commit d585124608e5e79e2a3df45a37a674a9cf36596c Author: ModelHub XC Date: Mon Jul 6 22:07:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4050a8e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Aisha-Llama-3.1-8B-Complete.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.f16.gguf filter=lfs diff=lfs merge=lfs -text +Aisha-Llama-3.1-8B-Complete.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Aisha-Llama-3.1-8B-Complete.IQ4_XS.gguf b/Aisha-Llama-3.1-8B-Complete.IQ4_XS.gguf new file mode 100644 index 0000000..77fa7a0 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:605af8c5a7b490aef7d178d7f8ed632dc94a4d3f561f66bc7d0b0723c9c572a5 +size 4484367936 diff --git a/Aisha-Llama-3.1-8B-Complete.Q2_K.gguf b/Aisha-Llama-3.1-8B-Complete.Q2_K.gguf new file mode 100644 index 0000000..4a4cca4 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a036ae6ba3ec7d177ffda6f0466c7e20b26d7c29d577863d716ad7a621207f8 +size 3179136576 diff --git a/Aisha-Llama-3.1-8B-Complete.Q3_K_L.gguf b/Aisha-Llama-3.1-8B-Complete.Q3_K_L.gguf new file mode 100644 index 0000000..744d04e --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4880b8b8dd990e1704c863a4ac549051c9d421e6ee1e18986216f9c97df80f1e +size 4321961536 diff --git a/Aisha-Llama-3.1-8B-Complete.Q3_K_M.gguf b/Aisha-Llama-3.1-8B-Complete.Q3_K_M.gguf new file mode 100644 index 0000000..8bbb92b --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:415a6a91831613e33d74a2953595c20076507c2201f72d14d49d125462dbda00 +size 4018923072 diff --git a/Aisha-Llama-3.1-8B-Complete.Q3_K_S.gguf b/Aisha-Llama-3.1-8B-Complete.Q3_K_S.gguf new file mode 100644 index 0000000..d2f243d --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a70cf3ce2a045604b60f28357672ec13bb6751b37faca1ba081730ed75d919 +size 3664504384 diff --git a/Aisha-Llama-3.1-8B-Complete.Q4_K_M.gguf b/Aisha-Llama-3.1-8B-Complete.Q4_K_M.gguf new file mode 100644 index 0000000..4d41fed --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebcfe3462cbce76072a476c5d38bd442793a9f578308ce0688b5bb625bea062 +size 4920739392 diff --git a/Aisha-Llama-3.1-8B-Complete.Q4_K_S.gguf b/Aisha-Llama-3.1-8B-Complete.Q4_K_S.gguf new file mode 100644 index 0000000..85e0751 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e54cb02c82738cf78d66f449c0dd6ad5b86195143f938fa98ffc207a8856420a +size 4692674112 diff --git a/Aisha-Llama-3.1-8B-Complete.Q5_K_M.gguf b/Aisha-Llama-3.1-8B-Complete.Q5_K_M.gguf new file mode 100644 index 0000000..0fc644c --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2354a135f284ea35a1240b50d1f5b5dc404da210173dfcdb3b77eb97c07036f6 +size 5732992576 diff --git a/Aisha-Llama-3.1-8B-Complete.Q5_K_S.gguf b/Aisha-Llama-3.1-8B-Complete.Q5_K_S.gguf new file mode 100644 index 0000000..bebda17 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8bce5efe820ef53f5b9db03f9ca7794495581e475df2ba4205eeeab2e67c6e1 +size 5599299136 diff --git a/Aisha-Llama-3.1-8B-Complete.Q6_K.gguf b/Aisha-Llama-3.1-8B-Complete.Q6_K.gguf new file mode 100644 index 0000000..9fb3882 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56ab7abce4a4f649f78cd0b3e0613f82563684e10c65b0a8300bd463e2a20cd +size 6596011584 diff --git a/Aisha-Llama-3.1-8B-Complete.Q8_0.gguf b/Aisha-Llama-3.1-8B-Complete.Q8_0.gguf new file mode 100644 index 0000000..01e7b61 --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68877b347d72bf582dbd5b93d59769658605a1db89cf46e1d9f75d9ea0d52f55 +size 8540776000 diff --git a/Aisha-Llama-3.1-8B-Complete.f16.gguf b/Aisha-Llama-3.1-8B-Complete.f16.gguf new file mode 100644 index 0000000..9a1615c --- /dev/null +++ b/Aisha-Llama-3.1-8B-Complete.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b076953e8f5abbbdc5d2bee31c7d6435d8126e58807e9a885361c97e9e07761a +size 16068896320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..357a61d --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: V3N0M/Aisha-Llama-3.1-8B-Complete +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- gguf +- llama.cpp +- unsloth +--- +## About + + + + + + + + + +static quants of https://huggingface.co/V3N0M/Aisha-Llama-3.1-8B-Complete + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Aisha-Llama-3.1-8B-Complete-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-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/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Aisha-Llama-3.1-8B-Complete-GGUF/resolve/main/Aisha-Llama-3.1-8B-Complete.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. + +