From 6a1cc790ec513bc295fc58da6bb502e8eb6386d0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 28 Sep 2026 23:37:19 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/TeenyTinyLlama-Doc-160m-GGUF Source: Original Platform --- .gitattributes | 49 +++++++++++++++++++ README.md | 74 +++++++++++++++++++++++++++++ TeenyTinyLlama-Doc-160m.IQ3_M.gguf | 3 ++ TeenyTinyLlama-Doc-160m.IQ3_S.gguf | 3 ++ TeenyTinyLlama-Doc-160m.IQ3_XS.gguf | 3 ++ TeenyTinyLlama-Doc-160m.IQ4_XS.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q2_K.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q3_K_L.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q3_K_M.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q3_K_S.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q4_K_M.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q4_K_S.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q5_K_M.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q5_K_S.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q6_K.gguf | 3 ++ TeenyTinyLlama-Doc-160m.Q8_0.gguf | 3 ++ TeenyTinyLlama-Doc-160m.f16.gguf | 3 ++ 17 files changed, 168 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 TeenyTinyLlama-Doc-160m.IQ3_M.gguf create mode 100644 TeenyTinyLlama-Doc-160m.IQ3_S.gguf create mode 100644 TeenyTinyLlama-Doc-160m.IQ3_XS.gguf create mode 100644 TeenyTinyLlama-Doc-160m.IQ4_XS.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q2_K.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q3_K_L.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q3_K_M.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q3_K_S.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q4_K_M.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q4_K_S.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q5_K_M.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q5_K_S.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q6_K.gguf create mode 100644 TeenyTinyLlama-Doc-160m.Q8_0.gguf create mode 100644 TeenyTinyLlama-Doc-160m.f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d09c9b4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +TeenyTinyLlama-Doc-160m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.f16.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TeenyTinyLlama-Doc-160m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..54cf8b5 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: mmoreirast/Doctor-Llama-160m +datasets: +- mmoreirast/medicine-training-pt +- mmoreirast/medicine-evaluation-pt +language: +- pt +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama-2 +- pt +- medicine +--- +## About + + + + + + +static quants of https://huggingface.co/mmoreirast/Doctor-Llama-160m + + +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/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q2_K.gguf) | Q2_K | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.IQ3_XS.gguf) | IQ3_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.IQ3_S.gguf) | IQ3_S | 0.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q3_K_S.gguf) | Q3_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.IQ3_M.gguf) | IQ3_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q3_K_M.gguf) | Q3_K_M | 0.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q3_K_L.gguf) | Q3_K_L | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.IQ4_XS.gguf) | IQ4_XS | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q4_K_S.gguf) | Q4_K_S | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q4_K_M.gguf) | Q4_K_M | 0.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q5_K_S.gguf) | Q5_K_S | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q5_K_M.gguf) | Q5_K_M | 0.2 | | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q6_K.gguf) | Q6_K | 0.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.Q8_0.gguf) | Q8_0 | 0.