commit 00c6f3cfee17057bf45184dd04ff8cedb5524dc6 Author: ModelHub XC Date: Tue Aug 11 15:37:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/PokeeAI_pokee_research_7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a975a77 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,73 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +PokeeAI_pokee_research_7b-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-bf16.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-imatrix.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +PokeeAI_pokee_research_7b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/PokeeAI_pokee_research_7b-IQ2_M.gguf b/PokeeAI_pokee_research_7b-IQ2_M.gguf new file mode 100644 index 0000000..1a9c433 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28fa10ae4eb8daed6074a65eb7fa0161e41f2768dd7bda2235dff66785a9137a +size 2780343072 diff --git a/PokeeAI_pokee_research_7b-IQ3_M.gguf b/PokeeAI_pokee_research_7b-IQ3_M.gguf new file mode 100644 index 0000000..00f3242 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9201566ca76ec516f9e37eb56f5db008fbe33dde20cec69bcb4cc0881e95a48f +size 3574012704 diff --git a/PokeeAI_pokee_research_7b-IQ3_XS.gguf b/PokeeAI_pokee_research_7b-IQ3_XS.gguf new file mode 100644 index 0000000..fcf5a65 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c4a65f9bb728cbdf8b4f7ff93d3c9489e52074a11263ac9774ebf5c8c4af9d +size 3346256672 diff --git a/PokeeAI_pokee_research_7b-IQ3_XXS.gguf b/PokeeAI_pokee_research_7b-IQ3_XXS.gguf new file mode 100644 index 0000000..f4a30b9 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b170bd31ae3cb6b917e20ccae012d92109bae6e31dd9988e8dc44688192919d8 +size 3114515232 diff --git a/PokeeAI_pokee_research_7b-IQ4_NL.gguf b/PokeeAI_pokee_research_7b-IQ4_NL.gguf new file mode 100644 index 0000000..7455a58 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a1381fcd40d246dbd25a51e80d6d7865274953057a61a82ec565173205963a +size 4437814048 diff --git a/PokeeAI_pokee_research_7b-IQ4_XS.gguf b/PokeeAI_pokee_research_7b-IQ4_XS.gguf new file mode 100644 index 0000000..e996608 --- /dev/null +++ b/PokeeAI_pokee_research_7b-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef196536118ef41c6ad680bd202d8926e98b7657c6616d0237eed97527565b4d +size 4218473248 diff --git a/PokeeAI_pokee_research_7b-Q2_K.gguf b/PokeeAI_pokee_research_7b-Q2_K.gguf new file mode 100644 index 0000000..24f6de0 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:832b9f19b76962468fa34cb672248088a2f8b2f21836d8690d7930f288ca1949 +size 3015940896 diff --git a/PokeeAI_pokee_research_7b-Q2_K_L.gguf b/PokeeAI_pokee_research_7b-Q2_K_L.gguf new file mode 100644 index 0000000..4620c7c --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57c5a51491c636c5db2d7b29898f06d0925da21399efdb081bc59b084f74997 +size 3548164896 diff --git a/PokeeAI_pokee_research_7b-Q3_K_L.gguf b/PokeeAI_pokee_research_7b-Q3_K_L.gguf new file mode 100644 index 0000000..c97b255 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8f0ba9feebac6715296dc1e5f279b233aee1a0630c643632743b3d956d8db2 +size 4088460064 diff --git a/PokeeAI_pokee_research_7b-Q3_K_M.gguf b/PokeeAI_pokee_research_7b-Q3_K_M.gguf new file mode 100644 index 0000000..ec518ad --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b837c33d20decac8a8fe39eec26ab36c75fafce639dab4bafcd0b53ea9f630b9 +size 3808391968 diff --git a/PokeeAI_pokee_research_7b-Q3_K_S.gguf b/PokeeAI_pokee_research_7b-Q3_K_S.gguf new file mode 100644 index 0000000..12a13e1 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9faddb0b833de8da9e3e3a73e0fcb9eb6be705f67ea3d03969ad0eab756f59f7 +size 3492369184 diff --git a/PokeeAI_pokee_research_7b-Q3_K_XL.gguf b/PokeeAI_pokee_research_7b-Q3_K_XL.gguf new file mode 100644 index 0000000..614483b --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad54d39a08dba49c6d780b44cf3cd3a56bb0e3d2c82b295e0452222fb8fd6436 +size 4565332768 diff --git a/PokeeAI_pokee_research_7b-Q4_0.gguf b/PokeeAI_pokee_research_7b-Q4_0.gguf new file mode 100644 index 0000000..bf565c4 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e62e4f3beadfd8cda0cbf055d43e9907061d147f721f4e4d125d42caa675b2 +size 4444121888 diff --git a/PokeeAI_pokee_research_7b-Q4_1.gguf b/PokeeAI_pokee_research_7b-Q4_1.gguf new file mode 100644 index 0000000..32396a1 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb86cbfb4915900d247bb32e1e4b0dbd39383aa2245d22dbc8ba48dbc55146c +size 4873284384 diff --git a/PokeeAI_pokee_research_7b-Q4_K_L.gguf b/PokeeAI_pokee_research_7b-Q4_K_L.gguf new file mode 100644 index 0000000..f3fdceb --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4424229a6ee678d8a9ae1262899eb554cfa1cd32c20dabeb9163f34ef8801129 +size 5087564576 diff --git a/PokeeAI_pokee_research_7b-Q4_K_M.gguf b/PokeeAI_pokee_research_7b-Q4_K_M.gguf new file mode 100644 index 0000000..554a917 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16c5c3aaa5e01e897431e4b6dfa15d7fcb69bcd71050716606ccb13eb5eb9c6 +size 4683074336 diff --git a/PokeeAI_pokee_research_7b-Q4_K_S.gguf b/PokeeAI_pokee_research_7b-Q4_K_S.gguf new file mode 100644 index 0000000..a8bacc6 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3d2675a077d2f97c8585111119047d08a7e86563b67e2836ce6907eba79e3b4 +size 4457769760 diff --git a/PokeeAI_pokee_research_7b-Q5_K_L.gguf b/PokeeAI_pokee_research_7b-Q5_K_L.gguf new file mode 100644 index 0000000..77330d4 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b54963e3120426af0ca78cb8deb5b0cdc497f0b92898aad09e029268ad9d7d +size 5781197600 diff --git a/PokeeAI_pokee_research_7b-Q5_K_M.gguf b/PokeeAI_pokee_research_7b-Q5_K_M.gguf new file mode 100644 index 0000000..703ee29 --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504b6d8d349b640d5721e50eb7ccd070a2647218eef07a7db8d0f548f382b64e +size 5444832032 diff --git a/PokeeAI_pokee_research_7b-Q5_K_S.gguf b/PokeeAI_pokee_research_7b-Q5_K_S.gguf new file mode 100644 index 0000000..c18321a --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9395de19603e0eec5f42912c35e9c61fbbcab139a78af31989d5c9352a902df2 +size 5315177248 diff --git a/PokeeAI_pokee_research_7b-Q6_K.gguf b/PokeeAI_pokee_research_7b-Q6_K.gguf new file mode 100644 index 0000000..5bd0ffb --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e4ebc622c63e6d913fa6a4b74fb897134d59cbd09d38bdbe6e0322360444200 +size 6254199584 diff --git a/PokeeAI_pokee_research_7b-Q6_K_L.gguf b/PokeeAI_pokee_research_7b-Q6_K_L.gguf new file mode 100644 index 0000000..00c64aa --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4ca180a75d718abd472c234f995f2d92d3a2e226169e8252872576a7707e18 +size 6518182688 diff --git a/PokeeAI_pokee_research_7b-Q8_0.gguf b/PokeeAI_pokee_research_7b-Q8_0.gguf new file mode 100644 index 0000000..e4e6b3e --- /dev/null +++ b/PokeeAI_pokee_research_7b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2225795965d37810b95ac57f58f33920a23b7ce0171030fc15ae6c247d212e +size 8098525984 diff --git a/PokeeAI_pokee_research_7b-bf16.gguf b/PokeeAI_pokee_research_7b-bf16.gguf new file mode 100644 index 0000000..fc6034b --- /dev/null +++ b/PokeeAI_pokee_research_7b-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23cfccba9f570f4b590dfae298399a8787bf66544ddee7b639f08b1d09365d95 +size 15237853696 diff --git a/PokeeAI_pokee_research_7b-imatrix.gguf b/PokeeAI_pokee_research_7b-imatrix.gguf new file mode 100644 index 0000000..818ce52 --- /dev/null +++ b/PokeeAI_pokee_research_7b-imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:516829bf25b33c8dc9e47dddadb5de10cb52527dcc3dfccd6dfee48754496639 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..85a090e --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model_relation: quantized +base_model: PokeeAI/pokee_research_7b +--- + +## Llamacpp imatrix Quantizations of pokee_research_7b by PokeeAI + +Using llama.cpp release b6818 for quantization. + +Original model: https://huggingface.co/PokeeAI/pokee_research_7b + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) combined with a subset of combined_all_small.parquet from Ed Addario [here](https://huggingface.co/datasets/eaddario/imatrix-calibration/blob/main/combined_all_small.parquet) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggml-org/llama.cpp), or any other llama.cpp based project + +## Prompt format + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [pokee_research_7b-bf16.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. | +| [pokee_research_7b-Q8_0.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. | +| [pokee_research_7b-Q6_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [pokee_research_7b-Q6_K.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. | +| [pokee_research_7b-Q5_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [pokee_research_7b-Q5_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. | +| [pokee_research_7b-Q5_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. | +| [pokee_research_7b-Q4_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [pokee_research_7b-Q4_1.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [pokee_research_7b-Q4_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [pokee_research_7b-Q3_K_XL.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [pokee_research_7b-Q4_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. | +| [pokee_research_7b-Q4_0.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [pokee_research_7b-IQ4_NL.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [pokee_research_7b-IQ4_XS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [pokee_research_7b-Q3_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. | +| [pokee_research_7b-Q3_K_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. | +| [pokee_research_7b-IQ3_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [pokee_research_7b-Q2_K_L.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [pokee_research_7b-Q3_K_S.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. | +| [pokee_research_7b-IQ3_XS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [pokee_research_7b-IQ3_XXS.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [pokee_research_7b-Q2_K.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. | +| [pokee_research_7b-IQ2_M.gguf](https://huggingface.co/bartowski/PokeeAI_pokee_research_7b-GGUF/blob/main/PokeeAI_pokee_research_7b-IQ2_M.gguf) | IQ2_M | 2.78GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/PokeeAI_pokee_research_7b-GGUF --include "PokeeAI_pokee_research_7b-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/PokeeAI_pokee_research_7b-GGUF --include "PokeeAI_pokee_research_7b-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (PokeeAI_pokee_research_7b-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggml-org/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggml-org/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggml-org/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggml-org/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file