commit f60a8b92198ca8a79916deca25fedc86cdfc5475 Author: ModelHub XC Date: Wed Sep 2 00:42:16 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_50-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1af2fa --- /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_50.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-dolphin-open_platypus-pruned_50.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.IQ4_XS.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.IQ4_XS.gguf new file mode 100644 index 0000000..2e4b5bb --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2073a56f5847faf641b873b62e5cb43d8c22f96f4e1fcf104285b7abc1955c +size 3647518368 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q2_K.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q2_K.gguf new file mode 100644 index 0000000..b6427f5 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db182aab6f627f428d4aad94e42083d9550bbcc2f1d626e740dc358e942abbf9 +size 2532865696 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_L.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_L.gguf new file mode 100644 index 0000000..5c43594 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98f2e3cae395758760f00a6525a65093d9542a5e2623bb9141286ab962e4f5d +size 3597112992 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_M.gguf new file mode 100644 index 0000000..4ddc032 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4081dcad1b3beece7e872cd155614d2ad22f45139802a2cd130ef4fe9a3ebb +size 3298006688 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_S.gguf new file mode 100644 index 0000000..7d6f970 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a9d566b620ed551790fc4ffd7acf3c8b18d1fab8f224424a2d4d1ee19524d9 +size 2948306592 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_M.gguf new file mode 100644 index 0000000..99c294c --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e9125f87df936186da137eb2a15367c77f8e174151bd35160e76f1d53ba1e56 +size 4081006240 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_S.gguf new file mode 100644 index 0000000..061dda6 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e6060202850f99a62788cc0f72fbd6af5e2df779bc6b3e77b64226400c5dc3 +size 3856742048 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_M.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_M.gguf new file mode 100644 index 0000000..d6906ef --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd50821ac5894b13e71abbd4d2d65f059cc41b4efdd1780924e24b7ea77cc669 +size 4783158944 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_S.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_S.gguf new file mode 100644 index 0000000..1b4d546 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b801fee309f04fa0192beec09c5ee00ab84e143e15379bf13f87948e25f95643 +size 4651693728 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q6_K.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q6_K.gguf new file mode 100644 index 0000000..90c8215 --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f0a1573b038a24e8ef1397ecda72035fdca7e204a23a261063d292807e7998 +size 5529196192 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.Q8_0.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q8_0.gguf new file mode 100644 index 0000000..035682b --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbaca13d13a26fed17142530305b9a118fd112ec6fcfac366ca69882aa5ff621 +size 7161091744 diff --git a/Llama-2-7b-dolphin-open_platypus-pruned_50.f16.gguf b/Llama-2-7b-dolphin-open_platypus-pruned_50.f16.gguf new file mode 100644 index 0000000..82c910d --- /dev/null +++ b/Llama-2-7b-dolphin-open_platypus-pruned_50.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fd6b4b457eb290e5f29410a05a3e450581c43f05e5cd2fabc9c204c9af5772 +size 13478106784 diff --git a/README.md b/README.md new file mode 100644 index 0000000..26462e6 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: RedHatAI/Llama-2-7b-dolphin-open_platypus-pruned_50 +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_50 + + +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_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-dolphin-open_platypus-pruned_50-GGUF/resolve/main/Llama-2-7b-dolphin-open_platypus-pruned_50.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. + +