commit 4058d65bde6ef66fcf86689ac1130a5e3b269b46 Author: ModelHub XC Date: Wed May 20 05:50:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9b50cc8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +Llama-3.1-8B-UltraMedical.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ1_M.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ1_M.gguf new file mode 100644 index 0000000..7507d19 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01e3bb26181c45fd4e24455dd4f5d076b1c4884abd5e5f9a832dadc1980e5227 +size 2161973536 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ1_S.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ1_S.gguf new file mode 100644 index 0000000..248f756 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e25d110b61a1c5669ed8793b7e285c53228e816e588d5e0cc133ea4d50ff24c +size 2019629344 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ2_M.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ2_M.gguf new file mode 100644 index 0000000..084535c --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba277a9637783b0b3f5ef3c6bc2616e80ca0364e68a19c990ab0ff5ac982298 +size 2948282656 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ2_S.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ2_S.gguf new file mode 100644 index 0000000..c32bb82 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33f39f1df2ceb54d3aa6e90d45a1a8ff21579934a3a739738481c4c76d7a770 +size 2758490400 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ2_XS.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6d13075 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ec501c1baf84b0338eeaa86f7d1d4d61ae6c9539b21c1e16efadfd1c65f1da +size 2605783328 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ2_XXS.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bf7bb5a --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c8466a6637911d86445e0cffbbb903b6ab7c72f6f93cf20ea1704a3e81106f +size 2399213856 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ3_M.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ3_M.gguf new file mode 100644 index 0000000..af5e6c0 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ac65c67d1339217a76093aafde1d515c21fe02dca6765e2d7331ce793946363 +size 3784825120 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ3_S.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ3_S.gguf new file mode 100644 index 0000000..30fa942 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37333c8bab46946f25a5d06bfcff5a2cd587ac28cb327b9bd63f3a939d3de4a3 +size 3682326816 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ3_XS.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ3_XS.gguf new file mode 100644 index 0000000..c016832 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17600fbffa7b171a4361c0e0950de1a4443b101c1e534369c398ee2efed7047 +size 3518748960 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ3_XXS.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4e67d7a --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae61e104cb09560649e81119ec60c93aeeaee9eb800aaa2204f30d58a0e9c5f +size 3274914080 diff --git a/Llama-3.1-8B-UltraMedical.i1-IQ4_XS.gguf b/Llama-3.1-8B-UltraMedical.i1-IQ4_XS.gguf new file mode 100644 index 0000000..811f1b9 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467587b2d1c3b72f54ffc4e26559b7c5e595c734e9557c4e6242cb61c32e4b3e +size 4447664416 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q2_K.gguf b/Llama-3.1-8B-UltraMedical.i1-Q2_K.gguf new file mode 100644 index 0000000..18b55a9 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a17d27e7feff2e4a54b034939a207c4e431454f366aac824700dac690bb2339c +size 3179133216 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q2_K_S.gguf b/Llama-3.1-8B-UltraMedical.i1-Q2_K_S.gguf new file mode 100644 index 0000000..db43937 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd876c28a98d8387754b1bc9cf7cb9a3e707a869b8d0b4e92050c623de04a56 +size 2988816672 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q3_K_L.gguf b/Llama-3.1-8B-UltraMedical.i1-Q3_K_L.gguf new file mode 100644 index 0000000..4bb5492 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f3412b55d18240c85be6fbeef8bf5f372bfc76c363619bb843e6b67ba9c6f7 +size 4321958176 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q3_K_M.gguf b/Llama-3.1-8B-UltraMedical.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1feda24 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83aa7be8370c6dc1f83940cd1a98f2db58f467decc9d87e66cc737d110ffe28f +size 4018919712 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q3_K_S.gguf b/Llama-3.1-8B-UltraMedical.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8048134 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:576dbf383b2a01773cc03c18783e1b5c44d854d1e0ea5bb87ce1436fcd74fcb5 +size 3664501024 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q4_0.gguf b/Llama-3.1-8B-UltraMedical.i1-Q4_0.gguf new file mode 100644 index 0000000..a580af8 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f3606ecd19c5c6dffacbf943cde3826ec6441e87002eb6104a8b87ac3c4b9d4 +size 4675893536 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q4_K_M.gguf b/Llama-3.1-8B-UltraMedical.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4a23a0a --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f58654150fba45dde06e43f6f9e2723f8458d73df892ebc123cdd6041013caa +size 4920736032 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q4_K_S.gguf b/Llama-3.1-8B-UltraMedical.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8cc25c1 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffffd466c04ddaecb55a56b6b2b966025fcf8128c46586b89f7889a2ee8aac4d +size 4692670752 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q5_K_M.gguf b/Llama-3.1-8B-UltraMedical.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4ca1c32 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe03c68d04b0e3c286289382dd83807235a584900a8ac2a934d378ae7cc8817 +size 5732989216 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q5_K_S.gguf b/Llama-3.1-8B-UltraMedical.i1-Q5_K_S.gguf new file mode 100644 index 0000000..63428af --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532484f8019e62ce08f0f5f26c573809b71384273efa3183c447922e553e0a57 +size 5599295776 diff --git a/Llama-3.1-8B-UltraMedical.i1-Q6_K.gguf b/Llama-3.1-8B-UltraMedical.i1-Q6_K.gguf new file mode 100644 index 0000000..871a91e --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dab10b057966475a154aa1632e0685f2f3ca749fc5f2eb93d7bb33a86e8f5fd +size 6596008224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f165496 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: TsinghuaC3I/Llama-3.1-8B-UltraMedical +datasets: +- TsinghuaC3I/UltraMedical +- TsinghuaC3I/UltraMedical-Preference +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/TsinghuaC3I/Llama-3.1-8B-UltraMedical + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-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/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.1 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-i1-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.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..3ab51f5 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6013ee34dc106052f3bd26edb4de01de275887583d2b21c131fba51a9c552cf5 +size 4988157