commit ac07d74c4dbe4fd00ddcc808b964fff76338a51c Author: ModelHub XC Date: Sun Jun 21 15:44:26 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0607ece --- /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 +ArliAI-Llama-3-8B-Formax-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +ArliAI-Llama-3-8B-Formax-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_M.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_M.gguf new file mode 100644 index 0000000..b0dbf78 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a600f35b61ebf8f6f2b7e107089c03fd1e88790d68c362fa3d8a51d6a0d17b4 +size 3784823584 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_S.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_S.gguf new file mode 100644 index 0000000..b63826c --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e386e4ab85cb387b4b4e0c0c3d24783cadc4423c78ad6aad18aa536f0795ad9 +size 3682325280 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_XS.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_XS.gguf new file mode 100644 index 0000000..5e3231c --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab12a866b33d5b31bb214f88592127fc87874677ec53c79bc71e371cc54c1b77 +size 3518747424 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.IQ4_XS.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..db7e92a --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd870a3c621d7e8f3057284d0d8875fab6f77786ddc610ddb22b698fb97fa64c +size 4484363040 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q2_K.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q2_K.gguf new file mode 100644 index 0000000..bcfbe3e --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d418e8e42e6292811c1dfe1abc70d974ee10c2f8bd6b4a7e1b441263f7582e7c +size 3179131680 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_L.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..c3bc2fa --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865f3b378d0ade3f32b2af688b24c71eeee8c98bc9273c5a13d5ea709e7aa76b +size 4321956640 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_M.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..4ed6eb7 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a448600f3a04cb245f2995dcd67795d60ac077455620d7b8b653fb069728b5 +size 4018918176 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_S.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..0f61f15 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519ceef6b4ea1f3961d8cca9a12a5a924886fa4f8b981cfe9e791805dca0c29f +size 3664499488 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_M.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..a244beb --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f3a7035c48145f2a77ffc51588f93adbc11461a14dfdacd9888c60537fad72f +size 4920734496 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_S.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..f2335bf --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7de1a89db4463db19fcda90671f1fd024aaabbc2d1797724bcf620df4316a4 +size 4692669216 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_M.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..ac56ce3 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c36eea55ea7cb2a7a82eba5a915623e19d57aa5ea305c6f1a2ac0c6add2f459 +size 5732987680 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_S.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..0d8620c --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a073387bf6b5b92ef26eebc0d278e217d3d4ae0496da08bcb6ad976cc469224c +size 5599294240 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q6_K.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q6_K.gguf new file mode 100644 index 0000000..d705b94 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043e094b10f1800c0ea0f4b18e9c5f7e671ec6869e9f13721d2f472ea1494947 +size 6596006688 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.Q8_0.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.Q8_0.gguf new file mode 100644 index 0000000..8dc93de --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd060f3dd011ddcbdb783bfea493544821d00d1a6ce391af3a949c846bba121 +size 8540771104 diff --git a/ArliAI-Llama-3-8B-Formax-v1.0.f16.gguf b/ArliAI-Llama-3-8B-Formax-v1.0.f16.gguf new file mode 100644 index 0000000..28bb964 --- /dev/null +++ b/ArliAI-Llama-3-8B-Formax-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9497935df2633a5fe90d7005d4f5049ff21080a56296eb8fc6ce6204e53dc67b +size 16068891424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..385b247 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: OwenArli/Llama-3-8B-ArliAI-Formax-v1.0 +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/OwenArli/Llama-3-8B-ArliAI-Formax-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ArliAI-Llama-3-8B-Formax-v1.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-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/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ArliAI-Llama-3-8B-Formax-v1.0-GGUF/resolve/main/ArliAI-Llama-3-8B-Formax-v1.0.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. + +