commit 0b42914e083a6a2edf9295b94569ea43d536dcc0 Author: ModelHub XC Date: Wed Jul 8 20:20:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SFT-LLama-7b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..40bc44b --- /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-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SFT-LLama-7b-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..4f513f5 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Oums/SFT-LLama-7b-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-chat + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SFT-LLama-7b-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-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SFT-LLama-7b-chat-GGUF/resolve/main/SFT-LLama-7b-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-chat.IQ4_XS.gguf b/SFT-LLama-7b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..08d57b1 --- /dev/null +++ b/SFT-LLama-7b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d394792ae4d3b4c3258ae0f461fbd39c1fbffb796873f55d30747907523faf +size 3647523808 diff --git a/SFT-LLama-7b-chat.Q2_K.gguf b/SFT-LLama-7b-chat.Q2_K.gguf new file mode 100644 index 0000000..8a3305e --- /dev/null +++ b/SFT-LLama-7b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6018af5466925a795cf8391a684b3add88a7763ae048876a179865cc8f17f6c +size 2532870304 diff --git a/SFT-LLama-7b-chat.Q3_K_L.gguf b/SFT-LLama-7b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..87781be --- /dev/null +++ b/SFT-LLama-7b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5d5408db369c94afdc7f12fd66b7c3d25de9f82e790510aa82a18710b57e744 +size 3597118016 diff --git a/SFT-LLama-7b-chat.Q3_K_M.gguf b/SFT-LLama-7b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..9a612e9 --- /dev/null +++ b/SFT-LLama-7b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c9f80e66b9646ff5cb49c13ef94d909fb3e8f723ef04a4871dfbbab452bdbd +size 3298011712 diff --git a/SFT-LLama-7b-chat.Q3_K_S.gguf b/SFT-LLama-7b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..5f4b0a5 --- /dev/null +++ b/SFT-LLama-7b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbbef46ceee605b72fd259b724d540a1cfa7f020a3a394c80da2edd8d6d2f8e +size 2948311616 diff --git a/SFT-LLama-7b-chat.Q4_K_M.gguf b/SFT-LLama-7b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..33c90f9 --- /dev/null +++ b/SFT-LLama-7b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1dafe69530b7b9b1e7d03175eb894e2013c51d6211eacf03608be399a7717ab +size 4081011808 diff --git a/SFT-LLama-7b-chat.Q4_K_S.gguf b/SFT-LLama-7b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..1a07b5e --- /dev/null +++ b/SFT-LLama-7b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e04104935832dde5440220d3d9f0e88666dd323b9f0dd9075b9d8fd7dbd1b9 +size 3856747616 diff --git a/SFT-LLama-7b-chat.Q5_K_M.gguf b/SFT-LLama-7b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..158b098 --- /dev/null +++ b/SFT-LLama-7b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9dd4a7600df39a912df5747f1ee9223fe66c8f993384f48041bd38ee46fcc17 +size 4783165024 diff --git a/SFT-LLama-7b-chat.Q5_K_S.gguf b/SFT-LLama-7b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..1f22faa --- /dev/null +++ b/SFT-LLama-7b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca09b92fd2763d6ba4b4c7a9c6f9343a8cc4596aae3954f36180fe3a6f83398 +size 4651699808 diff --git a/SFT-LLama-7b-chat.Q6_K.gguf b/SFT-LLama-7b-chat.Q6_K.gguf new file mode 100644 index 0000000..c85e545 --- /dev/null +++ b/SFT-LLama-7b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76150225c2be8369f44013c09b5d970414efa471324ba076395f1b50e182be4e +size 5529202816 diff --git a/SFT-LLama-7b-chat.Q8_0.gguf b/SFT-LLama-7b-chat.Q8_0.gguf new file mode 100644 index 0000000..38dd89d --- /dev/null +++ b/SFT-LLama-7b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e20b1bbce01d32efabc1ac6c534b4ebb3d312f30305548f8a799650b53a2174c +size 7161100352 diff --git a/SFT-LLama-7b-chat.f16.gguf b/SFT-LLama-7b-chat.f16.gguf new file mode 100644 index 0000000..209816b --- /dev/null +++ b/SFT-LLama-7b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2968c7636de7f855b1e00013675aa5bbf466505fdb9abd2d39ad1a027e98df +size 13478123072