commit 8497c8a723d3431c51e31b0c5c62a8c3fa83d9d5 Author: ModelHub XC Date: Wed May 13 15:09:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e75cace --- /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 +Llama-3-8B-StoryGenerator.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-StoryGenerator.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-StoryGenerator.i1-IQ1_M.gguf b/Llama-3-8B-StoryGenerator.i1-IQ1_M.gguf new file mode 100644 index 0000000..fcf076e --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9af1c5875d3a7dc31a34a07d0f5c69401dac6931896a7ea50212abb84ad0dae +size 2161972992 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ1_S.gguf b/Llama-3-8B-StoryGenerator.i1-IQ1_S.gguf new file mode 100644 index 0000000..9491304 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8d4882d85bd5312a2809ddb2c6ed16d80da53e0eada35214e80fd2f4b238c5 +size 2019628800 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ2_M.gguf b/Llama-3-8B-StoryGenerator.i1-IQ2_M.gguf new file mode 100644 index 0000000..2b04240 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45b39e5b5c301774a265be8ebae6952e9d492636ca4eb3ababfc646863fa5478 +size 2948282112 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ2_S.gguf b/Llama-3-8B-StoryGenerator.i1-IQ2_S.gguf new file mode 100644 index 0000000..de536ea --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431fe59f50e60536b3b83747c4fad705ba5fa9724e5556ebf990ff29836e0520 +size 2758489856 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ2_XS.gguf b/Llama-3-8B-StoryGenerator.i1-IQ2_XS.gguf new file mode 100644 index 0000000..395697f --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3afa3ec338ef98f825834e874b51078618c26d16d80745fb7a804d6448654ca5 +size 2605782784 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ2_XXS.gguf b/Llama-3-8B-StoryGenerator.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..96732a8 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c319cfc9b32a85cfad6b53e94dc0b247ac8a9ec73ceba087882ab8edcb6a1b17 +size 2399213312 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ3_M.gguf b/Llama-3-8B-StoryGenerator.i1-IQ3_M.gguf new file mode 100644 index 0000000..c72b98f --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96bfa18923a2934750c86a7b60139a5d5586b1eb2c949ef3904f612fc89dd7a0 +size 3784824576 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ3_S.gguf b/Llama-3-8B-StoryGenerator.i1-IQ3_S.gguf new file mode 100644 index 0000000..1bef2d1 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b54196e85f9a6dbab7602d0e36d30f54953b3ad03fe5e0d86fc0515b3b4434 +size 3682326272 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ3_XS.gguf b/Llama-3-8B-StoryGenerator.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7e7252b --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a455c4f61bb1de16b22aaf397f66d226aff63fd92a003bd55ed57fdd135ed8d9 +size 3518748416 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ3_XXS.gguf b/Llama-3-8B-StoryGenerator.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..41ecc6c --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fb841b515da4b43fb0785dff683e5e8e6b90830d22e51e7ddb41541a1a539d +size 3274913536 diff --git a/Llama-3-8B-StoryGenerator.i1-IQ4_XS.gguf b/Llama-3-8B-StoryGenerator.i1-IQ4_XS.gguf new file mode 100644 index 0000000..2c8d9d6 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b9e0260ce73090606639e65b8765a63a94ad88bd1172eac790de2b4b468438 +size 4447663872 diff --git a/Llama-3-8B-StoryGenerator.i1-Q2_K.gguf b/Llama-3-8B-StoryGenerator.i1-Q2_K.gguf new file mode 100644 index 0000000..47c27d3 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bee819d5529982b9963068bbcdfce1310a67e5a11f1fe5cc9ba6908817be378 +size 3179132672 diff --git a/Llama-3-8B-StoryGenerator.i1-Q3_K_L.gguf b/Llama-3-8B-StoryGenerator.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8af7b79 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2549fecfad8d74fd3ae11f8eff626c7d07c94ea9d681cd146a931dae1ba2d555 +size 4321957632 diff --git a/Llama-3-8B-StoryGenerator.i1-Q3_K_M.gguf b/Llama-3-8B-StoryGenerator.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c895a43 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbbb06ede407ab4a87b90efcfcb47954057792910f95fd075e9e75a48888d7d +size 4018919168 diff --git a/Llama-3-8B-StoryGenerator.i1-Q3_K_S.gguf b/Llama-3-8B-StoryGenerator.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e0aea76 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:009fa1baabc304dedb85c463e53e527770245962ac6a793add19bd81e6fef6c1 +size 3664500480 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_0.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_0.gguf new file mode 100644 index 0000000..bab4c28 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92138de4b0ddc304621b6ffbf60f32a3297c11a4c5cf3a5edd1566c0a3f83aa +size 4675892992 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_0_4_4.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..8c93e27 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81c5e14d042063ad0e7b1e2651a370a89aca8aabbd032fbb41ece19307ff1fc6 +size 4661212928 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_0_4_8.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..f3022e7 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dfc41966f7e521d605d7a7feb14d36d950c0e03a542b1d30d64d8a2d5494b8b +size 4661212928 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_0_8_8.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..9b7ae63 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dc486a220f617c7a6d8d910211cadf091b3b2e5cfc00fec75b6515f7bc488cd +size 4661212928 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_K_M.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_K_M.gguf new file mode 100644 index 0000000..92b5e53 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b3b8a4b9133be47a9606c4f324c352bdb21a11dd867eeb2cab4f253b997058 +size 4920735488 diff --git a/Llama-3-8B-StoryGenerator.i1-Q4_K_S.gguf b/Llama-3-8B-StoryGenerator.i1-Q4_K_S.gguf new file mode 100644 index 0000000..c9ddf8c --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d82731a68dad9da5568365339eebb57053aa67a71caf22bd31496805e01581 +size 4692670208 diff --git a/Llama-3-8B-StoryGenerator.i1-Q5_K_M.gguf b/Llama-3-8B-StoryGenerator.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3ad0388 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bf580b259e66726f56f6160698c5cce410afbb43e151a33d271f5c77e6bc501 +size 5732988672 diff --git a/Llama-3-8B-StoryGenerator.i1-Q5_K_S.gguf b/Llama-3-8B-StoryGenerator.i1-Q5_K_S.gguf new file mode 100644 index 0000000..60b7397 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88910ccc040f4f7811938e702b8173c5b71bd5c84609af3b3be6502ae1472a7e +size 5599295232 diff --git a/Llama-3-8B-StoryGenerator.i1-Q6_K.gguf b/Llama-3-8B-StoryGenerator.i1-Q6_K.gguf new file mode 100644 index 0000000..d38fab8 --- /dev/null +++ b/Llama-3-8B-StoryGenerator.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9cb20f3d41e3fb6e18101d031657a3965ebe082be6cacc1fa0e5b70e00ada94 +size 6596007680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..539f267 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: HaitameLaframe/Llama-3-8B-StoryGenerator +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/HaitameLaframe/Llama-3-8B-StoryGenerator + + +static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-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-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-StoryGenerator-i1-GGUF/resolve/main/Llama-3-8B-StoryGenerator.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..461c4ba --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6379a7fe7facdd8a0b6b81fb974ef4c1994fd4a939ebbef34b2eb4531b5b9083 +size 4988157