commit fd4bd3a599e77a975c806ce2ed271833eb3eb86f Author: ModelHub XC Date: Sun Sep 27 04:59:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama2-doctor-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cfe7011 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama2-doctor.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama2-doctor.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d286f4 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ashnaz/llama2-doctor +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ashnaz/llama2-doctor + + +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/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama2-doctor-GGUF/resolve/main/llama2-doctor.f16.gguf) | f16 | 16.2 | 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. + + diff --git a/llama2-doctor.IQ3_M.gguf b/llama2-doctor.IQ3_M.gguf new file mode 100644 index 0000000..e70e1e7 --- /dev/null +++ b/llama2-doctor.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9736684fb950d41c592a94b396b5b98f40f3e961613b2b7e686fcef0b8a1478c +size 3784823104 diff --git a/llama2-doctor.IQ3_S.gguf b/llama2-doctor.IQ3_S.gguf new file mode 100644 index 0000000..fbf152e --- /dev/null +++ b/llama2-doctor.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02c9ebeab897ee32ac6576d51c3643e8032a4119d4ff054d559f4848a1e0263 +size 3682324800 diff --git a/llama2-doctor.IQ3_XS.gguf b/llama2-doctor.IQ3_XS.gguf new file mode 100644 index 0000000..3cd88bb --- /dev/null +++ b/llama2-doctor.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6792f3a2726fdc0631e178a4f53e5c1164f93f22fcc50f305457b235845072f +size 3518746944 diff --git a/llama2-doctor.IQ4_XS.gguf b/llama2-doctor.IQ4_XS.gguf new file mode 100644 index 0000000..9e6b6b0 --- /dev/null +++ b/llama2-doctor.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0511c88b256c5c79dabbf1bc8d46efd009f3300e04778594c425f1f0696e6dfd +size 4484362560 diff --git a/llama2-doctor.Q2_K.gguf b/llama2-doctor.Q2_K.gguf new file mode 100644 index 0000000..808cb33 --- /dev/null +++ b/llama2-doctor.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab362a1bba5366f95fd1d67c8ee7cebf424f84aba1a77d3489066c883b6cd8f7 +size 3179131200 diff --git a/llama2-doctor.Q3_K_L.gguf b/llama2-doctor.Q3_K_L.gguf new file mode 100644 index 0000000..7faeb6b --- /dev/null +++ b/llama2-doctor.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f5862520cb6934bbd5257d7a8d85a69a1a34331b289ef4fda16a136898cb47 +size 4321956160 diff --git a/llama2-doctor.Q3_K_M.gguf b/llama2-doctor.Q3_K_M.gguf new file mode 100644 index 0000000..1cf9080 --- /dev/null +++ b/llama2-doctor.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc59e78ba7db9bc86ceb0c93b404c8080ebc6b182d40fe500b439a8246f45013 +size 4018917696 diff --git a/llama2-doctor.Q3_K_S.gguf b/llama2-doctor.Q3_K_S.gguf new file mode 100644 index 0000000..90accdc --- /dev/null +++ b/llama2-doctor.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a6ea29a89bcaa0572d875e59ef9c92be5fefc20664155a00afd8f72cd09c6f +size 3664499008 diff --git a/llama2-doctor.Q4_K_M.gguf b/llama2-doctor.Q4_K_M.gguf new file mode 100644 index 0000000..3e14329 --- /dev/null +++ b/llama2-doctor.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d4840f7b64e0dd409709e979c1e46e9fe26c1b9235ded0da4c58c2489073dd +size 4920734016 diff --git a/llama2-doctor.Q4_K_S.gguf b/llama2-doctor.Q4_K_S.gguf new file mode 100644 index 0000000..5faad56 --- /dev/null +++ b/llama2-doctor.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5eb64e56e90e556ed910f2621aeb4b9205a6dbed36d54e738fc29d2de2165e7 +size 4692668736 diff --git a/llama2-doctor.Q5_K_M.gguf b/llama2-doctor.Q5_K_M.gguf new file mode 100644 index 0000000..5b468cb --- /dev/null +++ b/llama2-doctor.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7c8935a1eff23ff44b494831cefcf16a992f804efc4a2d0e585f1a9ca83776 +size 5732987200 diff --git a/llama2-doctor.Q5_K_S.gguf b/llama2-doctor.Q5_K_S.gguf new file mode 100644 index 0000000..5b48c9a --- /dev/null +++ b/llama2-doctor.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c2efb73f2101fdfeeb9de6f45ed1f7e675a326a8b2f75766e189f48e9e649b +size 5599293760 diff --git a/llama2-doctor.Q6_K.gguf b/llama2-doctor.Q6_K.gguf new file mode 100644 index 0000000..2999ecb --- /dev/null +++ b/llama2-doctor.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f37faeef934ef2ed54a27512091ee3dbb288f40eb51171445252e0dd8fba85c +size 6596006208 diff --git a/llama2-doctor.Q8_0.gguf b/llama2-doctor.Q8_0.gguf new file mode 100644 index 0000000..992b4c6 --- /dev/null +++ b/llama2-doctor.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9415ee8f9576b73857024040b28bdd17a8951b39267769aceff329f1adb8a7 +size 8540770624 diff --git a/llama2-doctor.f16.gguf b/llama2-doctor.f16.gguf new file mode 100644 index 0000000..9d875e3 --- /dev/null +++ b/llama2-doctor.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f86c1fd11ed1411660caa0ee4cfbc90c1405be191fc9dc8f218c7c97005b669 +size 16068890944