commit f951fb0fb4cedb478c9c16c07efda57336d93a84 Author: ModelHub XC Date: Thu Jun 25 16:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2882e4e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-3.1-8B-instruct-psycology-8k_data-w.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.IQ4_XS.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.IQ4_XS.gguf new file mode 100644 index 0000000..ec51c8a --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:288446f918e40e6c5e3165ec9bc930720101ac7181cae145047ad498599fccc3 +size 4484368352 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q2_K.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q2_K.gguf new file mode 100644 index 0000000..b76e3c3 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d738986bc04b85a9a1483e2f3226f9d5f83984293a7af47ca0ccf16f0712790a +size 3179136992 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_L.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_L.gguf new file mode 100644 index 0000000..b5df1bf --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5254abc2766c68332db719454ff184295fac2de6d53953c83c7c27293a1ecda +size 4321961952 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_M.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_M.gguf new file mode 100644 index 0000000..7e3f62e --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ece3b7f0884f57c7579f1c0321393608735efb13319f9324f411f28bb5662c5 +size 4018923488 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_S.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_S.gguf new file mode 100644 index 0000000..e557735 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0030d7347e4be122718ae47f96655d3adbf1e26b6fd95c76c10ef49de132fb6f +size 3664504800 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_0_4_4.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_0_4_4.gguf new file mode 100644 index 0000000..183b303 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40f2b8fb3802c0bc3ab0fcbf32eebaf887cc3822fedb620c8b30003142a8f215 +size 4661217248 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_M.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_M.gguf new file mode 100644 index 0000000..adfaab1 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6434ebad67606d4678800c722264e4a2a5598e87801e4e056ec415d5f05fce58 +size 4920739808 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_S.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_S.gguf new file mode 100644 index 0000000..d9793b1 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e24af48d50d01a5fd107e0616ed3ea8ac620cbc0c33ff975627edf658be040c +size 4692674528 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_M.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_M.gguf new file mode 100644 index 0000000..7a9b8f9 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b5a11b35bf720bd80b0eb1597cd3220b7ac64d978745dc3fdf3286eb2e0118 +size 5732992992 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_S.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_S.gguf new file mode 100644 index 0000000..5c01830 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d2924516c49344da056325847a162cbd954cf2802fb4d1ebe02e0497692b04 +size 5599299552 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q6_K.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q6_K.gguf new file mode 100644 index 0000000..bd202ad --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84db2ec52a1b37e6653ad856f1019790e739ddcf752c2a46beb6a0d3bf27ddfd +size 6596012000 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.Q8_0.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q8_0.gguf new file mode 100644 index 0000000..66bbb29 --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7ef0ab13a2a615ced287db7a5ca782a2c4ba4044251e02f79be7997e69de6b +size 8540776416 diff --git a/Llama-3.1-8B-instruct-psycology-8k_data-w.f16.gguf b/Llama-3.1-8B-instruct-psycology-8k_data-w.f16.gguf new file mode 100644 index 0000000..99ed95f --- /dev/null +++ b/Llama-3.1-8B-instruct-psycology-8k_data-w.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85bed0032fa03a22dfbefe00cbbf2accd8cb22badf0f970f35495127fffc4165 +size 16068896736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..41d2849 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: wassimm/Llama-3.1-8B-instruct-psycology-8k_data-w +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/wassimm/Llama-3.1-8B-instruct-psycology-8k_data-w + + +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-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-instruct-psycology-8k_data-w-GGUF/resolve/main/Llama-3.1-8B-instruct-psycology-8k_data-w.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +