commit 1e97dbb00872e9d5b63b241d76e2f971f03208ef Author: ModelHub XC Date: Mon May 4 17:42:34 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..684a3a4 --- /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 +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_M.gguf new file mode 100644 index 0000000..ea7903d --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9bd7f952fc48b4c174cb2d51b59119ac36255c3859c1f9aeef6385e5698caf +size 2161977568 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_S.gguf new file mode 100644 index 0000000..a3ca7d2 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a220d4b2c9d34d2f580788af9a0fdf4a2fcc91f201b231d5ba13d71b09a66c1 +size 2019633376 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_M.gguf new file mode 100644 index 0000000..ca22d46 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de9820f711e197050d3d9a678e588f50631330684fce31e1cd7c470674205d78 +size 2948286688 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_S.gguf new file mode 100644 index 0000000..e65efe8 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa5501364242890e5ff55e059ba7544024638981bef50a1134674afc9e4a4f8 +size 2758494432 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XS.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8fadda4 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a07ba9189f4c9396cffd6633a52e946f845ab4aa62cd236fe73457749c9ea47 +size 2605787360 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XXS.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..4ce6581 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61439283f665a74250f86d6adb6ffa9018ae041e9fe4fb4241c4c735b8035a1 +size 2399217888 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_M.gguf new file mode 100644 index 0000000..b5c59c7 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abc8a78a0ce3d0e6a4e55c0f89594f740309e1b1b57f3f19b49d4bcd175ea5cb +size 3784829152 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_S.gguf new file mode 100644 index 0000000..d1d311b --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1698d36036a58f78cb0f7b1ca5d0c705b58d5255ec4aa3272dcf22331c6d8543 +size 3682330848 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XS.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0f0b42f --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3031c7bed776dc651ce02e012dc1d021b9d074da0bce2160ad7255d6451a1e +size 3518752992 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XXS.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..e05d1f9 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f347d746c501484b99b8d512130afcdae2011b42176a3662b711135cbf71b07a +size 3274918112 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ4_XS.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ4_XS.gguf new file mode 100644 index 0000000..31f191d --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5d5025e7f0980d894db1ff3593103bc090a68cb5ced9d7d671df3b591d03bf +size 4447668448 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q2_K.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q2_K.gguf new file mode 100644 index 0000000..fec789d --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:365f9d2184cf86a6f97fef57c950909f440e5d6301d4063c74491459f2bc39e9 +size 3179137248 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_L.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_L.gguf new file mode 100644 index 0000000..1fdb771 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442b5161daf3b32c9a264cff5d6de79515acf73cf855271d4537c62c9e24ebd1 +size 4321962208 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_M.gguf new file mode 100644 index 0000000..14a1d59 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d291b1b636556e40193e98c759e57cd914496bb6f313b41be08f46100fbcb02 +size 4018923744 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_S.gguf new file mode 100644 index 0000000..14b6032 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24657d719dda16f61d8c4a9bd724b4e70f3fac56677310b657f9eb149aa56087 +size 3664505056 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0.gguf new file mode 100644 index 0000000..7dac1c6 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c5e2722dd47544fbd51033f69d2cb97f4597163eab96b6f90351a716c2b0f9c +size 4675897568 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_4.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..bb191ee --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9250386b29f5525836b33ae1625b17d542dd76002f291fb3619c1078f495b0 +size 4661217504 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_8.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..e1461eb --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245e998d1f4bed665ed8ba1baa5b679ab3a9b7f23e9e461628a98cc4e1ef6a37 +size 4661217504 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_8_8.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..939ae96 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9eccfc41fb82b110ad5989609b54114efd998fc679fe21b76748c1eeb4b041c +size 4661217504 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_M.gguf new file mode 100644 index 0000000..4462eb3 --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55554135f0a0cdeb213305f52adf345c51e1b94f71f1776919749bacaf2b7c10 +size 4920740064 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0b976ea --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f5590fccb9e8ee5454c20b688297e4fe67faf1c2b8f71f90fd608c1c57e3d7e +size 4692674784 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_M.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_M.gguf new file mode 100644 index 0000000..4bafd9a --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:372e42f159a5b2bf3a697449122d227bea0d8f8ecb7b8512d622c15b36fc50f0 +size 5732993248 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_S.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_S.gguf new file mode 100644 index 0000000..abd16ae --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78edd566a772e44be999c81d283d55769a07d9655bdab1a2667a2db3296e141 +size 5599299808 diff --git a/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q6_K.gguf b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q6_K.gguf new file mode 100644 index 0000000..3e07d6f --- /dev/null +++ b/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4051f456bddaa12449d14b0faf521021a212c2bd662ca32475039a5bea1694ce +size 6596012256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3af2d8f --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: EpistemeAI2/Fireball-Alpaca-Llama3.1.06-8B-Philos +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/EpistemeAI2/Fireball-Alpaca-Llama3.1.06-8B-Philos + + +static quants are available at https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-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/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Fireball-Alpaca-Llama3.1.06-8B-Philos-i1-GGUF/resolve/main/Fireball-Alpaca-Llama3.1.06-8B-Philos.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..9046247 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b43a867302a573917163998efbe9b06980f44f8f8bfc85886865128cfe52c6f +size 4988157