commit 8b4f10af4cca0b1769f094b22166e99daa551a6e Author: ModelHub XC Date: Fri Jun 5 04:06:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..474ba7f --- /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 +Hermes-2-Theta-Llama-3-8B-32k.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_M.gguf new file mode 100644 index 0000000..7f58f74 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c85a1a3f966f17ae64d4a6c02b18d5b61431c6a5046913a145056667958a359 +size 2161971936 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_S.gguf new file mode 100644 index 0000000..a8262e9 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc071c85a64df16b888bafccafa49e63d9f90798229d209443c40b26b7d60d29 +size 2019627744 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_M.gguf new file mode 100644 index 0000000..0f22a58 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4be62834582848976c4468870efe7c04d839c7d61ef7aa1425af56751dd01f +size 2948281056 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_S.gguf new file mode 100644 index 0000000..43214fc --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb8bd4043cc97c0b80e2102012b2845282d869bdacb0db90f3cb9b2df370a80 +size 2758488800 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XS.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XS.gguf new file mode 100644 index 0000000..26358e5 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a793c50a995873747907780a1562a326544f31e083303d9175242e7e2f1299f +size 2605781728 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XXS.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..5a9fd94 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d6305643dbf53b9232d1bef34b42696a1fa739180ffd1862b2b126d904715f +size 2399212256 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_M.gguf new file mode 100644 index 0000000..371a840 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ab46e7bf5b826f4a77f34405994539d4922490fcb9d1c61f028c3032c5f402 +size 3784823520 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_S.gguf new file mode 100644 index 0000000..7fc1efe --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8022b66682d62bdf78dcdb52641ed934446388068f302f624b096a3ff32c27a4 +size 3682325216 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XS.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9bdacee --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3550fd0c5516e657b4877d88be9e414e07a575bba7d3a1bfc229e065dd1f171 +size 3518747360 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XXS.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d07b431 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60c60acb836c52b7ddb706faceded187f21490b3e3b2d1fd9a064b0eb7fa7212 +size 3274912480 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ4_XS.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ4_XS.gguf new file mode 100644 index 0000000..60bc6cb --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76eb3f7c34075bdb3e29bd81d934ffc9db4721509338ae10b7bb1b5b73f576b1 +size 4447662816 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q2_K.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q2_K.gguf new file mode 100644 index 0000000..c51c803 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f76ea130a90224be6ad7369d8ef935187c6c3f6b79b95709eccbb70a2adc70d +size 3179131616 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_L.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bd569df --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57e25c6d93af3a46f01372759c79ae9ee87d69fa0771e48b8117725256106f7a +size 4321956576 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1723200 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da20282bc6c1dd2c25e78ae140e327af231d4d6b5682a3c044e4661c210b7e3 +size 4018918112 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_S.gguf new file mode 100644 index 0000000..788a4e3 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc9537d5a9187e427997235d0169ce7450f202625ad725f50282221b9d4e2c1d +size 3664499424 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_0.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_0.gguf new file mode 100644 index 0000000..29df6b4 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fee25efdf75883744ab3c78ddb23acfb664eb3ecb583ea0b5d5e0328c6ade6 +size 4675891936 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_M.gguf new file mode 100644 index 0000000..7d6f909 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76cc3b5a16055bf747e23b676b800c1d35db0950612d00a4d9ff977be7d0c52a +size 4920734432 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_S.gguf new file mode 100644 index 0000000..38729bf --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40894c16b501f5a1c3f9196b5784a081d78288d1b9e7fc354527effcacf1a697 +size 4692669152 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_M.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_M.gguf new file mode 100644 index 0000000..7a40efd --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2628464ba05339d65a3bbf11402ac9eedaf956c1e7cb08658de0b2d35939346 +size 5732987616 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_S.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_S.gguf new file mode 100644 index 0000000..eabd6bc --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f8b9c9893e6fd273653e9c64d3345e43847f89489a1304396ca7d4eda1fc9b6 +size 5599294176 diff --git a/Hermes-2-Theta-Llama-3-8B-32k.i1-Q6_K.gguf b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q6_K.gguf new file mode 100644 index 0000000..8a9aff2 --- /dev/null +++ b/Hermes-2-Theta-Llama-3-8B-32k.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd0d44c5fc128083f0f94cbceef0673236c5ea6d6dea9cff80316db29943d7b +size 6596006624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9410650 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: OpenPipe/Hermes-2-Theta-Llama-3-8B-32k +datasets: +- teknium/OpenHermes-2.5 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- Llama-3 +- instruct +- finetune +- chatml +- DPO +- RLHF +- gpt4 +- synthetic data +- distillation +- function calling +- json mode +- axolotl +- merges +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/OpenPipe/Hermes-2-Theta-Llama-3-8B-32k + + +static quants are available at https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-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/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF/resolve/main/Hermes-2-Theta-Llama-3-8B-32k.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..861214c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f7aad633ca765e4c8b17679bb45585398167edd523f39fe23cb0a26507e12fd +size 4988161