commit 9c0ea3416f17cabf7f44a0c5eff98f91044df656 Author: ModelHub XC Date: Mon May 11 10:36:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1a59ea --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf new file mode 100644 index 0000000..3eb8d3a --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44897947d24a51f7053234e2f67911b5385f078bb4f9c1712a53717549e96862 +size 7875961248 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf new file mode 100644 index 0000000..8a69031 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:858e3114ae1e1ead323e4b0a51e663afc0095e69cd20da68656302b408658c5e +size 7223959968 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf new file mode 100644 index 0000000..18ce9c3 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9207fef32c81eb53d63628017577f18e01e72162e565a826e36b4c87ce3e0400 +size 11182682528 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf new file mode 100644 index 0000000..a567db6 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba2eff5714bd1b87b69af4cad8391caf8f4e92c5b308cd9d1832b99c7f09c236 +size 10313347488 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4a54c8e --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e99a46c4cdcf4778ae7f74c2f68c329db33ade5006434dde4582967e7727a7e +size 9884393888 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..362bdda --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e682f8749ad0bf73047366edd478d59954afa9ab639e49d4689f47f7315b6775 +size 8962630048 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf new file mode 100644 index 0000000..cb7b5c1 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8d60787fe32896681f4469620b51b056dde06b277167a4d767fc25865f74d3 +size 14700593568 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf new file mode 100644 index 0000000..420f770 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1d36f2fcb16ebe22a97c030be3cf96690015a88a4e0815c4527795eb35af2e +size 14328758688 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f7ab73f --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4fdf1404c23364e65dce2479709dc95fafb98bc677d1ad2b95ac14a27164f09 +size 13603275168 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..61cda3c --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d0da4aa4ae1a99d0803a95ee0b91a0c86cccea12b7f2fc25525be33ecd7ae6 +size 12742930848 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf b/Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..24a8128 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e398f123ff652dc857b9c9a7dfee08c16b4d2266ff0464984772da23524fec5 +size 17559458208 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf new file mode 100644 index 0000000..06c34af --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58f7717f0d827a9aa78d63f6227ef58d6cd8b343f52bb013f626f87828b9b5db +size 12222001568 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..a49167e --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10cc33f9ee5db56f5072bcf970fd75a1b5c7a52d5f99a85f5415ab1ee98acee +size 17117315488 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..76b0b06 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166a302733cb9140877b778f306c60d27c74c8223c2a7acba35894bec92737bd +size 15815115168 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..a059379 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1182fdac88756a9e3a2d5c7e100359d21002cb2eba08992ff70b41be772d717 +size 14284194208 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf new file mode 100644 index 0000000..5d12f91 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de89e611acdd6ae49f53d645ff959c1fe2cdb11d06328787b3ee1239b22c4ac +size 18568794528 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..277f774 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a24aa13461113760d7d9096b811c5ec76739609f9fe7db16f05a1321eb2e01 +size 19698962848 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..bc5a464 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b70a1e333e5410fd254e3abc2cbf0d54259ed3e494095face97ecbbe8d7aae77 +size 18641539488 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f4c398f --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a6cefb7f70b61a5a894cf24ca4fa55a98200967b477bb83ff7694f6191bd3ff +size 23083569568 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..90e88ea --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5b2e92b22c867612bc56acf44951c171a54633eaa4057d1c944c27d5f00717 +size 22465237408 diff --git a/Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf b/Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf new file mode 100644 index 0000000..741ee86 --- /dev/null +++ b/Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421949debe23e319748a26b16bae9f4441722dcbba83081f8734ad41dd520b28 +size 26679714208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b67c5b --- /dev/null +++ b/README.md @@ -0,0 +1,120 @@ +--- +base_model: Weyaxi/Einstein-v4-Qwen-1.5-32B +datasets: +- allenai/ai2_arc +- camel-ai/physics +- camel-ai/chemistry +- camel-ai/biology +- camel-ai/math +- metaeval/reclor +- openbookqa +- mandyyyyii/scibench +- derek-thomas/ScienceQA +- TIGER-Lab/ScienceEval +- jondurbin/airoboros-3.2 +- LDJnr/Capybara +- Cot-Alpaca-GPT4-From-OpenHermes-2.5 +- STEM-AI-mtl/Electrical-engineering +- knowrohit07/saraswati-stem +- sablo/oasst2_curated +- glaiveai/glaive-code-assistant +- lmsys/lmsys-chat-1m +- TIGER-Lab/MathInstruct +- bigbio/med_qa +- meta-math/MetaMathQA-40K +- openbookqa +- piqa +- metaeval/reclor +- derek-thomas/ScienceQA +- scibench +- sciq +- Open-Orca/SlimOrca +- migtissera/Synthia-v1.3 +- TIGER-Lab/ScienceEval +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +- phi +- phi2 +- einstein +- instruct +- finetune +- chatml +- gpt4 +- synthetic data +- science +- physics +- chemistry +- biology +- math +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Weyaxi/Einstein-v4-Qwen-1.5-32B + + +static quants are available at https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-GGUF +## 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/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.0 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_S.gguf) | i1-IQ2_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ2_M.gguf) | i1-IQ2_M | 11.3 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q2_K.gguf) | i1-Q2_K | 12.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.7 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_S.gguf) | i1-IQ3_S | 14.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ3_M.gguf) | i1-IQ3_M | 14.8 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 15.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.7 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_0.gguf) | i1-Q4_0 | 18.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 19.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.6 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.2 | | +| [GGUF](https://huggingface.co/mradermacher/Einstein-v4-Qwen-1.5-32B-i1-GGUF/resolve/main/Einstein-v4-Qwen-1.5-32B.i1-Q6_K.gguf) | i1-Q6_K | 26.8 | practically like static Q6_K | + +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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..bb61145 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27465f425469a4aa5690de6547f3b58a5526e74db0cc13ef25d0b17b0190b15 +size 14891546