commit 96356d0bf191d718456c700dadd948f085e1c129 Author: ModelHub XC Date: Sun Sep 27 14:21:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2e5d99f --- /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 +Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-Medical-Conversational.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_M.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_M.gguf new file mode 100644 index 0000000..3165b54 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a80d705e4ccc92a95bdff3119130ee0a61ce63f6b86a8aacc808abdf4113394 +size 1599669984 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_S.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_S.gguf new file mode 100644 index 0000000..13456a9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6d79437c9590d2e0114c2ad670c03189cccc54077d56a8e867424d8e6d4257 +size 1542850272 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_XS.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_XS.gguf new file mode 100644 index 0000000..d14d0fa --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abad287479b28cb3eeaaa1c363d2362f0bd84e75c721ce4ba66744c98ede8582 +size 1476789984 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.IQ4_XS.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ4_XS.gguf new file mode 100644 index 0000000..bfbc658 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da0973050c282d19e4620cc1a085ed4fe6ebe335485c0c41313f5454dc1eb01 +size 1840908000 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q2_K.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q2_K.gguf new file mode 100644 index 0000000..b0a0d4e --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a513bc783b9745b29fb77934323cef4459f0b902bbfad37986788ac10c497400 +size 1363936992 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_L.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_L.gguf new file mode 100644 index 0000000..daf605a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6617d36e30fc808a6e6029fa31f8440680013e941e6599c8ca7eef8be7b5fc03 +size 1815348960 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_M.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_M.gguf new file mode 100644 index 0000000..f3539a8 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2e8e6a98c326cc8931f9f1b67a9c2d58ce7ebf3fc4021ce2c5035962bba3f3 +size 1687160544 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_S.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_S.gguf new file mode 100644 index 0000000..5ec53c8 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d11deee2145349b6cd1d1c94f7ca747d8a6e94d84ec94675dcc79814ff45e98 +size 1542850272 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_M.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_M.gguf new file mode 100644 index 0000000..03f5118 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7928c11652cfef5908a14a4b3f868fb8f72a42dcbc0c83088454f9e516d470f0 +size 2019378912 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_S.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_S.gguf new file mode 100644 index 0000000..542d2d0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95032d7c2bc3131710cef3bbd000d1656ac49e7783cb12885775a06d2841c720 +size 1928201952 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_M.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_M.gguf new file mode 100644 index 0000000..549dfbe --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5de6efbe87af82e6a333e4088b278d875ec4f4d81190c05ecdb51565ed8ac17 +size 2322155232 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_S.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_S.gguf new file mode 100644 index 0000000..0c39ed7 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85684586e5768d2840b23f1f611bb66d5ba92a59c7df13b93aa552046801a178 +size 2269513440 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q6_K.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q6_K.gguf new file mode 100644 index 0000000..33a9308 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a75caaf6ab26bd6f91d53b491014c23692fc635714df907c5d25df534ad122d +size 2643855072 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.Q8_0.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.Q8_0.gguf new file mode 100644 index 0000000..7656399 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4eaf93832ba52e614eb9280bbe94bb3c673f335de691f326a4fcc3cdc2cf51 +size 3421900512 diff --git a/Llama-3.2-3B-Instruct-Medical-Conversational.f16.gguf b/Llama-3.2-3B-Instruct-Medical-Conversational.f16.gguf new file mode 100644 index 0000000..495c397 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Medical-Conversational.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ccb1a3540f481a482a5aa823ca6a1ae2c54bf40dba8258a01cbb2ddee932a1 +size 6433689312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c50863 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Joycean0301/Llama-3.2-3B-Instruct-Medical-Conversational +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Joycean0301/Llama-3.2-3B-Instruct-Medical-Conversational + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Instruct-Medical-Conversational-GGUF).*** + +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/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_XS.gguf) | IQ3_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_S.gguf) | IQ3_S | 1.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.IQ3_M.gguf) | IQ3_M | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-Medical-Conversational-GGUF/resolve/main/Llama-3.2-3B-Instruct-Medical-Conversational.f16.gguf) | f16 | 6.5 | 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. + +