commit b84fe6bc6a69f760626840449b43eec59025ac83 Author: ModelHub XC Date: Wed Sep 16 10:26:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-7b-Alpaca-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c84d595 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-7b-Alpaca.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-7b-Alpaca.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-7b-Alpaca.IQ3_M.gguf b/Llama-7b-Alpaca.IQ3_M.gguf new file mode 100644 index 0000000..37b68a0 --- /dev/null +++ b/Llama-7b-Alpaca.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e40cf02fce49bd1a94b70470283ed1b2c51c798f36f092bd43ed7bd9360ecb +size 3114865760 diff --git a/Llama-7b-Alpaca.IQ3_S.gguf b/Llama-7b-Alpaca.IQ3_S.gguf new file mode 100644 index 0000000..323806d --- /dev/null +++ b/Llama-7b-Alpaca.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ada30ca07be1b792c289d4b2b3d67c504b47b00d78e3a095591003fa8288d78 +size 2948306016 diff --git a/Llama-7b-Alpaca.IQ3_XS.gguf b/Llama-7b-Alpaca.IQ3_XS.gguf new file mode 100644 index 0000000..024ed61 --- /dev/null +++ b/Llama-7b-Alpaca.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86c951c4f276510de47d5ffdc252bb514434abc71b6e4a72ce488ff3bdaa808 +size 2796524640 diff --git a/Llama-7b-Alpaca.IQ4_XS.gguf b/Llama-7b-Alpaca.IQ4_XS.gguf new file mode 100644 index 0000000..5815ca5 --- /dev/null +++ b/Llama-7b-Alpaca.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd090753a51f112f03e43821e74d90279060bffedf61abc981b4ac6bcb1cbc65 +size 3647517792 diff --git a/Llama-7b-Alpaca.Q2_K.gguf b/Llama-7b-Alpaca.Q2_K.gguf new file mode 100644 index 0000000..b950a43 --- /dev/null +++ b/Llama-7b-Alpaca.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c696bdea4f6277642679b6a60339fee26aab9621583f8ea870f3bcc3045adfc +size 2532865120 diff --git a/Llama-7b-Alpaca.Q3_K_L.gguf b/Llama-7b-Alpaca.Q3_K_L.gguf new file mode 100644 index 0000000..fa83b73 --- /dev/null +++ b/Llama-7b-Alpaca.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ef700c1843d87c9c88f52a0f19bb20e206d14e8eb8939a9aa29d6d886e6713 +size 3597112416 diff --git a/Llama-7b-Alpaca.Q3_K_M.gguf b/Llama-7b-Alpaca.Q3_K_M.gguf new file mode 100644 index 0000000..ff3d0ce --- /dev/null +++ b/Llama-7b-Alpaca.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c16b980a9673aa8d6133c69bdb386ff4c69b87d857bf7eec42aa86d0f15d607c +size 3298006112 diff --git a/Llama-7b-Alpaca.Q3_K_S.gguf b/Llama-7b-Alpaca.Q3_K_S.gguf new file mode 100644 index 0000000..14c22d3 --- /dev/null +++ b/Llama-7b-Alpaca.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da166fe4bdcb5ed905be9707be4b24a1ee110a0b3e83cef6f1fd1982913f952e +size 2948306016 diff --git a/Llama-7b-Alpaca.Q4_K_M.gguf b/Llama-7b-Alpaca.Q4_K_M.gguf new file mode 100644 index 0000000..de65e79 --- /dev/null +++ b/Llama-7b-Alpaca.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613a5a9388de3fb98cfe84f19d191839f400a3368573d64ab946d3fa679a6c26 +size 4081005664 diff --git a/Llama-7b-Alpaca.Q4_K_S.gguf b/Llama-7b-Alpaca.Q4_K_S.gguf new file mode 100644 index 0000000..ca8e265 --- /dev/null +++ b/Llama-7b-Alpaca.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70655a95a56232cfe0175903e82bfc0cfa91e848d9313ae32d09652cdf179488 +size 3856741472 diff --git a/Llama-7b-Alpaca.Q5_K_M.gguf b/Llama-7b-Alpaca.Q5_K_M.gguf new file mode 100644 index 0000000..181cafd --- /dev/null +++ b/Llama-7b-Alpaca.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1cccdea9848a06547b96a8fc8905ae6023d3069016c0e0fa168683310d62d4 +size 4783158368 diff --git a/Llama-7b-Alpaca.Q5_K_S.gguf b/Llama-7b-Alpaca.Q5_K_S.gguf new file mode 100644 index 0000000..f524ab5 --- /dev/null +++ b/Llama-7b-Alpaca.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54bf892610025e5132433a533cfcd03a42c56265290866df11cab98086d6c51c +size 4651693152 diff --git a/Llama-7b-Alpaca.Q6_K.gguf b/Llama-7b-Alpaca.Q6_K.gguf new file mode 100644 index 0000000..8240769 --- /dev/null +++ b/Llama-7b-Alpaca.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7194b7ec934c33823654872da9b019c8756e38f8c44c8a522960890ad3c727fc +size 5529195616 diff --git a/Llama-7b-Alpaca.Q8_0.gguf b/Llama-7b-Alpaca.Q8_0.gguf new file mode 100644 index 0000000..2559a09 --- /dev/null +++ b/Llama-7b-Alpaca.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed0d51d7f1333c75a9121db468e2457b8257a3be90fdc106b3668f2b675d87d6 +size 7161091168 diff --git a/Llama-7b-Alpaca.f16.gguf b/Llama-7b-Alpaca.f16.gguf new file mode 100644 index 0000000..0993372 --- /dev/null +++ b/Llama-7b-Alpaca.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb5cf65917e4eb497fd3eeaa31ba34dd4e43b85c4616a860d4120253fd256229 +size 13478106208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dbcda49 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: MarcelPower/Llama-7b-Alpaca +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/MarcelPower/Llama-7b-Alpaca + + +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-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-7b-Alpaca-GGUF/resolve/main/Llama-7b-Alpaca.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. + +