commit f99af52481108bffb3383c64f10dc7cebf893781 Author: ModelHub XC Date: Fri Aug 7 13:11:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..017b11d --- /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-3-8B-SFT-RuoZhiBa.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-SFT-RuoZhiBa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-SFT-RuoZhiBa.IQ4_XS.gguf b/Llama-3-8B-SFT-RuoZhiBa.IQ4_XS.gguf new file mode 100644 index 0000000..e3f85ec --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f579732c5cf29096ee9e4b975e86e4420dc2a482d4e732e887a69badb5e2526 +size 4484363680 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q2_K.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q2_K.gguf new file mode 100644 index 0000000..6eea8e3 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6987b80898bf0994635f8f75fa5b85a326a9efbcdf80e4375727a93878c57c22 +size 3179132320 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q3_K_L.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_L.gguf new file mode 100644 index 0000000..db9de3a --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eb99b518761c2cda79e2fd9b02d8c43dcd84c134228844c9ec239d536bcdc11 +size 4321957280 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q3_K_M.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_M.gguf new file mode 100644 index 0000000..20d5ece --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3952293a2f7c356706301ba8ecc2ec9db349f3d9cde51b8318246eb10de7e19 +size 4018918816 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q3_K_S.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_S.gguf new file mode 100644 index 0000000..5a43c3f --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b08ede2cd34f9b5a393cf77b31e00838c1e4338a1642c1816ec8c782b3e09c2f +size 3664500128 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q4_K_M.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q4_K_M.gguf new file mode 100644 index 0000000..8c574c8 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ccdc12de02b060ea60b88fd7d4af000b3db0992dc5f403bbbb7b87622fe87b +size 4920735136 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q4_K_S.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q4_K_S.gguf new file mode 100644 index 0000000..47a1a05 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6998bbe47e202d3b99bbd05916fc4b4a962a62971f6050a4911a4b6124761922 +size 4692669856 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q5_K_M.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q5_K_M.gguf new file mode 100644 index 0000000..43a5b5e --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:120d927db7c8029abdfc2a85fba06f35cb71b811606b92eed242bf414285f497 +size 5732988320 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q5_K_S.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q5_K_S.gguf new file mode 100644 index 0000000..b36c7f8 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d9c30afaf82398298ae7b0f5a63273ea7c5f54f2195e0cc3b4af6951457018 +size 5599294880 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q6_K.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q6_K.gguf new file mode 100644 index 0000000..a3de6ea --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f1cd9417a0d26b7079b7f3849e3852087e62dca9a8164684441b5417f7771b +size 6596007328 diff --git a/Llama-3-8B-SFT-RuoZhiBa.Q8_0.gguf b/Llama-3-8B-SFT-RuoZhiBa.Q8_0.gguf new file mode 100644 index 0000000..865a787 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1d5ed61b7807711a859128326c8244ae9700b0a955bd6b92f1934b0579ec3f +size 8540771744 diff --git a/Llama-3-8B-SFT-RuoZhiBa.f16.gguf b/Llama-3-8B-SFT-RuoZhiBa.f16.gguf new file mode 100644 index 0000000..1023fe8 --- /dev/null +++ b/Llama-3-8B-SFT-RuoZhiBa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffb4b4a3f6aac73ecef0dc99b1c82bd4fcdefae984ba8a04ca7252b78701711 +size 16068892064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d5e7da --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Nagi-ovo/Llama-3-8B-SFT-RuoZhiBa +datasets: +- LooksJuicy/ruozhiba +- vicgalle/alpaca-gpt4 +language: +- zh +- en +library_name: transformers +quantized_by: mradermacher +tags: +- SFT +- fintune +- QLoRA +- Llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/Nagi-ovo/Llama-3-8B-SFT-RuoZhiBa + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-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/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-SFT-RuoZhiBa-GGUF/resolve/main/Llama-3-8B-SFT-RuoZhiBa.f16.gguf) | f16 | 16.2 | 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. + +