commit c41c05f378b445f207932b44a30422f9e4595ea2 Author: ModelHub XC Date: Fri Jun 26 07:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ghost-V5-Ultra-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bfa24f --- /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 +Ghost-V5-Ultra-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ghost-V5-Ultra-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ghost-V5-Ultra-8B.IQ4_XS.gguf b/Ghost-V5-Ultra-8B.IQ4_XS.gguf new file mode 100644 index 0000000..919cf5a --- /dev/null +++ b/Ghost-V5-Ultra-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b7179bbae642e08b2c924e24149efff32b1d628eb254cf6972f368a95fc003 +size 3944391008 diff --git a/Ghost-V5-Ultra-8B.Q2_K.gguf b/Ghost-V5-Ultra-8B.Q2_K.gguf new file mode 100644 index 0000000..fabd70e --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8fd6ab532c0c464db6070ebc4af40f9edfe92b10ce30175429260e8d4b82ad6 +size 2719244640 diff --git a/Ghost-V5-Ultra-8B.Q3_K_L.gguf b/Ghost-V5-Ultra-8B.Q3_K_L.gguf new file mode 100644 index 0000000..98a98f8 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8efaf042b274b120924ca11a725c74f7564ece8f1ef7783e53b79f08a4e5ab1 +size 3822027104 diff --git a/Ghost-V5-Ultra-8B.Q3_K_M.gguf b/Ghost-V5-Ultra-8B.Q3_K_M.gguf new file mode 100644 index 0000000..482a592 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774d6e8765426bac5c5cdf7bbdf0da9cde21554127e2591d564b4a56f0937465 +size 3518988640 diff --git a/Ghost-V5-Ultra-8B.Q3_K_S.gguf b/Ghost-V5-Ultra-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7bec71e --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b954af02c8866f4258750a2c5e952d493d8f13ec7d2fc54908d51fe990d1c08 +size 3164569952 diff --git a/Ghost-V5-Ultra-8B.Q4_K_M.gguf b/Ghost-V5-Ultra-8B.Q4_K_M.gguf new file mode 100644 index 0000000..a738b6c --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53083563acbdf54292c8730e6a1c8294bf1509b94edbc16c95f08dafa5de1dd +size 4368441696 diff --git a/Ghost-V5-Ultra-8B.Q4_K_S.gguf b/Ghost-V5-Ultra-8B.Q4_K_S.gguf new file mode 100644 index 0000000..46e51e2 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49ab08746328a18d75bb27d8bc843114f475ad4791025cfae424c282a3753fe +size 4140376416 diff --git a/Ghost-V5-Ultra-8B.Q5_K_M.gguf b/Ghost-V5-Ultra-8B.Q5_K_M.gguf new file mode 100644 index 0000000..6fbfeb4 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0c8936e7ccd75be9c7f1e375db19b045d534761f070e934813379d6eb78470b +size 5131411808 diff --git a/Ghost-V5-Ultra-8B.Q5_K_S.gguf b/Ghost-V5-Ultra-8B.Q5_K_S.gguf new file mode 100644 index 0000000..9eb9ad6 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a286e259ddbea2037024e386fb7144bfed80d27809ab6547f147d493c1718e07 +size 4997718368 diff --git a/Ghost-V5-Ultra-8B.Q6_K.gguf b/Ghost-V5-Ultra-8B.Q6_K.gguf new file mode 100644 index 0000000..c90c62c --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e9a2a717f084e8df978c6202364c3f8a928338bff9d17e3af0ee3e9f6538c52 +size 5942067552 diff --git a/Ghost-V5-Ultra-8B.Q8_0.gguf b/Ghost-V5-Ultra-8B.Q8_0.gguf new file mode 100644 index 0000000..9286cc6 --- /dev/null +++ b/Ghost-V5-Ultra-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6834b663ff8cd6746d75589dc39215c159d8a49f39c5cef2c8aa0a513b1e6099 +size 7695860064 diff --git a/Ghost-V5-Ultra-8B.f16.gguf b/Ghost-V5-Ultra-8B.f16.gguf new file mode 100644 index 0000000..d2b0ae5 --- /dev/null +++ b/Ghost-V5-Ultra-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfb7ec0c4268a2e434b7544733632493d26a1c5b942bc88212fde45ff779a6e +size 14484734304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6e835a2 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ghost4280/Ghost-V5-Ultra-8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/ghost4280/Ghost-V5-Ultra-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Ghost-V5-Ultra-8B-GGUF).*** + +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/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ghost-V5-Ultra-8B-GGUF/resolve/main/Ghost-V5-Ultra-8B.f16.gguf) | f16 | 14.6 | 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. + +