commit 4dc3924e3d05dd520941e8e917d360c6fe33b454 Author: ModelHub XC Date: Tue Jun 23 11:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..485be28 --- /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 +Llama3.1-Instruct-SEP-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-Instruct-SEP-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-Instruct-SEP-Chat.IQ4_XS.gguf b/Llama3.1-Instruct-SEP-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..2a24ce9 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69fcec21bfc3552afbac9b0306e84abc8f066bbf6d5cf30f260bdd660822600a +size 4484368576 diff --git a/Llama3.1-Instruct-SEP-Chat.Q2_K.gguf b/Llama3.1-Instruct-SEP-Chat.Q2_K.gguf new file mode 100644 index 0000000..5d53d11 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2cd96df70b0e1208e6143f33a6019660420e58d7c7e56d1d9325f5e77e33f53 +size 3179137216 diff --git a/Llama3.1-Instruct-SEP-Chat.Q3_K_L.gguf b/Llama3.1-Instruct-SEP-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..8029db1 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8fe3a102224dcc938e739c643ea533b51c42dff112c6cc463f9493924376fa +size 4321962176 diff --git a/Llama3.1-Instruct-SEP-Chat.Q3_K_M.gguf b/Llama3.1-Instruct-SEP-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..2790022 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63c13671343614ba732a600983d7b25ff52f67e3ea2185e1ae38517b59d3984 +size 4018923712 diff --git a/Llama3.1-Instruct-SEP-Chat.Q3_K_S.gguf b/Llama3.1-Instruct-SEP-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..0025cb4 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de32b1e5ff4eeb0cbcddf8bda0f7186cb0f63d693045c7d9ba168a21c568d0fc +size 3664505024 diff --git a/Llama3.1-Instruct-SEP-Chat.Q4_K_M.gguf b/Llama3.1-Instruct-SEP-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..1cd57be --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b15910935b4faa482241f3dcb2c2a2c78b21f1fd6738f3625361c8c614ad73 +size 4920740032 diff --git a/Llama3.1-Instruct-SEP-Chat.Q4_K_S.gguf b/Llama3.1-Instruct-SEP-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..f0b0182 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76088dba2eba3017fa75bbc7663d5210fc365907d1a9ea332d3b657190985e0b +size 4692674752 diff --git a/Llama3.1-Instruct-SEP-Chat.Q5_K_M.gguf b/Llama3.1-Instruct-SEP-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..ebbc536 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:801b4bce519cfa43705c7ca214821280bfa3f442d60365c7f63ab0c6a8e17e46 +size 5732993216 diff --git a/Llama3.1-Instruct-SEP-Chat.Q5_K_S.gguf b/Llama3.1-Instruct-SEP-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..1c7a4ec --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdbe6c97d1426bf048451e6bb66abcdd13a48bcfd465ea9c25f862939a5b5332 +size 5599299776 diff --git a/Llama3.1-Instruct-SEP-Chat.Q6_K.gguf b/Llama3.1-Instruct-SEP-Chat.Q6_K.gguf new file mode 100644 index 0000000..6892cd7 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbc884de3c6094e7307328c161ae75d2808ba64faec27979d1869f3c8492f4b7 +size 6596012224 diff --git a/Llama3.1-Instruct-SEP-Chat.Q8_0.gguf b/Llama3.1-Instruct-SEP-Chat.Q8_0.gguf new file mode 100644 index 0000000..a2117a1 --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261d6907c36d7b3bebf0ab17963eb5cebf40f7338051a4206cee75905118a004 +size 8540776640 diff --git a/Llama3.1-Instruct-SEP-Chat.f16.gguf b/Llama3.1-Instruct-SEP-Chat.f16.gguf new file mode 100644 index 0000000..557bb4f --- /dev/null +++ b/Llama3.1-Instruct-SEP-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efc6d7cf2038aba1e8ea0c98507e9f00e2f8ab041a90039ae1b67ae8c302044 +size 16068896960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b709a7e --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: ruggsea/Llama3.1-Instruct-SEP-Chat +datasets: +- ruggsea/stanford-encyclopedia-of-philosophy_chat_multi_turn +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- philosophy +- art +--- +## About + + + + + + +static quants of https://huggingface.co/ruggsea/Llama3.1-Instruct-SEP-Chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-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/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-Instruct-SEP-Chat-GGUF/resolve/main/Llama3.1-Instruct-SEP-Chat.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. + +