d2e72c625ca016309ee97067f67353f39451b184554099e39321ed19eec29 +size 641691744 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q4_K_M.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q4_K_M.gguf new file mode 100644 index 0000000..97a5f15 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b89b087376c2f3562fdc610aca16a83e1e731bea96d0e1b4a60a7c7833b4a6 +size 807694432 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q4_K_S.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q4_K_S.gguf new file mode 100644 index 0000000..026e609 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944678604194537b718f5d4c518586f518bd283c4cebdf140a46babe61f4508c +size 775647328 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q5_K_M.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q5_K_M.gguf new file mode 100644 index 0000000..d17c91a --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb84016902c5b86e10e5b2ee725dbdd245f54f93e8e1ef147d8850125db692bc +size 911503456 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q5_K_S.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q5_K_S.gguf new file mode 100644 index 0000000..6b3dbbc --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4458522f0f285a4fc179dd8162248e47b22ec5b9edd06eb4765b4a5103be7fc +size 892563552 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q6_K.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q6_K.gguf new file mode 100644 index 0000000..75aee1a --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0320bd1799c57f76b3022a10182f85ff302d5c0834b27a1c9eba6ee578ea1f03 +size 1021800544 diff --git a/Llama-3.2-1B-Instruct-NL2SH.Q8_0.gguf b/Llama-3.2-1B-Instruct-NL2SH.Q8_0.gguf new file mode 100644 index 0000000..2889bcb --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a540cde71463e0b5023dc39bc2260c3322e59ffd061fcdda99319c4d64899b +size 1321082976 diff --git a/Llama-3.2-1B-Instruct-NL2SH.f16.gguf b/Llama-3.2-1B-Instruct-NL2SH.f16.gguf new file mode 100644 index 0000000..b6a1636 --- /dev/null +++ b/Llama-3.2-1B-Instruct-NL2SH.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:018700ee4eb09496d7592ddf04df0aab235265d401da5fc63ab7d48ee3d01927 +size 2479595616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..24a4c15 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: westenfelder/Llama-3.2-1B-Instruct-NL2SH +datasets: +- westenfelder/NL2SH-ALFA +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/westenfelder/Llama-3.2-1B-Instruct-NL2SH + + +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-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-1B-Instruct-NL2SH-GGUF/resolve/main/Llama-3.2-1B-Instruct-NL2SH.f16.gguf) | f16 | 2.6 | 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. + +