commit 33081a530228cbd536a7e8feb8eee8389b467657 Author: ModelHub XC Date: Fri Jul 17 17:12:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ghost-7b-v0.9.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..29ffb5f --- /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-7b-v0.9.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ghost-7b-v0.9.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bb97aa1 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: ghost-x/ghost-7b-v0.9.1 +language: +- en +- vi +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- ghost +--- +## About + + + + + + +static quants of https://huggingface.co/ghost-x/ghost-7b-v0.9.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ghost-7b-v0.9.1-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/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ghost-7b-v0.9.1-GGUF/resolve/main/ghost-7b-v0.9.1.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. + + diff --git a/ghost-7b-v0.9.1.IQ4_XS.gguf b/ghost-7b-v0.9.1.IQ4_XS.gguf new file mode 100644 index 0000000..350bc97 --- /dev/null +++ b/ghost-7b-v0.9.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d00743ce5547c9ca52abb9dde5da97d926d9fd827b6a960330cc678bbd0942 +size 3944389696 diff --git a/ghost-7b-v0.9.1.Q2_K.gguf b/ghost-7b-v0.9.1.Q2_K.gguf new file mode 100644 index 0000000..c9dcb05 --- /dev/null +++ b/ghost-7b-v0.9.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942a5c1ac910e36fd9d612f5f3788deea55029214fe4137cf5a8436652bcc31c +size 2719243328 diff --git a/ghost-7b-v0.9.1.Q3_K_L.gguf b/ghost-7b-v0.9.1.Q3_K_L.gguf new file mode 100644 index 0000000..377d88b --- /dev/null +++ b/ghost-7b-v0.9.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffec06e303ee950b4c76da8817f45df659c5cfaef3305e493f5a66d3a12c7f3e +size 3822025792 diff --git a/ghost-7b-v0.9.1.Q3_K_M.gguf b/ghost-7b-v0.9.1.Q3_K_M.gguf new file mode 100644 index 0000000..02aa91b --- /dev/null +++ b/ghost-7b-v0.9.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d720a439970122c6f0b0da026f15e1bd0a9447090d9cef2963dd4656fbb8b10 +size 3518987328 diff --git a/ghost-7b-v0.9.1.Q3_K_S.gguf b/ghost-7b-v0.9.1.Q3_K_S.gguf new file mode 100644 index 0000000..f4893ab --- /dev/null +++ b/ghost-7b-v0.9.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f4ddf54a8601a6eec308b86acda160261d4d1e062adce2f2dd26974d36c949 +size 3164568640 diff --git a/ghost-7b-v0.9.1.Q4_K_M.gguf b/ghost-7b-v0.9.1.Q4_K_M.gguf new file mode 100644 index 0000000..8aa9168 --- /dev/null +++ b/ghost-7b-v0.9.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:691257b79db587f4988da52ca8e3c1fa63bd3042ce95cda2e9ca2ce492a71c50 +size 4368440384 diff --git a/ghost-7b-v0.9.1.Q4_K_S.gguf b/ghost-7b-v0.9.1.Q4_K_S.gguf new file mode 100644 index 0000000..2e5a87e --- /dev/null +++ b/ghost-7b-v0.9.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:152d5ed3a268defaf42ef4503d95d254e406f26fb0b1b27932c139436eaf476f +size 4140375104 diff --git a/ghost-7b-v0.9.1.Q5_K_M.gguf b/ghost-7b-v0.9.1.Q5_K_M.gguf new file mode 100644 index 0000000..d501488 --- /dev/null +++ b/ghost-7b-v0.9.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039314390e19417475f4977922017e8c76c1968d6fe014d483e7dd503947f437 +size 5131410496 diff --git a/ghost-7b-v0.9.1.Q5_K_S.gguf b/ghost-7b-v0.9.1.Q5_K_S.gguf new file mode 100644 index 0000000..8d06c8d --- /dev/null +++ b/ghost-7b-v0.9.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31c3ead37146aa55e8973d172664cb3c56cf50c54d97543b4704cb0ecab620f +size 4997717056 diff --git a/ghost-7b-v0.9.1.Q6_K.gguf b/ghost-7b-v0.9.1.Q6_K.gguf new file mode 100644 index 0000000..2ae23af --- /dev/null +++ b/ghost-7b-v0.9.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bcf2cf82bd1d56986c76d80750696f32a4a98ca27442da5698c080cca9e01ee +size 5942066240 diff --git a/ghost-7b-v0.9.1.Q8_0.gguf b/ghost-7b-v0.9.1.Q8_0.gguf new file mode 100644 index 0000000..da8d821 --- /dev/null +++ b/ghost-7b-v0.9.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4835649d85cdb1114c5648ebd1182930386e07287d60b1cb22eed1f1d7ef32 +size 7695858752 diff --git a/ghost-7b-v0.9.1.f16.gguf b/ghost-7b-v0.9.1.f16.gguf new file mode 100644 index 0000000..2567750 --- /dev/null +++ b/ghost-7b-v0.9.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b06718734bc99f929128eb35cdcc6ff0ef2a7c300bad88b50aeba4767fa077 +size 14484732992