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TeenyTinyLlama-Doc-160m-GGUF/resolve/main/TeenyTinyLlama-Doc-160m.f16.gguf) | f16 | 0.4 | 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/TeenyTinyLlama-Doc-160m.IQ3_M.gguf b/TeenyTinyLlama-Doc-160m.IQ3_M.gguf new file mode 100644 index 0000000..b1e48d8 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45c3929979c364f612f6864e406de54adc519f11e8ee99b73cb01332b173aa38 +size 82416768 diff --git a/TeenyTinyLlama-Doc-160m.IQ3_S.gguf b/TeenyTinyLlama-Doc-160m.IQ3_S.gguf new file mode 100644 index 0000000..1965733 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97e71fcdf809d1576916f532b6b60d8a15efc0c5c940d66573381035db515e5 +size 80223360 diff --git a/TeenyTinyLlama-Doc-160m.IQ3_XS.gguf b/TeenyTinyLlama-Doc-160m.IQ3_XS.gguf new file mode 100644 index 0000000..9404fcc --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1fba394b15154100fdc6ab7ca4cfbef4a248accb5c0b5eea49447e75d9f854c +size 77569152 diff --git a/TeenyTinyLlama-Doc-160m.IQ4_XS.gguf b/TeenyTinyLlama-Doc-160m.IQ4_XS.gguf new file mode 100644 index 0000000..324e96b --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:390e2801b755e39f41f8f150a78ee7835bbe2526af0f5713de4955e35770e238 +size 94589728 diff --git a/TeenyTinyLlama-Doc-160m.Q2_K.gguf b/TeenyTinyLlama-Doc-160m.Q2_K.gguf new file mode 100644 index 0000000..0d0a994 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64124f4401f3e9dc7f19e2a491d9c5bd55ad10816ac1eda1bf48a770771550c +size 70538720 diff --git a/TeenyTinyLlama-Doc-160m.Q3_K_L.gguf b/TeenyTinyLlama-Doc-160m.Q3_K_L.gguf new file mode 100644 index 0000000..7e02054 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5988e9c47be7fd78753ca5080b494d92306915e995abc72a86156e459e0d8a +size 91171968 diff --git a/TeenyTinyLlama-Doc-160m.Q3_K_M.gguf b/TeenyTinyLlama-Doc-160m.Q3_K_M.gguf new file mode 100644 index 0000000..fc423ab --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acad469d5ad8f75322551e88e2ca585c44b999e1c7d7b454bfacba806a092671 +size 86011008 diff --git a/TeenyTinyLlama-Doc-160m.Q3_K_S.gguf b/TeenyTinyLlama-Doc-160m.Q3_K_S.gguf new file mode 100644 index 0000000..733e4a8 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d926a01dcd0d3c8c978ad82890fc311821b9a66add88257e1184d5700d4dce08 +size 80223360 diff --git a/TeenyTinyLlama-Doc-160m.Q4_K_M.gguf b/TeenyTinyLlama-Doc-160m.Q4_K_M.gguf new file mode 100644 index 0000000..1db467b --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98d7aed99732ba43f3604c6943a0fb8c6a0739f902eda6390f6cb26e8d132ee9 +size 103089984 diff --git a/TeenyTinyLlama-Doc-160m.Q4_K_S.gguf b/TeenyTinyLlama-Doc-160m.Q4_K_S.gguf new file mode 100644 index 0000000..7436226 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f033c4ee92fd0009dc54d5d38c4a70ec076c8656153b367a64ed5736abffd90 +size 99117888 diff --git a/TeenyTinyLlama-Doc-160m.Q5_K_M.gguf b/TeenyTinyLlama-Doc-160m.Q5_K_M.gguf new file mode 100644 index 0000000..dc9b97c --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786779906b5df1ea4e0db8308532fc64c68f3ab861dc2b6e8e1945fa25f94cb3 +size 118106112 diff --git a/TeenyTinyLlama-Doc-160m.Q5_K_S.gguf b/TeenyTinyLlama-Doc-160m.Q5_K_S.gguf new file mode 100644 index 0000000..0e82055 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6769510dfa036ca2121145435f8df347c19159cb474fa97336f2213f924207a +size 115756032 diff --git a/TeenyTinyLlama-Doc-160m.Q6_K.gguf b/TeenyTinyLlama-Doc-160m.Q6_K.gguf new file mode 100644 index 0000000..4bfada2 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86939a489841af7a45df28cc3eeec06728322c351d661dff4b68cf1d015672f +size 134060768 diff --git a/TeenyTinyLlama-Doc-160m.Q8_0.gguf b/TeenyTinyLlama-Doc-160m.Q8_0.gguf new file mode 100644 index 0000000..d49cb5c --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57c81b76e72e31c8e6e57667a8b2c27565ca5370d65d1b5f734f2ad365a0e38 +size 173392288 diff --git a/TeenyTinyLlama-Doc-160m.f16.gguf b/TeenyTinyLlama-Doc-160m.f16.gguf new file mode 100644 index 0000000..4745f58 --- /dev/null +++ b/TeenyTinyLlama-Doc-160m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b5ed6c1001eed3629c2cedb46b272292f5e9d504b4740a81d26259e0b94a33d +size 325643488