commit 879fa2b759563cdf0db076187d9c36a8d752fe89 Author: ModelHub XC Date: Mon Sep 14 15:05:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b933d88 --- /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-3.1-8B-Instruct-travelplanner-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-Instruct-travelplanner-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.IQ4_XS.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..120a143 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce5e65dab27ada189e7f86acd555c82299f8a639e313bebda8c06c3fe78e4ff +size 4484363936 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q2_K.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q2_K.gguf new file mode 100644 index 0000000..b4d01a1 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b568ffd250cd49663e559bc62ec45c3e5ba078bc581169639f9eb8a3739eb360 +size 3179132576 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_L.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..fdeed5f --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c7e6dc649ec0e08cf2a5d5c14c05e3a4028fd800a2d8ed28e5532f8fa16860b +size 4321957536 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_M.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..f85eec0 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229a8395ae097e22beb1e07cb1fe6e7dfaacb90c13cff911084b44c446334040 +size 4018919072 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_S.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..7bd4f8c --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c21fde753f47f24da528dec4043f8fb7e04f207b7e562a64375a8dd6aadb162 +size 3664500384 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_M.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..3a742c6 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37597d5218f9fd4db517a6c834159479a00cf6037efc14dc828d2b0b9debf107 +size 4920735392 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_S.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..5517e0b --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:159036e155698a9234ee8e65f48c0e84b91d0f8994521efdfdeb5ac7997959f7 +size 4692670112 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_M.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..f6700fa --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e978da2ddfe9744f71c64912c57bb0b2a40890a7fff16b665094b725356859 +size 5732988576 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_S.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..dec1624 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38c7613344a0a6f17408b5e8feb2c6fb680baa73e7ae856c0a22f6c3ae1954d +size 5599295136 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q6_K.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q6_K.gguf new file mode 100644 index 0000000..56b718b --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9aeea308b1e1916b6af5fa44c38c90934f78735ba7a3d0729fc45735013cde3 +size 6596007584 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.Q8_0.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q8_0.gguf new file mode 100644 index 0000000..3f66fcd --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:609783bd67d86a7c55dd4bc688cff109934673e02aa6fa308a03568c129b9c67 +size 8540772000 diff --git a/Llama-3.1-8B-Instruct-travelplanner-SFT.f16.gguf b/Llama-3.1-8B-Instruct-travelplanner-SFT.f16.gguf new file mode 100644 index 0000000..cbde4b7 --- /dev/null +++ b/Llama-3.1-8B-Instruct-travelplanner-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ff64e08e84891549f39b1dc17c590bac61166cd77d9690ac13e4fca1acc7e7 +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d86f70d --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: hsaest/Llama-3.1-8B-Instruct-travelplanner-SFT +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/hsaest/Llama-3.1-8B-Instruct-travelplanner-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-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/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-Instruct-travelplanner-SFT-GGUF/resolve/main/Llama-3.1-8B-Instruct-travelplanner-SFT.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. + +