commit 45efa29b868fce334c44a5f756d7bfcd0b74b0bd Author: ModelHub XC Date: Wed Sep 23 09:16:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1_8I_ARC_RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cf25b2a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Llama3.1_8I_ARC_RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1_8I_ARC_RP.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1_8I_ARC_RP.IQ4_XS.gguf b/Llama3.1_8I_ARC_RP.IQ4_XS.gguf new file mode 100644 index 0000000..d204693 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a8d3e2aa1f4d230e166605296d08ddff0e00e5ab192b51d282edb4598ddc5a +size 4484368320 diff --git a/Llama3.1_8I_ARC_RP.Q2_K.gguf b/Llama3.1_8I_ARC_RP.Q2_K.gguf new file mode 100644 index 0000000..63f969e --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a7bea29f823797c8b101bd75088909656a8c25d3ecd83966b81ce8d208c760 +size 3179136960 diff --git a/Llama3.1_8I_ARC_RP.Q3_K_L.gguf b/Llama3.1_8I_ARC_RP.Q3_K_L.gguf new file mode 100644 index 0000000..f67e5a3 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1135ad123798d95666040c386470565d2216e8f747dd32d54df30641ae7432 +size 4321961920 diff --git a/Llama3.1_8I_ARC_RP.Q3_K_M.gguf b/Llama3.1_8I_ARC_RP.Q3_K_M.gguf new file mode 100644 index 0000000..d70baf2 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc1c9cb9957a1b781ceea6f1fc8fcfffb52d54af778b4b580e65ec0668569e0 +size 4018923456 diff --git a/Llama3.1_8I_ARC_RP.Q3_K_S.gguf b/Llama3.1_8I_ARC_RP.Q3_K_S.gguf new file mode 100644 index 0000000..af73ad1 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b257c633bbbf0501adceb6a93f7d2a4bb9d872c88cced178f8997eb6977b24b8 +size 3664504768 diff --git a/Llama3.1_8I_ARC_RP.Q4_0_4_4.gguf b/Llama3.1_8I_ARC_RP.Q4_0_4_4.gguf new file mode 100644 index 0000000..c3820db --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11179ecf8549e7d6152771ef0c2a5e86703a38fc73cde9a956c4c6ae7548691 +size 4661217216 diff --git a/Llama3.1_8I_ARC_RP.Q4_K_M.gguf b/Llama3.1_8I_ARC_RP.Q4_K_M.gguf new file mode 100644 index 0000000..88a32e4 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d943fe4a1e31eaa1071bd944f13e3708c98c53c9f7f4d390b3324757c958185 +size 4920739776 diff --git a/Llama3.1_8I_ARC_RP.Q4_K_S.gguf b/Llama3.1_8I_ARC_RP.Q4_K_S.gguf new file mode 100644 index 0000000..ef75841 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd7418de34095144722bfa9928355a5ed526640ec0d4a60b65d701292be9ee1 +size 4692674496 diff --git a/Llama3.1_8I_ARC_RP.Q5_K_M.gguf b/Llama3.1_8I_ARC_RP.Q5_K_M.gguf new file mode 100644 index 0000000..566c58c --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f7adac33753c560edaee001217eb4a8f3c6c5b6c392663e25403319a98d349 +size 5732992960 diff --git a/Llama3.1_8I_ARC_RP.Q5_K_S.gguf b/Llama3.1_8I_ARC_RP.Q5_K_S.gguf new file mode 100644 index 0000000..88f738c --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32778dd387b9e4748146866657f8a6963902faa585222b42daf1996321afcf24 +size 5599299520 diff --git a/Llama3.1_8I_ARC_RP.Q6_K.gguf b/Llama3.1_8I_ARC_RP.Q6_K.gguf new file mode 100644 index 0000000..f95bacd --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2921c7ebd711476ec7c6a351ca870ed3efb7459f79d2079f9e59e4868154d8da +size 6596011968 diff --git a/Llama3.1_8I_ARC_RP.Q8_0.gguf b/Llama3.1_8I_ARC_RP.Q8_0.gguf new file mode 100644 index 0000000..430e92b --- /dev/null +++ b/Llama3.1_8I_ARC_RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949f565382ac2483e3512be693c6e0b0a513e1b325598ef66398b0ba6c434fb6 +size 8540776384 diff --git a/Llama3.1_8I_ARC_RP.f16.gguf b/Llama3.1_8I_ARC_RP.f16.gguf new file mode 100644 index 0000000..e419314 --- /dev/null +++ b/Llama3.1_8I_ARC_RP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37db466f9bd368b41ee4c63dc8de44d400512cd04117316fe9cdfe4c9828b4a3 +size 16068896704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b925ada --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: naturalseeker/Llama3.1_8I_ARC_RP +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/naturalseeker/Llama3.1_8I_ARC_RP + + +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/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1_8I_ARC_RP-GGUF/resolve/main/Llama3.1_8I_ARC_RP.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. + +