commit 8938786d7924e2cc6cfa7623f34e77a79249c271 Author: ModelHub XC Date: Thu Jul 30 09:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TherapyLlama-8B-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c4fa299 --- /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 +TherapyLlama-8B-v1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TherapyLlama-8B-v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd64009 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: victunes/TherapyLlama-8B-v1 +datasets: +- victunes/nart-100k-synthetic-buddy-mixed-names +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/victunes/TherapyLlama-8B-v1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/TherapyLlama-8B-v1-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/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TherapyLlama-8B-v1-GGUF/resolve/main/TherapyLlama-8B-v1.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/TherapyLlama-8B-v1.IQ3_M.gguf b/TherapyLlama-8B-v1.IQ3_M.gguf new file mode 100644 index 0000000..a9ac521 --- /dev/null +++ b/TherapyLlama-8B-v1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d746fe2a30b4f15623b05f015bf3085d70b0f34b0922efdd57427ddb39987f +size 3784824096 diff --git a/TherapyLlama-8B-v1.IQ3_S.gguf b/TherapyLlama-8B-v1.IQ3_S.gguf new file mode 100644 index 0000000..11f9780 --- /dev/null +++ b/TherapyLlama-8B-v1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad806eba9b1591c6bfc12047bb0ec185e3d51643f95fb544dec289c85c2e887 +size 3682325792 diff --git a/TherapyLlama-8B-v1.IQ3_XS.gguf b/TherapyLlama-8B-v1.IQ3_XS.gguf new file mode 100644 index 0000000..a529555 --- /dev/null +++ b/TherapyLlama-8B-v1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:493636228a839c74b47f897f33c5cbba0826196749c11ac73e93521233571b62 +size 3518747936 diff --git a/TherapyLlama-8B-v1.IQ4_XS.gguf b/TherapyLlama-8B-v1.IQ4_XS.gguf new file mode 100644 index 0000000..23ceb7f --- /dev/null +++ b/TherapyLlama-8B-v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44ba8dc1b27fc5182e4103b527154d318694d31b15bd5ee93f89a5bc6df370b +size 4484363552 diff --git a/TherapyLlama-8B-v1.Q2_K.gguf b/TherapyLlama-8B-v1.Q2_K.gguf new file mode 100644 index 0000000..15a3941 --- /dev/null +++ b/TherapyLlama-8B-v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf35f7284d027593d84df620ac82f6f7b63c45514d6349dd1fd420315983ccd6 +size 3179132192 diff --git a/TherapyLlama-8B-v1.Q3_K_L.gguf b/TherapyLlama-8B-v1.Q3_K_L.gguf new file mode 100644 index 0000000..4be71d8 --- /dev/null +++ b/TherapyLlama-8B-v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f73d482e308f5d9dfd3747f6f68dbefc185f841c525e11e0b9927d649df86e19 +size 4321957152 diff --git a/TherapyLlama-8B-v1.Q3_K_M.gguf b/TherapyLlama-8B-v1.Q3_K_M.gguf new file mode 100644 index 0000000..521f703 --- /dev/null +++ b/TherapyLlama-8B-v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dcfddc821e32daf4e6d4a0b14a50bcda634f7b1c2aec0bdbc9c59ffbf646be5 +size 4018918688 diff --git a/TherapyLlama-8B-v1.Q3_K_S.gguf b/TherapyLlama-8B-v1.Q3_K_S.gguf new file mode 100644 index 0000000..1588308 --- /dev/null +++ b/TherapyLlama-8B-v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2563acccf256ab2fea0c0a0083baaebb1af4d34060eb5eeac3c576f47361b531 +size 3664500000 diff --git a/TherapyLlama-8B-v1.Q4_K_M.gguf b/TherapyLlama-8B-v1.Q4_K_M.gguf new file mode 100644 index 0000000..350c3e9 --- /dev/null +++ b/TherapyLlama-8B-v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1b01b7bf4b7c55c754bb06e1f82236b04cfbe3012411c1104e9b6b4551cfa0 +size 4920735008 diff --git a/TherapyLlama-8B-v1.Q4_K_S.gguf b/TherapyLlama-8B-v1.Q4_K_S.gguf new file mode 100644 index 0000000..561b359 --- /dev/null +++ b/TherapyLlama-8B-v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca597a5af06cb69fbe060c0b6363d9db97a65a2e28af15243a16735ca39f16c1 +size 4692669728 diff --git a/TherapyLlama-8B-v1.Q5_K_M.gguf b/TherapyLlama-8B-v1.Q5_K_M.gguf new file mode 100644 index 0000000..d403df2 --- /dev/null +++ b/TherapyLlama-8B-v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2a292eea6fb52308700b04f3de8173477e277c231d581fe13957f9cff3f028d +size 5732988192 diff --git a/TherapyLlama-8B-v1.Q5_K_S.gguf b/TherapyLlama-8B-v1.Q5_K_S.gguf new file mode 100644 index 0000000..57890de --- /dev/null +++ b/TherapyLlama-8B-v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9497e38bdcd259abfa681ba5fa803ab703589199e65525423629a464e4f4c424 +size 5599294752 diff --git a/TherapyLlama-8B-v1.Q6_K.gguf b/TherapyLlama-8B-v1.Q6_K.gguf new file mode 100644 index 0000000..5c84e52 --- /dev/null +++ b/TherapyLlama-8B-v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e65ab60bfc57c46098ec14ad9ae79001cc013e2b9e5a2270657837e78e9cad +size 6596007200 diff --git a/TherapyLlama-8B-v1.Q8_0.gguf b/TherapyLlama-8B-v1.Q8_0.gguf new file mode 100644 index 0000000..033fa5b --- /dev/null +++ b/TherapyLlama-8B-v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce23c62442e442b626f3dcbe055d50b0a9cfd51260e69c9e0a6f662fd9decf8b +size 8540771616 diff --git a/TherapyLlama-8B-v1.f16.gguf b/TherapyLlama-8B-v1.f16.gguf new file mode 100644 index 0000000..614ebce --- /dev/null +++ b/TherapyLlama-8B-v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4deac95fc2e6e8f5709ca6e8dff8eb7061f837a45bdad07decb8e6ddfc248f76 +size 16068891936