commit 0fae59e38ebc4112a1e98b9ef4e3c063b424b275 Author: ModelHub XC Date: Mon Oct 5 19:57:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SFT-LLama-7b-Nachos-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f948405 --- /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 +SFT-LLama-7b-Nachos-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-Nachos-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9ad351 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Oums/SFT-LLama-7b-Nachos-chat +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Oums/SFT-LLama-7b-Nachos-chat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SFT-LLama-7b-Nachos-chat-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/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-Nachos-chat-GGUF/resolve/main/SFT-LLama-7b-Nachos-chat.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. + + diff --git a/SFT-LLama-7b-Nachos-chat.IQ4_XS.gguf b/SFT-LLama-7b-Nachos-chat.IQ4_XS.gguf new file mode 100644 index 0000000..47e987f --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eac15fea96629681b1ffef99ffa4b3d3fb6a8de8bee757d695ea5cf2bd8b703 +size 3647623104 diff --git a/SFT-LLama-7b-Nachos-chat.Q2_K.gguf b/SFT-LLama-7b-Nachos-chat.Q2_K.gguf new file mode 100644 index 0000000..3411cb2 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55683e932bb9471440118511462af9304d5d51fa2da001b23986aaf1021790e3 +size 2532954624 diff --git a/SFT-LLama-7b-Nachos-chat.Q3_K_L.gguf b/SFT-LLama-7b-Nachos-chat.Q3_K_L.gguf new file mode 100644 index 0000000..d00f714 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8222db6a3828092bd2cf3fb8309f640f13249ac53e161d9600d61c0178d6e269 +size 3597209824 diff --git a/SFT-LLama-7b-Nachos-chat.Q3_K_M.gguf b/SFT-LLama-7b-Nachos-chat.Q3_K_M.gguf new file mode 100644 index 0000000..b69aafb --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a59c71089016b4f2f96a3a17637086575aa18920154b111f3e4ad8d2d541be62 +size 3298103520 diff --git a/SFT-LLama-7b-Nachos-chat.Q3_K_S.gguf b/SFT-LLama-7b-Nachos-chat.Q3_K_S.gguf new file mode 100644 index 0000000..02359f5 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e1064dec7f750ccd341e2c55853abd91fade932f417e4f71f5e8f2c56f8ca9 +size 2948403424 diff --git a/SFT-LLama-7b-Nachos-chat.Q4_K_M.gguf b/SFT-LLama-7b-Nachos-chat.Q4_K_M.gguf new file mode 100644 index 0000000..fca4398 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc49e3be3a6d03fa9a096b66fde1ca9e1635c64d21482e32c99fc472453f895 +size 4081113408 diff --git a/SFT-LLama-7b-Nachos-chat.Q4_K_S.gguf b/SFT-LLama-7b-Nachos-chat.Q4_K_S.gguf new file mode 100644 index 0000000..fc1f60b --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a12cc453494c20c8c12c06b2d08f97decb0d0d6e25cd67b7e235baaaeccae2 +size 3856849216 diff --git a/SFT-LLama-7b-Nachos-chat.Q5_K_M.gguf b/SFT-LLama-7b-Nachos-chat.Q5_K_M.gguf new file mode 100644 index 0000000..5dcf765 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03507254c249974ca61cb9a7ae631c5a85a2f68b515e5d45a6d5d3dc1babdb52 +size 4783275840 diff --git a/SFT-LLama-7b-Nachos-chat.Q5_K_S.gguf b/SFT-LLama-7b-Nachos-chat.Q5_K_S.gguf new file mode 100644 index 0000000..ad04ca3 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a020c4dd16058c96ee6c0e745974b7c6e1bebbc152f79715969d4402ba104b +size 4651810624 diff --git a/SFT-LLama-7b-Nachos-chat.Q6_K.gguf b/SFT-LLama-7b-Nachos-chat.Q6_K.gguf new file mode 100644 index 0000000..84e54d0 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3275d2e08b24656736ff8beeac74f7c00cb17e4cfd65b9804f7b719f9572337 +size 5529323424 diff --git a/SFT-LLama-7b-Nachos-chat.Q8_0.gguf b/SFT-LLama-7b-Nachos-chat.Q8_0.gguf new file mode 100644 index 0000000..b667b26 --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d05fe6f7644b5822e01e312e42d5bea24df4bf153030f24f9168d8e2240dd61 +size 7161256672 diff --git a/SFT-LLama-7b-Nachos-chat.f16.gguf b/SFT-LLama-7b-Nachos-chat.f16.gguf new file mode 100644 index 0000000..2711bae --- /dev/null +++ b/SFT-LLama-7b-Nachos-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e53a5bf405cde6639ef7ddf67688b7f15af9212127725ce6682528dcbab5a7f +size 13478417632