commit 6bc714815d17e91bf3fa6bc3961ded1b86c93779 Author: ModelHub XC Date: Wed Sep 30 22:48:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-psych-finetuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f582758 --- /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 +Llama-2-7b-psych-finetuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-psych-finetuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-psych-finetuned.IQ4_XS.gguf b/Llama-2-7b-psych-finetuned.IQ4_XS.gguf new file mode 100644 index 0000000..fed4211 --- /dev/null +++ b/Llama-2-7b-psych-finetuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6eddbf5f31cb69a42ecc5037ee7613b53f3919e236c7e8bb486e590873caf0f +size 3647517184 diff --git a/Llama-2-7b-psych-finetuned.Q2_K.gguf b/Llama-2-7b-psych-finetuned.Q2_K.gguf new file mode 100644 index 0000000..f13163b --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295ea2a95f3141f91c2e8cf662f9e97f0acd1ec6423df521e4ddc202ea323cb3 +size 2532864512 diff --git a/Llama-2-7b-psych-finetuned.Q3_K_L.gguf b/Llama-2-7b-psych-finetuned.Q3_K_L.gguf new file mode 100644 index 0000000..7299ff9 --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45a3d494285dc2df93020947bdb653e2478bf41860914866218ab9e319547fe +size 3597111808 diff --git a/Llama-2-7b-psych-finetuned.Q3_K_M.gguf b/Llama-2-7b-psych-finetuned.Q3_K_M.gguf new file mode 100644 index 0000000..b1eea45 --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55068d6ba1ed3826e095a01fe54fb2b655459fcb8c512e95464b48dad2db153f +size 3298005504 diff --git a/Llama-2-7b-psych-finetuned.Q3_K_S.gguf b/Llama-2-7b-psych-finetuned.Q3_K_S.gguf new file mode 100644 index 0000000..5ef2683 --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67a2d55f244f3fe161f35eaf3bb104b28189f79353443ef9ff1320b8a7557b0 +size 2948305408 diff --git a/Llama-2-7b-psych-finetuned.Q4_K_M.gguf b/Llama-2-7b-psych-finetuned.Q4_K_M.gguf new file mode 100644 index 0000000..d9ff6cc --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7caa041666e8ca10e5d71148d82a013c5524e5b58bd0627598a48238d0c856cb +size 4081005056 diff --git a/Llama-2-7b-psych-finetuned.Q4_K_S.gguf b/Llama-2-7b-psych-finetuned.Q4_K_S.gguf new file mode 100644 index 0000000..3179aea --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2774417e5abcff8ad732ba53b5a7730a1b012fbc63b345f1102c35efcc0edd +size 3856740864 diff --git a/Llama-2-7b-psych-finetuned.Q5_K_M.gguf b/Llama-2-7b-psych-finetuned.Q5_K_M.gguf new file mode 100644 index 0000000..3541e0a --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a203846bad6b53e5bb25713db4c4d53e25326b980bc6ee28b5a8b64c1f48b0ba +size 4783157760 diff --git a/Llama-2-7b-psych-finetuned.Q5_K_S.gguf b/Llama-2-7b-psych-finetuned.Q5_K_S.gguf new file mode 100644 index 0000000..215176b --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fa5417d167fc046b2add619b6d72f32659bd045faf45698df4ffaf8de9a4544 +size 4651692544 diff --git a/Llama-2-7b-psych-finetuned.Q6_K.gguf b/Llama-2-7b-psych-finetuned.Q6_K.gguf new file mode 100644 index 0000000..74813dc --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e484d569f29cedaec45fc15753d0a1d0cd25bc60d619148de6ac0cca630e5a58 +size 5529195008 diff --git a/Llama-2-7b-psych-finetuned.Q8_0.gguf b/Llama-2-7b-psych-finetuned.Q8_0.gguf new file mode 100644 index 0000000..9ada2ae --- /dev/null +++ b/Llama-2-7b-psych-finetuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1228d90e13239ceaf6cee2d4d581b164b8d49658acb324d08f0ffacbde9169 +size 7161090560 diff --git a/Llama-2-7b-psych-finetuned.f16.gguf b/Llama-2-7b-psych-finetuned.f16.gguf new file mode 100644 index 0000000..0494779 --- /dev/null +++ b/Llama-2-7b-psych-finetuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070a65f2d1ef8e46058b6e3449681a088695f08fcc7e97ff560a0b39a2425913 +size 13478105600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aefd60a --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: raflibagas/Llama-2-7b-psych-finetuned +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/raflibagas/Llama-2-7b-psych-finetuned + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-psych-finetuned-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-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-psych-finetuned-GGUF/resolve/main/Llama-2-7b-psych-finetuned.f16.gguf) | f16 | 13.6 | 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. + +