commit e565de4c5874284cd546d91f7cdca1ef5ffc99fa Author: ModelHub XC Date: Wed Apr 22 10:24:54 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88812b0 --- /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 +Colossal-LLaMA-2-13b-base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Colossal-LLaMA-2-13b-base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ1_M.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ1_M.gguf new file mode 100644 index 0000000..27bac06 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb9344fb3a5ec4fe0017e57154d9c925bdb92b0a10c4585bde3d83cf717ed9c4 +size 3332363104 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ1_S.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ1_S.gguf new file mode 100644 index 0000000..ee2064e --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b185ed686924ef9933e68a083ec230a0841cf7f264fd1a22150cc9f6576fe0 +size 3092439904 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ2_M.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ2_M.gguf new file mode 100644 index 0000000..668b36d --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19f5a45edcf793c2f0b4885a36f6c60a011d12f6e339749a91fa865cda1f28a +size 4730626784 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ2_S.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ2_S.gguf new file mode 100644 index 0000000..fccca52 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5006f1f1540aa85c0f8fa10dfe43fbbf68bf35b512be8139a07bc78bfcd80550 +size 4410729184 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ2_XS.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..ba838f5 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afebfbaa29559836cec7a9caba8d4a8dbddba62df9ff96329586caba9067ba45 +size 4084900704 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ2_XXS.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..390b807 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada82e91f51c292e94ef73459cf99c9fd83d92c36f078c36866c026660a05c92 +size 3732235104 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ3_M.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ3_M.gguf new file mode 100644 index 0000000..878b28f --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dbe9b2f0985042e0566aea921acbee38e1229073bfd74a8594665e1cc63fa4f +size 6222788704 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ3_S.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ3_S.gguf new file mode 100644 index 0000000..b8e65af --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983962f9f1b4e99a850fe4c28056731ec4b212882e77ab740f39833405b72c73 +size 5897259104 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ3_XS.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7041930 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53fe11386c76c49cfd6a15581fa368f7e88c33316562c092dc2414241db39d1a +size 5599889504 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ3_XXS.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..42f0129 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9a1abd65c672ab27ed21b250db74347ed86194e2fa854c16924828f92aafe1 +size 5173609184 diff --git a/Colossal-LLaMA-2-13b-base.i1-IQ4_XS.gguf b/Colossal-LLaMA-2-13b-base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..46cc052 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c4e97ede4c9c307870745a7dcdaee0ad633e284eedcd22b79394fb2acbc02a6 +size 7221794784 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q2_K.gguf b/Colossal-LLaMA-2-13b-base.i1-Q2_K.gguf new file mode 100644 index 0000000..b66f3dc --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2720baf16c5b9b396f8f85b3c9ea9286f37cd92f5c0fcd6e38c2378b3bac41fc +size 5073254624 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q3_K_L.gguf b/Colossal-LLaMA-2-13b-base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..2b98161 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc9d5682be4989d21da7afe85a93d272d6d7267e896c61e16727a34b66a5343 +size 7167838304 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q3_K_M.gguf b/Colossal-LLaMA-2-13b-base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d1d8946 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb1b1d5a105be076a613fda686021b78bcd835414569dbe9c2a2bb1493c7447 +size 6576048224 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q3_K_S.gguf b/Colossal-LLaMA-2-13b-base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..401940b --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75821762fdc7d2d99add833fb8da8e499c01e4a299dad2bd5d5765862823bc51 +size 5897259104 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_0.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_0.gguf new file mode 100644 index 0000000..9dd28df --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6a694551c51c1cb16bb695f7ab821b33bf6417301bf9d50b7964b18ab15ab1 +size 7651462624 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_4.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..dfffb00 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f69c7d8407307daccbe68b7c25db0f09f734c577eaaa474d352c50cf6edce6b +size 7629344224 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_8.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..1b74b3e --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93272a864f859b4bfbaae1c876889048cd0a724609f360e3928de711c2600810 +size 7629344224 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_0_8_8.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..19480cb --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b781e622c36d994b1473c2be8c0a5957b184e063cb47c44b9db0f76e7f3cc0e +size 7629344224 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_K_M.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e49c34a --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8694d4d942c7aa38bc94e6cab10446edfb05a5e2a88f5e992957f78ec714865 +size 8129465824 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q4_K_S.gguf b/Colossal-LLaMA-2-13b-base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fdf0006 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fa3afe348b904b8a9c94c532563ce97ccf45133e623de86a114c04c4332ad0 +size 7686688224 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q5_K_M.gguf b/Colossal-LLaMA-2-13b-base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..53e5051 --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42192b95cf36ccd5fa059e8fa40707ed3340f3bf561b75d4ca579ff3d764da6b +size 9517180384 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q5_K_S.gguf b/Colossal-LLaMA-2-13b-base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c23a90e --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d8e13b245e9a7312925e7fb44db8c0ea63c80146e86fe455657cc5d53184d30 +size 9259541984 diff --git a/Colossal-LLaMA-2-13b-base.i1-Q6_K.gguf b/Colossal-LLaMA-2-13b-base.i1-Q6_K.gguf new file mode 100644 index 0000000..1ca2aeb --- /dev/null +++ b/Colossal-LLaMA-2-13b-base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c80a0eef44114bfe6b7799172518fca6707c9dfe123b421325df8400a17fb909 +size 10991627104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..09703a2 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: hpcai-tech/Colossal-LLaMA-2-13b-base +language: +- zh +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/hpcai-tech/Colossal-LLaMA-2-13b-base + + +static quants are available at https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-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/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ1_M.gguf) | i1-IQ1_M | 3.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ2_S.gguf) | i1-IQ2_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ2_M.gguf) | i1-IQ2_M | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q2_K.gguf) | i1-Q2_K | 5.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ3_S.gguf) | i1-IQ3_S | 6.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.0 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ3_M.gguf) | i1-IQ3_M | 6.3 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.7 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 7.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.3 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 7.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 7.7 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 7.7 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_0.gguf) | i1-Q4_0 | 7.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 8.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 9.4 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.6 | | +| [GGUF](https://huggingface.co/mradermacher/Colossal-LLaMA-2-13b-base-i1-GGUF/resolve/main/Colossal-LLaMA-2-13b-base.i1-Q6_K.gguf) | i1-Q6_K | 11.1 | 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..bbdb247 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f380ab27d7bc753ff4a056e8fdbdff327b2996df78ea5a2b4a017f156c9632f +size 7136325