commit 116dd0b8fa827b7a925cd1e6cf0f9d656441209b Author: ModelHub XC Date: Fri Oct 23 20:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7243343 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Open-Platypus-Llama-2-7b-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Open-Platypus-Llama-2-7b-hf.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Open-Platypus-Llama-2-7b-hf.IQ4_XS.gguf b/Open-Platypus-Llama-2-7b-hf.IQ4_XS.gguf new file mode 100644 index 0000000..737069b --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543a618b751dc8e2c0dfbb5a994d61700e57a2dff53c5e2d15618c7690a3784a +size 3647517920 diff --git a/Open-Platypus-Llama-2-7b-hf.Q2_K.gguf b/Open-Platypus-Llama-2-7b-hf.Q2_K.gguf new file mode 100644 index 0000000..0a64eac --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6ba4b6cceee9d16c44f90a8ce518ba64620c47315c6b6add7270a69c6119f28 +size 2532865248 diff --git a/Open-Platypus-Llama-2-7b-hf.Q3_K_L.gguf b/Open-Platypus-Llama-2-7b-hf.Q3_K_L.gguf new file mode 100644 index 0000000..8343a82 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92aa0d0420d832b83cff66118af7adc84c773915c864c7a59de960923d003877 +size 3597112544 diff --git a/Open-Platypus-Llama-2-7b-hf.Q3_K_M.gguf b/Open-Platypus-Llama-2-7b-hf.Q3_K_M.gguf new file mode 100644 index 0000000..1acefce --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:067ee75ea7ab4ebb4874213c671dcacb538230a55cbab1d408b4392385a42a4a +size 3298006240 diff --git a/Open-Platypus-Llama-2-7b-hf.Q3_K_S.gguf b/Open-Platypus-Llama-2-7b-hf.Q3_K_S.gguf new file mode 100644 index 0000000..f156414 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9e3b5ffa66436578a3d8a60a2d02463c00a4969607e95593ab827ec0aeb0ed +size 2948306144 diff --git a/Open-Platypus-Llama-2-7b-hf.Q4_0_4_4.gguf b/Open-Platypus-Llama-2-7b-hf.Q4_0_4_4.gguf new file mode 100644 index 0000000..295c1f6 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae17df6097f023107236ef155eddd5f0990b914d7bd33deaae0e89c88b575226 +size 3825808608 diff --git a/Open-Platypus-Llama-2-7b-hf.Q4_K_M.gguf b/Open-Platypus-Llama-2-7b-hf.Q4_K_M.gguf new file mode 100644 index 0000000..42e2d4c --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:990b622724160bd79e22b2dd6dd3af13d2d6ceef3171fa45965a263cb5f3ce0c +size 4081005792 diff --git a/Open-Platypus-Llama-2-7b-hf.Q4_K_S.gguf b/Open-Platypus-Llama-2-7b-hf.Q4_K_S.gguf new file mode 100644 index 0000000..d2afc01 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67ce78784c7153e0e52a66dc893e1386d020f28dc3ca5e64438c8ff24c5906e +size 3856741600 diff --git a/Open-Platypus-Llama-2-7b-hf.Q5_K_M.gguf b/Open-Platypus-Llama-2-7b-hf.Q5_K_M.gguf new file mode 100644 index 0000000..c469f08 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5474bb5d5b4b8ae45dcbe3035bde2c25702aa9707cdbc725feb5b33b1421488 +size 4783158496 diff --git a/Open-Platypus-Llama-2-7b-hf.Q5_K_S.gguf b/Open-Platypus-Llama-2-7b-hf.Q5_K_S.gguf new file mode 100644 index 0000000..55b0ee1 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f7a98ad2f1e917bdc89d658a8634a62a6e9c1012e17df419a9f2b790ba3842b +size 4651693280 diff --git a/Open-Platypus-Llama-2-7b-hf.Q6_K.gguf b/Open-Platypus-Llama-2-7b-hf.Q6_K.gguf new file mode 100644 index 0000000..9c3b327 --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d55e56c76e139b5513416928732f2632e09497446bf317a0cf517a72d548fa5 +size 5529195744 diff --git a/Open-Platypus-Llama-2-7b-hf.Q8_0.gguf b/Open-Platypus-Llama-2-7b-hf.Q8_0.gguf new file mode 100644 index 0000000..f76b13a --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a24a04fbf0b5522e86d2710205fbab25031d561e786aa22e4d16147c9d868a11 +size 7161091296 diff --git a/Open-Platypus-Llama-2-7b-hf.f16.gguf b/Open-Platypus-Llama-2-7b-hf.f16.gguf new file mode 100644 index 0000000..843764d --- /dev/null +++ b/Open-Platypus-Llama-2-7b-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e1f92af9e0e4d19cc89914471fd6abda9ce0d94199971025f34683a09d4b1a +size 13478106336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5732311 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: kody0525/Open-Platypus-Llama-2-7b-hf +datasets: +- garage-bAInd/Open-Platypus +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- Llama-2-7b-hf +- Open-Platypus +--- +## About + + + + + + +static quants of https://huggingface.co/kody0525/Open-Platypus-Llama-2-7b-hf + + +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/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Open-Platypus-Llama-2-7b-hf-GGUF/resolve/main/Open-Platypus-Llama-2-7b-hf.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. 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. + +