commit f2e142d7ca046539a3a7ff243c00fdbd9e4c9041 Author: ModelHub XC Date: Tue Oct 20 15:00:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..136d56c --- /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 +llama3-psychiatrist-v1.3B-fp16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3-psychiatrist-v1.3B-fp16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a8765d6 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: wiweka24/llama3-psychiatrist-v1.3B-fp16 +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/wiweka24/llama3-psychiatrist-v1.3B-fp16 + + +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/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3-psychiatrist-v1.3B-fp16-GGUF/resolve/main/llama3-psychiatrist-v1.3B-fp16.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/llama3-psychiatrist-v1.3B-fp16.IQ3_M.gguf b/llama3-psychiatrist-v1.3B-fp16.IQ3_M.gguf new file mode 100644 index 0000000..63139bb --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf1a6b18fe7eb54ef46351c382540bb261f3ef6c4248031abc41dfd0d4ffdd0c +size 3784823168 diff --git a/llama3-psychiatrist-v1.3B-fp16.IQ3_S.gguf b/llama3-psychiatrist-v1.3B-fp16.IQ3_S.gguf new file mode 100644 index 0000000..cad160c --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e93eb826bcfdd5e0c5fde9e330c15b231b8878cff5b4af6c9afde9221c4ab11 +size 3682324864 diff --git a/llama3-psychiatrist-v1.3B-fp16.IQ3_XS.gguf b/llama3-psychiatrist-v1.3B-fp16.IQ3_XS.gguf new file mode 100644 index 0000000..d9dbbd5 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3949b18d49fd6e747d1dad41846ba0505a54858c6da44f8aba2fbe52857afe1a +size 3518747008 diff --git a/llama3-psychiatrist-v1.3B-fp16.IQ4_XS.gguf b/llama3-psychiatrist-v1.3B-fp16.IQ4_XS.gguf new file mode 100644 index 0000000..c4fdbca --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce8e40ad2429186e4bbfd182afc0d1762d280fcd492c3ca0d5fc546ffd69fa0 +size 4484362624 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q2_K.gguf b/llama3-psychiatrist-v1.3B-fp16.Q2_K.gguf new file mode 100644 index 0000000..c5b54c9 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5d6a85745e42bcbb9438689ca6d2a9056e3b26a9623f1cdbdef4473988105e +size 3179131264 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q3_K_L.gguf b/llama3-psychiatrist-v1.3B-fp16.Q3_K_L.gguf new file mode 100644 index 0000000..1ffc7ef --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7054d306500acf1edfa49b252e7ee5db4ad0c04cd45a70946c8f6d7a70e641e3 +size 4321956224 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q3_K_M.gguf b/llama3-psychiatrist-v1.3B-fp16.Q3_K_M.gguf new file mode 100644 index 0000000..579fc58 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62cc7961d0df9392f00491a28a1632b151cd43d8009cb6282913cf80b5fab157 +size 4018917760 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q3_K_S.gguf b/llama3-psychiatrist-v1.3B-fp16.Q3_K_S.gguf new file mode 100644 index 0000000..78ac042 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4b84b562b9ebbace9f3b4373cf1f1817d4d6dddf48b2be266a3d49d1e82d2b +size 3664499072 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q4_K_M.gguf b/llama3-psychiatrist-v1.3B-fp16.Q4_K_M.gguf new file mode 100644 index 0000000..11d7c67 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c414bddbb2c7aa777a4c935de209aa50fe5411a2aa2cbc128071181599ba7d92 +size 4920734080 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q4_K_S.gguf b/llama3-psychiatrist-v1.3B-fp16.Q4_K_S.gguf new file mode 100644 index 0000000..a3da7ab --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfff6703f79e514c814dfd138ad17f557e72e530b52f9e1039b0ced61d271034 +size 4692668800 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q5_K_M.gguf b/llama3-psychiatrist-v1.3B-fp16.Q5_K_M.gguf new file mode 100644 index 0000000..24e326d --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918ed3d198a3d3b166f085cf00e666a33b5f4211d6d71eeac1ee98d9ce3df755 +size 5732987264 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q5_K_S.gguf b/llama3-psychiatrist-v1.3B-fp16.Q5_K_S.gguf new file mode 100644 index 0000000..bcb12a5 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170d6f8edb3c2f5131c4f2d66c4990949ac4b43c4a20839276e116bbc81f7f3a +size 5599293824 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q6_K.gguf b/llama3-psychiatrist-v1.3B-fp16.Q6_K.gguf new file mode 100644 index 0000000..c5c208e --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d883640d75ba3ee1b939e29b53d52e27f3edd3e4e559c4270909458b60c0c433 +size 6596006272 diff --git a/llama3-psychiatrist-v1.3B-fp16.Q8_0.gguf b/llama3-psychiatrist-v1.3B-fp16.Q8_0.gguf new file mode 100644 index 0000000..bb82313 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8257b3cdb7e5666bba1a18d12a6b6e6b1883efdac4a4355fed50adfe9774dcf +size 8540770688 diff --git a/llama3-psychiatrist-v1.3B-fp16.f16.gguf b/llama3-psychiatrist-v1.3B-fp16.f16.gguf new file mode 100644 index 0000000..52a7386 --- /dev/null +++ b/llama3-psychiatrist-v1.3B-fp16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f99366c7380735c8a9a030db1612ad4824c49e135fdbaba65d461b401b3b6776 +size 16068891008