commit 7f3f2b74ba05ec36689a30f3e9f3bb0e3b05e03c Author: ModelHub XC Date: Wed Jun 24 11:21:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TherapyZ-Llama-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d0ebf80 --- /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 +TherapyZ-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyZ-Llama-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..142f401 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: ozertuu/TherapyZ-Llama-3-8B +datasets: +- ozertuu/therapy-conversations-combined-translated-tr +language: +- tr +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/ozertuu/TherapyZ-Llama-3-8B + + +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/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyZ-Llama-3-8B-GGUF/resolve/main/TherapyZ-Llama-3-8B.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/TherapyZ-Llama-3-8B.IQ4_XS.gguf b/TherapyZ-Llama-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..62f4546 --- /dev/null +++ b/TherapyZ-Llama-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccf36c2db7f49c4210469b0f5b26c666f39601860932144d0351865985e63bf +size 4484364256 diff --git a/TherapyZ-Llama-3-8B.Q2_K.gguf b/TherapyZ-Llama-3-8B.Q2_K.gguf new file mode 100644 index 0000000..714f45a --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c6cefe83d36d081f8f3f91fc71231dcb956f65b3fe40fa09031c692652b748 +size 3179132896 diff --git a/TherapyZ-Llama-3-8B.Q3_K_L.gguf b/TherapyZ-Llama-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..e5bee19 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b845f53bcbae556fd7259667eb2f9b2939869a365ac8a88e67d0a03699ce0285 +size 4321957856 diff --git a/TherapyZ-Llama-3-8B.Q3_K_M.gguf b/TherapyZ-Llama-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..e1ea41e --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b95cbe96127d5ebe4dccaeac21fddbc44fa491e7d864c5158a5a0dd7aebfa6 +size 4018919392 diff --git a/TherapyZ-Llama-3-8B.Q3_K_S.gguf b/TherapyZ-Llama-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..96f4038 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d710e21e25d11a328e30870baeff624e8e8d7403a4f3fb56b832d7ca1f91409 +size 3664500704 diff --git a/TherapyZ-Llama-3-8B.Q4_K_M.gguf b/TherapyZ-Llama-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..f3fccc0 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a9812f847a8fa5c276bcffdfcd0cef3a514bfc4f315e8df1b9326684a78de0 +size 4920735712 diff --git a/TherapyZ-Llama-3-8B.Q4_K_S.gguf b/TherapyZ-Llama-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..6c6ed99 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd2c5e1a373d4a4f78704a9ad2b8ae6c71de2a566b680fe41e360bd92ed8e9b9 +size 4692670432 diff --git a/TherapyZ-Llama-3-8B.Q5_K_M.gguf b/TherapyZ-Llama-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..f0f7ae5 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f506387f755e45c3926ad1f8da1340fdb8b5905b49e685636f923220e56eacef +size 5732988896 diff --git a/TherapyZ-Llama-3-8B.Q5_K_S.gguf b/TherapyZ-Llama-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..78c8a37 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1bd6b311b8a8ff398c4cf9788af0e86d78f728607ac93b874948a623df3f4da +size 5599295456 diff --git a/TherapyZ-Llama-3-8B.Q6_K.gguf b/TherapyZ-Llama-3-8B.Q6_K.gguf new file mode 100644 index 0000000..7700fdd --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750e2565c5dcb8261b8c8f6f7410a7911ce9a2547b3d8bb9092afca0ad48423b +size 6596007904 diff --git a/TherapyZ-Llama-3-8B.Q8_0.gguf b/TherapyZ-Llama-3-8B.Q8_0.gguf new file mode 100644 index 0000000..f4ab7f8 --- /dev/null +++ b/TherapyZ-Llama-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51e8853b989f3e037755da04a648d8ca10ca453f10c5213ad6d2ced50f7cfa3e +size 8540772320 diff --git a/TherapyZ-Llama-3-8B.f16.gguf b/TherapyZ-Llama-3-8B.f16.gguf new file mode 100644 index 0000000..ba7fe2e --- /dev/null +++ b/TherapyZ-Llama-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4bcbf21f2eeaff3238341cb6da08a10459ffa8a6b8655938b4fe90c5ba0cc43 +size 16068892640