commit df54dec8e66bf710fba6af116005e09128cbc001 Author: ModelHub XC Date: Tue Sep 1 14:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f67334 --- /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-dolphin-open_platypus-pruned_70.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.IQ4_XS.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.IQ4_XS.gguf new file mode 100644 index 0000000..9ed5cab --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312016383025c38ab68605c6f12a86829be64eafad9a7f1dbb95b4fae20251e9 +size 3647518368 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q2_K.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q2_K.gguf new file mode 100644 index 0000000..0639f37 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac610eaf955a488df012eb2ff34b5a4c84fe23adb6d765aaf446dd867688804 +size 2532865696 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_L.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_L.gguf new file mode 100644 index 0000000..2aaa7a8 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2d3c5d0b3162281d7e4269483aad8b25ca62fa24352315ff9a80bcfab15701e +size 3597112992 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_M.gguf new file mode 100644 index 0000000..f283735 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4da4de9aed69b531a62856eecc1b920238fca7ba2dec8d8ae2b67dba78ade60f +size 3298006688 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_S.gguf new file mode 100644 index 0000000..1c6c026 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d1551c11fb2f4dc7334d72948562d96863d12409822cef05da8c3557e1513c +size 2948306592 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_M.gguf new file mode 100644 index 0000000..3e673bf --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89063c5275ceef26387e1f6ee0600c1744e3583f68d47b6e5cca68bc0f6dfa41 +size 4081006240 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_S.gguf new file mode 100644 index 0000000..1385fd1 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb241f931960de02403f964733ed86ae918d4cfbbca4184a68d26a30fb28f4ba +size 3856742048 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_M.gguf new file mode 100644 index 0000000..b6f4589 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabbf99524a7100c2d2b30459f84c23d1bd7ba864dd6635e2b2eef446708279b +size 4783158944 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_S.gguf new file mode 100644 index 0000000..b0406bb --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35ac4c27634b5379969ae2b0425d519409b2fdda780c52685719fcc327d3a1e +size 4651693728 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q6_K.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q6_K.gguf new file mode 100644 index 0000000..241451f --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce63c7e7c790065b0d0e9660ce983decc881c8a2eaccca8efff38188f56a8e53 +size 5529196192 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.Q8_0.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q8_0.gguf new file mode 100644 index 0000000..2871a6e --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffce1bcd6b92a2920f5e5ecdb59c3ccf199306874943d7b9a4f3cc7b84dbf40 +size 7161091744 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_70.f16.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_70.f16.gguf new file mode 100644 index 0000000..0b77023 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_70.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a74fe0eb43518bee387613b52acddb26d6859cdeda3eaacb7b5f6e44d18c50 +size 13478106784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3ca9a34 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: RedHatAI/Llama-2-7b-dolphin-open_platypus-pruned_70 +datasets: +- garage-bAInd/Open-Platypus +- Open-Orca/OpenOrca +- cognitivecomputations/dolphin +language: +- en +library_name: transformers +model_type: llama +quantized_by: mradermacher +tags: +- sparse +- instruct +--- +## About + + + + + + +static quants of https://huggingface.co/RedHatAI/Llama-2-7b-dolphin-open_platypus-pruned_70 + + +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-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_70-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_70.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. + +