commit ed2ac333eb9450b26510ce46ce416a23b39056ba Author: ModelHub XC Date: Tue May 19 20:26:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fbdc029 --- /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 +DeepSeek-llama3.1-HARI-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-llama3.1-HARI-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ1_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..4ecca11 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb0b72473ae71059c49d411b7c0791f3ca28328bf693017fc71c1919e636d8a +size 2161978112 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ1_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..ddd15cc --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3116c49f98a87b8db8ebaae2a50754ce7bfedc4b567fe222943055ca827bf37d +size 2019633920 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ2_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..0bb5fc4 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8be140f4e9c38ef16389e10c36e4ba862ee63de0c159d2c89fec59fcab580a +size 2948287648 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ2_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..8639565 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08830161d9dfc58604674c7353c61ecc7b80adb326f00d6947fde158c002f4c4 +size 2758495392 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XS.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..db9fc0c --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac1396d20d2a309f96a55a8fd523dd0018244fcaebca9199e51cb2e08260bdbb +size 2605787904 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XXS.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..f3501e7 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c3f98a958f1749adb1519b30c3513f78083ee454cd0035112d50cbceba496c +size 2399218432 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ3_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..78e9195 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beef47a9be78f90e2c96f5bc71309556c9902efb0cb41db6801099882f146079 +size 3784830656 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ3_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..9743e41 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ade36bcf04cbf6cc7cf58af73e0e2dfa8ec1a05d988eaf2187fe21c15786c8 +size 3682332352 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XS.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..211ca45 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f98cfe9c3a691300892e276c64c1e08d1ba76faf0256dc3bb0ca18d8dc0b24 +size 3518754496 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XXS.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8b05d07 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16619cef84c244d71c67ea4ea027f79b547f7c8863daa78add6decf0168a925a +size 3274919072 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ4_NL.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..c81c53c --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f4d58383f9e8fb958933b5d7febbadebbfaf37e94875d83f6342e333755940 +size 4677996768 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-IQ4_XS.gguf b/DeepSeek-llama3.1-HARI-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e4f33fd --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60739586f5cc024f7f1861b0379132ccc89ec168d6a66db95c5fa0d427e4615c +size 4447670368 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q2_K.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..6e070ca --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074a92d7d108e316a170f028a88872669acee46fcb97bdaa9adcbf205a8b3af2 +size 3179138336 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q2_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..e576df5 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5729e85a6d13724669a53efa02c45f709743c22e88b38dc48002d4914a0ee57 +size 2988821792 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_L.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..ca48cc8 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed927cc80110c4758231430bb472e27901b3895a60adcf77ce53be3d01f711f5 +size 4321963712 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a37372c --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c7198a0b5790eefb4805185e6b5c53fb1351d4805c3172a77139e3a2fb1cfbf +size 4018925248 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d0a7203 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bac7b10e1a2df0010d3020898f098e700a91707173db681f13d3c2f1cedc6742 +size 3664506560 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q4_0.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..f6188aa --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426496b26e55c89b2e9056391e144d6134890e1dadd79cfb946e94be2be0756c +size 4675899616 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q4_1.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q4_1.gguf new file mode 100644 index 0000000..6f176db --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bbdc4b1b5798766ec590c74c7e7c37b4d98032fd46c8d95e06747fe808dc031 +size 5130260960 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..1fe701c --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48193135821abb491d3d7a14b0a7ab78cbefd5d3b707e6aec209e0304996c8a2 +size 4920742112 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8286f9b --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530a959d9e777d575ad9865ea8ab6ea165ab5f1252e889354f553fc37ced43be +size 4692676832 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_M.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0f6d505 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a491c595caa09aa8aedd97400bed1e08750c07fb2b490fd86b983a3d3cdf5621 +size 5732995808 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_S.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..422b896 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fe4c5479326e21b2c3e4eacf11d8b9ffe04558b0f2665a53c5fa12c04ab160 +size 5599302368 diff --git a/DeepSeek-llama3.1-HARI-8B.i1-Q6_K.gguf b/DeepSeek-llama3.1-HARI-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..0aff631 --- /dev/null +++ b/DeepSeek-llama3.1-HARI-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd578265f0c8496a09edc129bfb83f538e15a31e69dd29aa08c0420e7ae6fe50 +size 6596015360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8a731e --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: SNUH-HARI/DeepSeek-llama3.1-HARI-8B +datasets: +- FreedomIntelligence/medical-o1-reasoning-SFT +- SNUH-HARI/KorMedLawQA +language: +- en +- ko +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- medical +- unsloth +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/SNUH-HARI/DeepSeek-llama3.1-HARI-8B + + +static quants are available at https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-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/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.8 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-llama3.1-HARI-8B-i1-GGUF/resolve/main/DeepSeek-llama3.1-HARI-8B.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..219994a --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8d49cb4cd61d10d3146d54b6f120bb39178ab75251062a96f978264f3f7565 +size 4988157