commit fe6783d4abeb2b36c670440826b159aa6be98db2 Author: ModelHub XC Date: Mon Jun 15 04:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ToRoLaMa-7b-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..67c1a93 --- /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 +ToRoLaMa-7b-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ToRoLaMa-7b-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c95a5e6 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: allbyai/ToRoLaMa-7b-v1.0 +language: +- vi +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allbyai/ToRoLaMa-7b-v1.0 + + +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/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ToRoLaMa-7b-v1.0-GGUF/resolve/main/ToRoLaMa-7b-v1.0.f16.gguf) | f16 | 13.8 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/ToRoLaMa-7b-v1.0.IQ4_XS.gguf b/ToRoLaMa-7b-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..4d86f64 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fabfe52802c8c99621378d32a1a5ed417d61e531b86b7283e7aa9d2786abf2fc +size 3727027424 diff --git a/ToRoLaMa-7b-v1.0.Q2_K.gguf b/ToRoLaMa-7b-v1.0.Q2_K.gguf new file mode 100644 index 0000000..af5d92e --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddada74dec2ce41a2cb21658f28000c90b56c779d4ec2e00e3eec0208d2fb8fd +size 2600474656 diff --git a/ToRoLaMa-7b-v1.0.Q3_K_L.gguf b/ToRoLaMa-7b-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..b53d6e3 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91204831527756cb31d37fa0704afad6dffd3f2687d8a46a51cbed8693bdd792 +size 3670672000 diff --git a/ToRoLaMa-7b-v1.0.Q3_K_M.gguf b/ToRoLaMa-7b-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..248ec29 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea0e9c36eb91997fcf1c1526f137533817b672af9d10f5393704499a90929078 +size 3371565696 diff --git a/ToRoLaMa-7b-v1.0.Q3_K_S.gguf b/ToRoLaMa-7b-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..ed080eb --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fa281d95a6f01d0983567992cd30a2c0632d91e97c239c3f5a9083180e043b5 +size 3021865600 diff --git a/ToRoLaMa-7b-v1.0.Q4_K_M.gguf b/ToRoLaMa-7b-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..f4c6a61 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34aa059bb26b2a02e20807748d1c4068d88773805c078da4d184ff18535ed74b +size 4162346080 diff --git a/ToRoLaMa-7b-v1.0.Q4_K_S.gguf b/ToRoLaMa-7b-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..71686e2 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55aba41702d6660cc53b5a7fc4583e31f8345e315a18e4393d5808cf6868152 +size 3938081888 diff --git a/ToRoLaMa-7b-v1.0.Q5_K_M.gguf b/ToRoLaMa-7b-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..9b043ae --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:931081ba372c03714f3a9d89d62e02bdd7b5281070fde772a1615f8b5cedf924 +size 4871821920 diff --git a/ToRoLaMa-7b-v1.0.Q5_K_S.gguf b/ToRoLaMa-7b-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..8c10dce --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd81c99dffdae3c1bf28f5c3addb2404ac49bd9ac02f30881cdb313683b98d40 +size 4740356704 diff --git a/ToRoLaMa-7b-v1.0.Q6_K.gguf b/ToRoLaMa-7b-v1.0.Q6_K.gguf new file mode 100644 index 0000000..49abc17 --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a97c23aed214093848262c7f41dd6f48c877b2fb3d1a762668f6e51d4d7587 +size 5625640000 diff --git a/ToRoLaMa-7b-v1.0.Q8_0.gguf b/ToRoLaMa-7b-v1.0.Q8_0.gguf new file mode 100644 index 0000000..b5ef7ca --- /dev/null +++ b/ToRoLaMa-7b-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea79c6868e2c026646883ecb36e82649889dd19256084ec28e556dbfbfbcc51 +size 7285912704 diff --git a/ToRoLaMa-7b-v1.0.f16.gguf b/ToRoLaMa-7b-v1.0.f16.gguf new file mode 100644 index 0000000..351b4cb --- /dev/null +++ b/ToRoLaMa-7b-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3f705a3cd5586f30695e2a661ac87c48dd2a66db0d278aaaa0a1d04c3655e5 +size 13712774784