commit 49d030711141f01ad2b1e4c4394a8240386a489d Author: ModelHub XC Date: Wed May 20 17:48:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AlphaMed-3B-instruct-rl-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e264674 --- /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 +AlphaMed-3B-instruct-rl.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlphaMed-3B-instruct-rl.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AlphaMed-3B-instruct-rl.IQ4_XS.gguf b/AlphaMed-3B-instruct-rl.IQ4_XS.gguf new file mode 100644 index 0000000..adb063a --- /dev/null +++ b/AlphaMed-3B-instruct-rl.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13687b2f9d840853556592646772ae324d701a8dce7219b408c2603520a67f2f +size 1918491488 diff --git a/AlphaMed-3B-instruct-rl.Q2_K.gguf b/AlphaMed-3B-instruct-rl.Q2_K.gguf new file mode 100644 index 0000000..554de24 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa967945e5e03083556672d8405341e810a81661b9d9e8bc8b6a97bd51a67322 +size 1376856928 diff --git a/AlphaMed-3B-instruct-rl.Q3_K_L.gguf b/AlphaMed-3B-instruct-rl.Q3_K_L.gguf new file mode 100644 index 0000000..549631c --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c219cb90bbb2e29b8cbac47bb95f2d0c392fbb328289cc0512272ec4df3d8cf1 +size 1841095520 diff --git a/AlphaMed-3B-instruct-rl.Q3_K_M.gguf b/AlphaMed-3B-instruct-rl.Q3_K_M.gguf new file mode 100644 index 0000000..2f02a62 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:443972b446f486b08b494e20c23b15c00498817fa9cb0d33def7b6ec1aa75581 +size 1724179296 diff --git a/AlphaMed-3B-instruct-rl.Q3_K_S.gguf b/AlphaMed-3B-instruct-rl.Q3_K_S.gguf new file mode 100644 index 0000000..4291c08 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6502da97e9cc87a240bb9e72e9abb2d0faf113ec0b2be4d6d7737c4f89777988 +size 1588061024 diff --git a/AlphaMed-3B-instruct-rl.Q4_K_M.gguf b/AlphaMed-3B-instruct-rl.Q4_K_M.gguf new file mode 100644 index 0000000..ee7b3ff --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4924ee08deb5a36e0bfc923f0ff0a545179fc9cde6ef6dc06e498a9bb4ee5b14 +size 2104933216 diff --git a/AlphaMed-3B-instruct-rl.Q4_K_S.gguf b/AlphaMed-3B-instruct-rl.Q4_K_S.gguf new file mode 100644 index 0000000..e4beea7 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dba9677cadc566766a2c66dff64b6b174352fbe1c0fc05d74020b3a44214513 +size 2009414496 diff --git a/AlphaMed-3B-instruct-rl.Q5_K_M.gguf b/AlphaMed-3B-instruct-rl.Q5_K_M.gguf new file mode 100644 index 0000000..3906895 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89aab0bd8a212ac36d84865363740404af0fa261e94b4b1507de734f6ea390f +size 2438740832 diff --git a/AlphaMed-3B-instruct-rl.Q5_K_S.gguf b/AlphaMed-3B-instruct-rl.Q5_K_S.gguf new file mode 100644 index 0000000..b6d943f --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f0a4c0bdfbcc376360be31bdcf906ed19b3479ac0e36bfc76adc53ac109547 +size 2383592288 diff --git a/AlphaMed-3B-instruct-rl.Q6_K.gguf b/AlphaMed-3B-instruct-rl.Q6_K.gguf new file mode 100644 index 0000000..1aeca96 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c634ef1f4953bf1b9c7fbfc54e577e83f720c0d398fcbe53d8d7890cf7f489aa +size 2793411424 diff --git a/AlphaMed-3B-instruct-rl.Q8_0.gguf b/AlphaMed-3B-instruct-rl.Q8_0.gguf new file mode 100644 index 0000000..a9c4a29 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b30c4f7507b21a7a305a573e57bb6aebaf39ec8f4914337cab1367ac80c2dd +size 3616088928 diff --git a/AlphaMed-3B-instruct-rl.f16.gguf b/AlphaMed-3B-instruct-rl.f16.gguf new file mode 100644 index 0000000..ec98669 --- /dev/null +++ b/AlphaMed-3B-instruct-rl.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbba8439f4a751c137642006e9a458adbd599af2854efaf8351c3c584f85911f +size 6800647008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2587e1f --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: che111/AlphaMed-3B-instruct-rl +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/che111/AlphaMed-3B-instruct-rl + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-i1-GGUF +## 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/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AlphaMed-3B-instruct-rl-GGUF/resolve/main/AlphaMed-3B-instruct-rl.f16.gguf) | f16 | 6.9 | 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. + +