commit 7161a209f0c30dcd87d2d2a3003f7f0feaa6f4b7 Author: ModelHub XC Date: Mon Apr 27 20:47:33 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c1ecc9b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..28c186d --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c72a42268f90e350fea60dcd596046f603ea07d18e4115e58b35e17f658c96 +size 2161977408 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..37f7ab6 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9445c132e0f60b9268dfc510312fa597cdd5835a863903633431d83effed2805 +size 2019633216 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..8eba0cb --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6d8fe41952ace18c7f46ffa78f46542ada0623cc1429ddf697a0c07e089e2de +size 2948286528 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..125500d --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d46830e161b87f753c88017fede7fe6087387552fc1f5fd88d00435cb017e6 +size 2758494272 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XS.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4ae2715 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e305140978d4e602f42cf62fda4cf5c1043b760e512d7c958dfec8370bd9e0a +size 2605787200 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XXS.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1eb15c0 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca30c0c79db6f0bbb87e28b9265e73eb8c14b14824c476dd8803e9d0e3a33bb +size 2399217728 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..7b1b735 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b36f940694ca29ff75fc093ce86bb918599b05e57228bc2983675c2e4957e1 +size 3784828992 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..f48d4f2 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfc6232be08973d6ebd80dab600653fce85e8c0adf763a3e2ba8e46a5f7f592 +size 3682330688 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XS.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..b5a9609 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c02c688705d20063a7e51eea01505da86bbb0ba31b916ff19c66035132237bc4 +size 3518752832 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XXS.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..48fedd2 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c781b343990bf1fc89498720b3bc430b38e462cdc63a53a6ea7385803aac87 +size 3274917952 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_NL.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_NL.gguf new file mode 100644 index 0000000..090b174 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2511ab985d1e59d91943c88de86e464236c3e51f679f7841cfb73ee18b871de7 +size 4677994560 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_XS.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..32c925e --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7ddf8950231817ea0ef1cd33ea2af6a0a1763888070689ca599f23ee12d471b +size 4447668288 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K.gguf new file mode 100644 index 0000000..ff3328f --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc3d35909179895785893eae8bfc68541258391cec4232bcc58be103edb447da +size 3179137088 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K_S.gguf new file mode 100644 index 0000000..6c17496 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd6a24982513cb0a372cfaa38900564eb1d6a6ce2a3161084718458c716b7ed +size 2988820544 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_L.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4f0a347 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aa5cdcf376dd05f2871638ca28e797c14ea1640e74fc80c572e6f98f87c52cc +size 4321962048 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1558578 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefcbccdf5e8803b83cbdbae3a225d0fd814338fbcb66f82c218b23e747a93c0 +size 4018923584 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d5cff7e --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f5d652149912b2d6087c87ed28270ad61de2166aa53fc01713d09c71b1ae395 +size 3664504896 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_0.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_0.gguf new file mode 100644 index 0000000..0042c0a --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97cdf62e0327418bbf00d8ffeb07f123865b041f39174e99ac097865897b660 +size 4675897408 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_1.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_1.gguf new file mode 100644 index 0000000..e0dce0f --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c72a44814d76f39b71d49440f0c807a62505b17f2de5bd45a51d98ac8d047fe +size 5130258496 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..db2f341 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0141e83d73d77dae1b90db74ef8ecfa3c1a333872b3069fad285e2c6ab3ec622 +size 4920739904 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..283bf8b --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f223aa1b4d41ec9371657901d00bf2a83586cc6113d7e858ba38d9511e6a57 +size 4692674624 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_M.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6d13ef2 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810f5e5ecf4a433bf4a33bf023efb019b5139f186e19eb225add0c222ca8721f +size 5732993088 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_S.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f0accb0 --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29611ad7d29ecfdef227e727674748b5ee0e1ba5bc84295781988655eadf73dd +size 5599299648 diff --git a/KoBioMed-Llama-3.1-8B-Instruct.i1-Q6_K.gguf b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q6_K.gguf new file mode 100644 index 0000000..79d158b --- /dev/null +++ b/KoBioMed-Llama-3.1-8B-Instruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3931bad618ff05df33b1fc45049d4508c6d40a68d71590c85a8c75170619fe04 +size 6596012096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5587b0a --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Lowenzahn/KoBioMed-Llama-3.1-8B-Instruct +language: +- ko +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- biology +- medical +- Llama +- Instruction +- DPO +- text-generation-inference +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Lowenzahn/KoBioMed-Llama-3.1-8B-Instruct + + +static quants are available at https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-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/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KoBioMed-Llama-3.1-8B-Instruct-i1-GGUF/resolve/main/KoBioMed-Llama-3.1-8B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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..d76c221 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30349597a879c12b6542107649905e27a4a79dcd91cc712b52261b25d1612e70 +size 4988157