commit 2019a1b88666bcb92205f451ae8ed719eed36e82 Author: ModelHub XC Date: Fri Jun 5 14:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BastiAI-2.5-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..99cf6fe --- /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 +BastiAI-2.5-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BastiAI-2.5-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BastiAI-2.5-Instruct.IQ4_XS.gguf b/BastiAI-2.5-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..25ed87f --- /dev/null +++ b/BastiAI-2.5-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320042bdc32f1c6f22e2ae9d3e1fc3c9250cd4ef578da7ca425b8492f4c1d0a8 +size 2286316832 diff --git a/BastiAI-2.5-Instruct.Q2_K.gguf b/BastiAI-2.5-Instruct.Q2_K.gguf new file mode 100644 index 0000000..4b68782 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cef7b7eacaf82f0d254adf28a5e8a956a228eb7dc46e379cc74012f364038c5 +size 1669500192 diff --git a/BastiAI-2.5-Instruct.Q3_K_L.gguf b/BastiAI-2.5-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..78a2ed3 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d15e1fa00646ee68d24c281a688055c1421cb676fea230ecc278a56343bb6a +size 2239786272 diff --git a/BastiAI-2.5-Instruct.Q3_K_M.gguf b/BastiAI-2.5-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b8f3bd6 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bebc01a2f7149958d274a999b0d3f5d977fd6ab5a086809f7ba33e17f47659 +size 2075618592 diff --git a/BastiAI-2.5-Instruct.Q3_K_S.gguf b/BastiAI-2.5-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..00d2b11 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fd96aa02ba438a6d1cc0629f076a3ac81b98a0e887e002ae5566c0c38bdea3 +size 1886997792 diff --git a/BastiAI-2.5-Instruct.Q4_K_M.gguf b/BastiAI-2.5-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..1115637 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bbc3c9166388b84273359f441295a9398f3dc65dca0158e60f53852aa3e8d78 +size 2497281312 diff --git a/BastiAI-2.5-Instruct.Q4_K_S.gguf b/BastiAI-2.5-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..797c6e8 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8fb6deab1f3b3a55ddbf031f4faa99a43366b9dba1675b985ad92d801812c2c +size 2383310112 diff --git a/BastiAI-2.5-Instruct.Q5_K_M.gguf b/BastiAI-2.5-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b979aaa --- /dev/null +++ b/BastiAI-2.5-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427c0b93138e033ea6eda849a1f63b75e2500343d189d78ea9d3aab51e0c3994 +size 2889514272 diff --git a/BastiAI-2.5-Instruct.Q5_K_S.gguf b/BastiAI-2.5-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..d1081cb --- /dev/null +++ b/BastiAI-2.5-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9759bbf2afa8b3293406f388d902899142f4cd47c3cc5bf08d4cff09460e9e8 +size 2823712032 diff --git a/BastiAI-2.5-Instruct.Q6_K.gguf b/BastiAI-2.5-Instruct.Q6_K.gguf new file mode 100644 index 0000000..d5a65c3 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:526eb70370627893ecf42efb944677970370aa8cdfbc0b985eb970f04395d6ce +size 3306261792 diff --git a/BastiAI-2.5-Instruct.Q8_0.gguf b/BastiAI-2.5-Instruct.Q8_0.gguf new file mode 100644 index 0000000..5b96722 --- /dev/null +++ b/BastiAI-2.5-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2def1e6e9836fc4da64def8cde0616e64eb8f1e293586621d68f0cbca57bd3d9 +size 4280405792 diff --git a/BastiAI-2.5-Instruct.f16.gguf b/BastiAI-2.5-Instruct.f16.gguf new file mode 100644 index 0000000..5927d29 --- /dev/null +++ b/BastiAI-2.5-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37ad5cd816b15378aa40ef992bb8e4411ce1a5ad54c643f71345ea4dbc40b0e9 +size 8051285792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b51c0fc --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Cartik/BastiAI-2.5-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Cartik/BastiAI-2.5-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BastiAI-2.5-Instruct-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/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BastiAI-2.5-Instruct-GGUF/resolve/main/BastiAI-2.5-Instruct.f16.gguf) | f16 | 8.2 | 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. + +