commit 04b049cbd7f3b2babddf4d64a5468aacfb8440fe Author: ModelHub XC Date: Wed Sep 30 05:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RickLLama-3.1-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..acbd59a --- /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 +RickLLama-3.1-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RickLLama-3.1-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9777470 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: theneuralmaze/RickLLama-3.1-8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +--- +## About + + + + + + +static quants of https://huggingface.co/theneuralmaze/RickLLama-3.1-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/RickLLama-3.1-8B-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/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RickLLama-3.1-8B-GGUF/resolve/main/RickLLama-3.1-8B.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/RickLLama-3.1-8B.IQ4_XS.gguf b/RickLLama-3.1-8B.IQ4_XS.gguf new file mode 100644 index 0000000..bcc7a3e --- /dev/null +++ b/RickLLama-3.1-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49bbd0434f6ac85fe7936837b55edd9979a5a170211fb7630c55541f297fbd97 +size 4484368896 diff --git a/RickLLama-3.1-8B.Q2_K.gguf b/RickLLama-3.1-8B.Q2_K.gguf new file mode 100644 index 0000000..1356c1b --- /dev/null +++ b/RickLLama-3.1-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8a243f9b47dfb2833a8abb127d85b0f6998c98b566ff1f9f13cc3bafc911566 +size 3179137536 diff --git a/RickLLama-3.1-8B.Q3_K_L.gguf b/RickLLama-3.1-8B.Q3_K_L.gguf new file mode 100644 index 0000000..573c6eb --- /dev/null +++ b/RickLLama-3.1-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9f444f27de1f71581c6805acc669e547fc7eadf700ba578c86a579d6e37b53 +size 4321962496 diff --git a/RickLLama-3.1-8B.Q3_K_M.gguf b/RickLLama-3.1-8B.Q3_K_M.gguf new file mode 100644 index 0000000..5e3edc4 --- /dev/null +++ b/RickLLama-3.1-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fadb7d89b833e4850a55a0f1c225d8cd314a90471681eb30b3eef39c73906b1f +size 4018924032 diff --git a/RickLLama-3.1-8B.Q3_K_S.gguf b/RickLLama-3.1-8B.Q3_K_S.gguf new file mode 100644 index 0000000..a297a40 --- /dev/null +++ b/RickLLama-3.1-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5cdca3997ead97a0fb6a08faa6f6d9f84274fe77b27ad66168bec8a47ec7da +size 3664505344 diff --git a/RickLLama-3.1-8B.Q4_K_M.gguf b/RickLLama-3.1-8B.Q4_K_M.gguf new file mode 100644 index 0000000..5df18b2 --- /dev/null +++ b/RickLLama-3.1-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7c7ee9d58c9b85b31b4c32af6a6a8b5ad9cfa8c3a714fd689892bf4fb4e045 +size 4920740352 diff --git a/RickLLama-3.1-8B.Q4_K_S.gguf b/RickLLama-3.1-8B.Q4_K_S.gguf new file mode 100644 index 0000000..54669e1 --- /dev/null +++ b/RickLLama-3.1-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fc85a2ef35a3a245a2cefecc7ba30922cfd287a823b8fe7383f17dc88f889b +size 4692675072 diff --git a/RickLLama-3.1-8B.Q5_K_M.gguf b/RickLLama-3.1-8B.Q5_K_M.gguf new file mode 100644 index 0000000..907b920 --- /dev/null +++ b/RickLLama-3.1-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72151e2f5d474aa0ef225135b6ddfe9a428230e40e874780822a67200ed43314 +size 5732993536 diff --git a/RickLLama-3.1-8B.Q5_K_S.gguf b/RickLLama-3.1-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0b607fb --- /dev/null +++ b/RickLLama-3.1-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa05f11e7a287a261fcb9c1c06f8b4b1fe88447cff1e81f08aaa94e2a445cc1 +size 5599300096 diff --git a/RickLLama-3.1-8B.Q6_K.gguf b/RickLLama-3.1-8B.Q6_K.gguf new file mode 100644 index 0000000..76192d2 --- /dev/null +++ b/RickLLama-3.1-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3ca85ac45402634e33b7fc3ac79b70ecad2f5c41b37bfa4aa9fd365d4ae092b +size 6596012544 diff --git a/RickLLama-3.1-8B.Q8_0.gguf b/RickLLama-3.1-8B.Q8_0.gguf new file mode 100644 index 0000000..02ce86b --- /dev/null +++ b/RickLLama-3.1-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef58b3c7a5c98f60c8293a0ad507e27d44a85f0591c7a43549d73023e0ac348d +size 8540776960 diff --git a/RickLLama-3.1-8B.f16.gguf b/RickLLama-3.1-8B.f16.gguf new file mode 100644 index 0000000..96aa8ec --- /dev/null +++ b/RickLLama-3.1-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc2353ab5885056fbad93ded772185972aca7bcb4eb43875c85034ccf028a43 +size 16068897280