commit 71f942e4eb4ea334717b62e0c2fa8523a4d53bca Author: ModelHub XC Date: Mon Jun 15 19:56:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Oracle-Tinyllama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..85e12dc --- /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 +Oracle-Tinyllama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Oracle-Tinyllama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Oracle-Tinyllama.IQ4_XS.gguf b/Oracle-Tinyllama.IQ4_XS.gguf new file mode 100644 index 0000000..629b30e --- /dev/null +++ b/Oracle-Tinyllama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fa7e7fc784d351df24fec1ea7722f981827a00bc4cac127863eb1617ec2bbdf +size 609807968 diff --git a/Oracle-Tinyllama.Q2_K.gguf b/Oracle-Tinyllama.Q2_K.gguf new file mode 100644 index 0000000..36b10fd --- /dev/null +++ b/Oracle-Tinyllama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a162d295fa7932d88c2b9b56e45827289761527e057a21989cc388cd08d5fb9f +size 432131680 diff --git a/Oracle-Tinyllama.Q3_K_L.gguf b/Oracle-Tinyllama.Q3_K_L.gguf new file mode 100644 index 0000000..1fbf257 --- /dev/null +++ b/Oracle-Tinyllama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1441fe721bb6014cc165f3285662cff2e7ca57d2001953df20ee7c1bf5b917c9 +size 591527520 diff --git a/Oracle-Tinyllama.Q3_K_M.gguf b/Oracle-Tinyllama.Q3_K_M.gguf new file mode 100644 index 0000000..81efba6 --- /dev/null +++ b/Oracle-Tinyllama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa162c415bed3195492a197a6370838d78b8416b24b3736b4f29fba7e412d47f +size 548404832 diff --git a/Oracle-Tinyllama.Q3_K_S.gguf b/Oracle-Tinyllama.Q3_K_S.gguf new file mode 100644 index 0000000..449a20b --- /dev/null +++ b/Oracle-Tinyllama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06754d79a4c2894eb664e087814f582bab280a8a1558b7b9e7ca6fd3ceb9a9d4 +size 499342944 diff --git a/Oracle-Tinyllama.Q4_K_M.gguf b/Oracle-Tinyllama.Q4_K_M.gguf new file mode 100644 index 0000000..475c89a --- /dev/null +++ b/Oracle-Tinyllama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5917276311317e5b9aae0d6f8bbc338dabc49a8b663b1c05c04ebb8a0fda6c50 +size 667815520 diff --git a/Oracle-Tinyllama.Q4_K_S.gguf b/Oracle-Tinyllama.Q4_K_S.gguf new file mode 100644 index 0000000..06aa2e6 --- /dev/null +++ b/Oracle-Tinyllama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860e10de170387366385c7e099593fb126b4a1506740e77a2d784e0ea38dbc0c +size 639872608 diff --git a/Oracle-Tinyllama.Q5_K_M.gguf b/Oracle-Tinyllama.Q5_K_M.gguf new file mode 100644 index 0000000..68713b9 --- /dev/null +++ b/Oracle-Tinyllama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f235c2c4345c7eb6f9b2a1d245572770b761e8cf8d3bee75d3a3df6f227c63 +size 782044768 diff --git a/Oracle-Tinyllama.Q5_K_S.gguf b/Oracle-Tinyllama.Q5_K_S.gguf new file mode 100644 index 0000000..38e50df --- /dev/null +++ b/Oracle-Tinyllama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b22b66d4610a93766a8867cbeb4bb131c5ba2eef2518265000657fe103efecd0 +size 766029408 diff --git a/Oracle-Tinyllama.Q6_K.gguf b/Oracle-Tinyllama.Q6_K.gguf new file mode 100644 index 0000000..1f05838 --- /dev/null +++ b/Oracle-Tinyllama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0334a6f6d73e707e0db4f9f8d6bb01233b83b0e5afd91f96ec01355b96f5b7c +size 903413344 diff --git a/Oracle-Tinyllama.Q8_0.gguf b/Oracle-Tinyllama.Q8_0.gguf new file mode 100644 index 0000000..fc5148d --- /dev/null +++ b/Oracle-Tinyllama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f3e087b39a48ff88034eb0db904522968983e6ee23d70eacc0ab2dcb85d26e +size 1169808992 diff --git a/Oracle-Tinyllama.f16.gguf b/Oracle-Tinyllama.f16.gguf new file mode 100644 index 0000000..c151894 --- /dev/null +++ b/Oracle-Tinyllama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4699ac0b42b6ccb9ebd8d1a1fa05c426ddba65e6d5f6b98d4fbd0534691773f +size 2201017952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6549fa0 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: SePO2024/Oracle-Tinyllama +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SePO2024/Oracle-Tinyllama + + +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/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Oracle-Tinyllama-GGUF/resolve/main/Oracle-Tinyllama.f16.gguf) | f16 | 2.3 | 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. + +