commit e105e14630c537befa0019575eb0d3c4491a5e3b Author: ModelHub XC Date: Sat Jun 20 19:40:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-turbcat-instruct-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5a5289c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama3-turbcat-instruct-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-turbcat-instruct-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..26dc8c9 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: turboderp/llama3-turbcat-instruct-8b +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/turboderp/llama3-turbcat-instruct-8b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-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/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-turbcat-instruct-8b-GGUF/resolve/main/llama3-turbcat-instruct-8b.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. + + diff --git a/llama3-turbcat-instruct-8b.IQ3_M.gguf b/llama3-turbcat-instruct-8b.IQ3_M.gguf new file mode 100644 index 0000000..0cfd2b1 --- /dev/null +++ b/llama3-turbcat-instruct-8b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8d874ab83062a628e8d71d9ba9e3ad9459a365b44881d9a0b5f8d1bf26b7019 +size 3784823680 diff --git a/llama3-turbcat-instruct-8b.IQ3_S.gguf b/llama3-turbcat-instruct-8b.IQ3_S.gguf new file mode 100644 index 0000000..49ab5c9 --- /dev/null +++ b/llama3-turbcat-instruct-8b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2412648ab3753d80ceec61c34b2cd18e2585384da4b296f89252fae455699f6 +size 3682325376 diff --git a/llama3-turbcat-instruct-8b.IQ3_XS.gguf b/llama3-turbcat-instruct-8b.IQ3_XS.gguf new file mode 100644 index 0000000..0db7a35 --- /dev/null +++ b/llama3-turbcat-instruct-8b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e5d9ce6f2d2b54cabd24e0763eb3726708c0872afb92d3fe4f8e17c0034a4b +size 3518747520 diff --git a/llama3-turbcat-instruct-8b.IQ4_XS.gguf b/llama3-turbcat-instruct-8b.IQ4_XS.gguf new file mode 100644 index 0000000..eeab1f2 --- /dev/null +++ b/llama3-turbcat-instruct-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef59a26d0cab87660d989f47a42d60f23d6d9cf11b7721d66ea1c29632618375 +size 4484363136 diff --git a/llama3-turbcat-instruct-8b.Q2_K.gguf b/llama3-turbcat-instruct-8b.Q2_K.gguf new file mode 100644 index 0000000..288e89a --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bbdc2dc492361989e6c90743928c196d7da651a555e6fc7c05a0642df8d417e +size 3179131776 diff --git a/llama3-turbcat-instruct-8b.Q3_K_L.gguf b/llama3-turbcat-instruct-8b.Q3_K_L.gguf new file mode 100644 index 0000000..044a217 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3994b8ee36540f428aea3a81c4f44ded64f926336dff83cf6737534cdd7aaceb +size 4321956736 diff --git a/llama3-turbcat-instruct-8b.Q3_K_M.gguf b/llama3-turbcat-instruct-8b.Q3_K_M.gguf new file mode 100644 index 0000000..a95a422 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3318ae013fc05229d3f839aa4c97723113233b250daa523515418fa11a6b22e2 +size 4018918272 diff --git a/llama3-turbcat-instruct-8b.Q3_K_S.gguf b/llama3-turbcat-instruct-8b.Q3_K_S.gguf new file mode 100644 index 0000000..9eb6174 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e28a3d74f0aea67ce4de273286c8f9524cd036e083b71c077d357fe35be80c87 +size 3664499584 diff --git a/llama3-turbcat-instruct-8b.Q4_K_M.gguf b/llama3-turbcat-instruct-8b.Q4_K_M.gguf new file mode 100644 index 0000000..6892710 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f81bd942bcf415144f85139903977458d5bd91089cc75fa7da903667fb2b07b +size 4920734592 diff --git a/llama3-turbcat-instruct-8b.Q4_K_S.gguf b/llama3-turbcat-instruct-8b.Q4_K_S.gguf new file mode 100644 index 0000000..1a733b5 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074127cb324980cead66198d16ef3e542e2df04d4bd824a0d7c772c86fbfa158 +size 4692669312 diff --git a/llama3-turbcat-instruct-8b.Q5_K_M.gguf b/llama3-turbcat-instruct-8b.Q5_K_M.gguf new file mode 100644 index 0000000..2d56814 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb8079dd6e0be2d7c8dffbf82d75d28f79b4f82691ca060f6049476882ce5da +size 5732987776 diff --git a/llama3-turbcat-instruct-8b.Q5_K_S.gguf b/llama3-turbcat-instruct-8b.Q5_K_S.gguf new file mode 100644 index 0000000..1f4e21b --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199f986f6f0fa4e567b0459fb9f0d8aed9fb46f3b1ab80a48880b8bb4dafed42 +size 5599294336 diff --git a/llama3-turbcat-instruct-8b.Q6_K.gguf b/llama3-turbcat-instruct-8b.Q6_K.gguf new file mode 100644 index 0000000..075f342 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aefe107b9279e2b7f58216470796f18a59e253b767649e74cee398af63f8b263 +size 6596006784 diff --git a/llama3-turbcat-instruct-8b.Q8_0.gguf b/llama3-turbcat-instruct-8b.Q8_0.gguf new file mode 100644 index 0000000..b438436 --- /dev/null +++ b/llama3-turbcat-instruct-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef444c7f0b428a072bfc575a9fe4e30e349be84de9b114ad6d038209bab1986 +size 8540771200 diff --git a/llama3-turbcat-instruct-8b.f16.gguf b/llama3-turbcat-instruct-8b.f16.gguf new file mode 100644 index 0000000..af51432 --- /dev/null +++ b/llama3-turbcat-instruct-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae130409093e08504fe6f39766f9bbfcf24e991f41e2b714e014ed3cb2b3192e +size 16068891520