commit e97d7d173b3a4797b2002f5730a13545b2c9fee6 Author: ModelHub XC Date: Sun Oct 11 19:23:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-2-7b-alpaca-gpt4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ca4731 --- /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-2-7b-alpaca-gpt4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-2-7b-alpaca-gpt4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6337248 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Seungyoun/llama-2-7b-alpaca-gpt4 +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- IFT +--- +## About + + + + + + +static quants of https://huggingface.co/Seungyoun/llama-2-7b-alpaca-gpt4 + + +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-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-2-7b-alpaca-gpt4-GGUF/resolve/main/llama-2-7b-alpaca-gpt4.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/llama-2-7b-alpaca-gpt4.IQ4_XS.gguf b/llama-2-7b-alpaca-gpt4.IQ4_XS.gguf new file mode 100644 index 0000000..9cbe190 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a6298498c04d672f321439e718441198dbc1cab28160a0e477ede7640478c7 +size 3647517408 diff --git a/llama-2-7b-alpaca-gpt4.Q2_K.gguf b/llama-2-7b-alpaca-gpt4.Q2_K.gguf new file mode 100644 index 0000000..118aa8e --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0f00b1d8d11185d431aac84198b82f0c29a93baab7c8275248b212ed6f86f5 +size 2532864736 diff --git a/llama-2-7b-alpaca-gpt4.Q3_K_L.gguf b/llama-2-7b-alpaca-gpt4.Q3_K_L.gguf new file mode 100644 index 0000000..cc7d342 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cf30c32508397695d75dc1292e01c4dde4cb3f717c4cd7e1517c9197f66c9c +size 3597112032 diff --git a/llama-2-7b-alpaca-gpt4.Q3_K_M.gguf b/llama-2-7b-alpaca-gpt4.Q3_K_M.gguf new file mode 100644 index 0000000..c396521 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f502f7362ae84ff320d7fa7f36f6b8489b03706cf4d9fa85392c37a2a6dad4 +size 3298005728 diff --git a/llama-2-7b-alpaca-gpt4.Q3_K_S.gguf b/llama-2-7b-alpaca-gpt4.Q3_K_S.gguf new file mode 100644 index 0000000..ec02737 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eefe1f2879c88c998597b6116ab08149aa61ebaddce5b7a14f4b34fedb4e6e9a +size 2948305632 diff --git a/llama-2-7b-alpaca-gpt4.Q4_K_M.gguf b/llama-2-7b-alpaca-gpt4.Q4_K_M.gguf new file mode 100644 index 0000000..3c8121a --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4135dc96c582cdba8c1af59eda6f7b6c364e4fde41cab04e5fce93b4ad8b2a40 +size 4081005280 diff --git a/llama-2-7b-alpaca-gpt4.Q4_K_S.gguf b/llama-2-7b-alpaca-gpt4.Q4_K_S.gguf new file mode 100644 index 0000000..fba9b37 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909ce6a3e7f6e4c938c5801cae46b488bdb37aa1108bc63f1b52ee9498794b0e +size 3856741088 diff --git a/llama-2-7b-alpaca-gpt4.Q5_K_M.gguf b/llama-2-7b-alpaca-gpt4.Q5_K_M.gguf new file mode 100644 index 0000000..76ab00e --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32aac4a7906344fdc1357d5f22fccdbb45a040557e8e54bea7cbafcb5fd9be9 +size 4783157984 diff --git a/llama-2-7b-alpaca-gpt4.Q5_K_S.gguf b/llama-2-7b-alpaca-gpt4.Q5_K_S.gguf new file mode 100644 index 0000000..fc8f3a1 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47273428b70635c1b88d77a759f08921268eaf0b5d947d382f37fdf5d80c469 +size 4651692768 diff --git a/llama-2-7b-alpaca-gpt4.Q6_K.gguf b/llama-2-7b-alpaca-gpt4.Q6_K.gguf new file mode 100644 index 0000000..d57ba16 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13f861ba0e2e07366dac3cf606ce41d086f2354f790f3711afe8a77745d6489 +size 5529195232 diff --git a/llama-2-7b-alpaca-gpt4.Q8_0.gguf b/llama-2-7b-alpaca-gpt4.Q8_0.gguf new file mode 100644 index 0000000..a91f2c0 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae497a5ff490393d62a377e9cb03f776b5650c9bd7e4e9213a3d3ccb491a506 +size 7161090784 diff --git a/llama-2-7b-alpaca-gpt4.f16.gguf b/llama-2-7b-alpaca-gpt4.f16.gguf new file mode 100644 index 0000000..a78a478 --- /dev/null +++ b/llama-2-7b-alpaca-gpt4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704a3f7dcf7f4980dafd4a7e583eca8cfe9d7c12268cf21db221cca4d3ce8264 +size 13478105824