commit c73be39fcf78d8de485377dea7768915f8879f1a Author: ModelHub XC Date: Thu Sep 24 03:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41d0a7a --- /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 +NPFT-finetuned-LLAMA-2-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NPFT-finetuned-LLAMA-2-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NPFT-finetuned-LLAMA-2-7B.IQ4_XS.gguf b/NPFT-finetuned-LLAMA-2-7B.IQ4_XS.gguf new file mode 100644 index 0000000..0ee3032 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb86aa0ceca3b087b48da97da0cf92e9e1237a8d7019694a2f496360bba8817 +size 3647517344 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q2_K.gguf b/NPFT-finetuned-LLAMA-2-7B.Q2_K.gguf new file mode 100644 index 0000000..984639c --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f9424ba9f772b649fc53766e0faf62883b241265c3ebb006dc2291642f110b +size 2532864672 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q3_K_L.gguf b/NPFT-finetuned-LLAMA-2-7B.Q3_K_L.gguf new file mode 100644 index 0000000..1ddbb02 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fd700c76222df3660a53491a5ca7868066e10de042841726de9364a443d4da +size 3597111968 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q3_K_M.gguf b/NPFT-finetuned-LLAMA-2-7B.Q3_K_M.gguf new file mode 100644 index 0000000..7327017 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd5850a03861266ecb48bfda60d2f1f3af613a2dfe63e5d2077adb43349c846 +size 3298005664 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q3_K_S.gguf b/NPFT-finetuned-LLAMA-2-7B.Q3_K_S.gguf new file mode 100644 index 0000000..da3aef0 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5611bd239fc492cbe0621927687efce5c11f32c0c245aaa06f72f2605a26b1d3 +size 2948305568 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q4_K_M.gguf b/NPFT-finetuned-LLAMA-2-7B.Q4_K_M.gguf new file mode 100644 index 0000000..5a16fcf --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed9abdd189644561fa950f00a8034833c912c129e6374a9568ddc7357c7eae7 +size 4081005216 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q4_K_S.gguf b/NPFT-finetuned-LLAMA-2-7B.Q4_K_S.gguf new file mode 100644 index 0000000..c146f7e --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e677114bc7b85d313fd08d5bd9c4478ac6e3e0042817d82ba081b89ccab5b64 +size 3856741024 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q5_K_M.gguf b/NPFT-finetuned-LLAMA-2-7B.Q5_K_M.gguf new file mode 100644 index 0000000..e25fe40 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165be511a51af5bddcc4a0d3d5360eca2e008ce347ad2da14bdd8a6be53089b3 +size 4783157920 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q5_K_S.gguf b/NPFT-finetuned-LLAMA-2-7B.Q5_K_S.gguf new file mode 100644 index 0000000..0a4c979 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b195eaed739425a5c9c44962bc126476b1ea07a272cd9c58d7f175158ff1e26 +size 4651692704 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q6_K.gguf b/NPFT-finetuned-LLAMA-2-7B.Q6_K.gguf new file mode 100644 index 0000000..40a2ab3 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec0568c50f78cd925e9eb4f200873c9cc1f472bae34c65af482eca8166959b6 +size 5529195168 diff --git a/NPFT-finetuned-LLAMA-2-7B.Q8_0.gguf b/NPFT-finetuned-LLAMA-2-7B.Q8_0.gguf new file mode 100644 index 0000000..7c5e0b1 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e46dd239656773d7c9351de5e4e717c8dba5379de3a3eac534a1ba9b3368409 +size 7161090720 diff --git a/NPFT-finetuned-LLAMA-2-7B.f16.gguf b/NPFT-finetuned-LLAMA-2-7B.f16.gguf new file mode 100644 index 0000000..5ed1162 --- /dev/null +++ b/NPFT-finetuned-LLAMA-2-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212d97a45fde5a37bbbad54542f424bdd20068b84ffaa88dc92276b11b0e0b87 +size 13478105760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..78775d0 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Simwang/NPFT-finetuned-LLAMA-2-7B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Simwang/NPFT-finetuned-LLAMA-2-7B + + +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/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NPFT-finetuned-LLAMA-2-7B-GGUF/resolve/main/NPFT-finetuned-LLAMA-2-7B.f16.gguf) | f16 | 13.6 | 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. + +