commit c75a81ddd703aaf67cbfd27c0a6ea644a822a2a1 Author: ModelHub XC Date: Wed Sep 9 08:50:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +*.gguf* 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 \ No newline at end of file diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ2_M.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ2_M.gguf new file mode 100644 index 0000000..256ce6d --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586e2e8277a43a25f258241b365266b97cb4ba194b9123e12f6b79baf58e0d04 +size 2780340192 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_M.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_M.gguf new file mode 100644 index 0000000..8205299 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9cb69167c85ecb911f2f8d56f509fa3aa8ef76f8767d22f2ff1e891c06c405b +size 3574009824 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XS.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XS.gguf new file mode 100644 index 0000000..8a67c24 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6e4533b50e09d362974b5b4fb2f8f8d634b6ecd64465cb103f605fbdba25c5 +size 3346253792 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XXS.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XXS.gguf new file mode 100644 index 0000000..f528236 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5756b3f75a0091836fb1cd6c1acab5d397535eccba6cde0c0b7a617a0a5d703d +size 3114512352 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_NL.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_NL.gguf new file mode 100644 index 0000000..00c7499 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b979fc2d6445589970918d4ba1f877daece9e857e69493f97a719aa4c7b534e +size 4437811168 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_XS.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_XS.gguf new file mode 100644 index 0000000..8443681 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f3bf11572138bf796673a0b0284947e7233e954cbbfbb376be1f698bb90317e +size 4218470368 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K.gguf new file mode 100644 index 0000000..d3ebf3e --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa46b3d5bc70f15a945461bdfc3ee3d5cfae7bbbb40fb5f44b7425c3dc5d090c +size 3015938016 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K_L.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K_L.gguf new file mode 100644 index 0000000..d6ac6d2 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb54a61202401d02f6d856fce230343987aa95ea838f6b0a83bd7760ff724d8 +size 3548162016 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_L.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_L.gguf new file mode 100644 index 0000000..3cb3a16 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b324b19f16a4ad89f3bd9c52199e996823729476ad91af826b85e98c831a960d +size 4088457184 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_M.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_M.gguf new file mode 100644 index 0000000..69166e9 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2966f22ac16d6c2c3bfe0d092ccb11d0410626cd9ad8d16c8a4b9fedb8a78882 +size 3808389088 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_S.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_S.gguf new file mode 100644 index 0000000..522c923 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0cfda007cb4abaf7de62289437cd8015fa180dabf18726e318111b099d281c2 +size 3492366304 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_XL.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_XL.gguf new file mode 100644 index 0000000..255049b --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cc95f665f96c17c6999d0c6d3d8657576e257538295f6dcc6e5cf593529a2c7 +size 4565329888 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_0.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_0.gguf new file mode 100644 index 0000000..4c0af4a --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad638b4350d39b7e5693c91d8d45e593bd6cd7f568cd16795b82aa93493fceb7 +size 4444119008 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_1.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_1.gguf new file mode 100644 index 0000000..976ab6f --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc5a3c980149a81f9b8d59f823d7053b6799df2f2e3ccaf24ca721e6b55fda7 +size 4873281504 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_L.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_L.gguf new file mode 100644 index 0000000..ec44e74 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e438cb773c252d799dc915e1b6cf3a4830e3567ffd212f1b2f9047d4ef1c8f3 +size 5087561696 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_M.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_M.gguf new file mode 100644 index 0000000..778a724 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbda41c638c23a3e8e9fb33c27ca0d0a0ee044b6813941a0017fd46369a35ec5 +size 4683071456 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_S.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_S.gguf new file mode 100644 index 0000000..8a912c0 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0462463c14aabab887143a18cea149fd312d09b586aed526fb3e268c6ac5ad +size 4457766880 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_L.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_L.gguf new file mode 100644 index 0000000..036abe3 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f74437756ad278cd46ef5bfd667d715b4dfac1c76fe4db50bcb45bb056cf622 +size 5781194720 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_M.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_M.gguf new file mode 100644 index 0000000..2fc68ba --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d431709c498cc7ddc88f9757250d129d310f1214799b91d10ff4b3b231c3ea +size 5444829152 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_S.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_S.gguf new file mode 100644 index 0000000..843f2ff --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4422667879959b2740e946e85c062f4def862b7f147113224f22ce3bb4dc15c +size 5315174368 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K.gguf new file mode 100644 index 0000000..47d1dc5 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8dc77eb83563fa17f073bfabe77521dda2f31745f065e31b33e3845cea56f1e +size 6254196704 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K_L.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K_L.gguf new file mode 100644 index 0000000..12e4eec --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c036e0ee08108432ba8af87400dea9831045515276024bd742d3c41dab369257 +size 6518179808 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q8_0.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q8_0.gguf new file mode 100644 index 0000000..92d2ba4 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c97242cfa89a64dd6d70ac64838d892b751ed6a97abff39b33a330c0fd8fca +size 8098523104 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B-bf16.gguf b/ChaoticNeutrals_Very_Berry_Qwen2_7B-bf16.gguf new file mode 100644 index 0000000..3ed52f2 --- /dev/null +++ b/ChaoticNeutrals_Very_Berry_Qwen2_7B-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af7726ed89a87d4724fbec7ed350bfe593c4692d2d54fe814c6606215aae704 +size 15237850816 diff --git a/ChaoticNeutrals_Very_Berry_Qwen2_7B.imatrix b/ChaoticNeutrals_Very_Berry_Qwen2_7B.imatrix new file mode 100644 index 0000000..5cff903 Binary files /dev/null and b/ChaoticNeutrals_Very_Berry_Qwen2_7B.imatrix differ diff --git a/README.md b/README.md new file mode 100644 index 0000000..f907a3e --- /dev/null +++ b/README.md @@ -0,0 +1,173 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +tags: +- not-for-all-audiences +base_model_relation: quantized +base_model: ChaoticNeutrals/Very_Berry_Qwen2_7B +license: apache-2.0 +--- + +## Llamacpp imatrix Quantizations of Very_Berry_Qwen2_7B by ChaoticNeutrals + +Using llama.cpp release b4978 for quantization. + +Original model: https://huggingface.co/ChaoticNeutrals/Very_Berry_Qwen2_7B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|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 | +| -------- | ---------- | --------- | ----- | ----------- | +| [Very_Berry_Qwen2_7B-bf16.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. | +| [Very_Berry_Qwen2_7B-Q8_0.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Very_Berry_Qwen2_7B-Q6_K_L.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_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*. | +| [Very_Berry_Qwen2_7B-Q6_K.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. | +| [Very_Berry_Qwen2_7B-Q5_K_L.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Very_Berry_Qwen2_7B-Q5_K_M.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. | +| [Very_Berry_Qwen2_7B-Q5_K_S.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. | +| [Very_Berry_Qwen2_7B-Q4_K_L.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Very_Berry_Qwen2_7B-Q4_1.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_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. | +| [Very_Berry_Qwen2_7B-Q4_K_M.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. | +| [Very_Berry_Qwen2_7B-Q3_K_XL.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_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. | +| [Very_Berry_Qwen2_7B-Q4_K_S.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Very_Berry_Qwen2_7B-Q4_0.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Very_Berry_Qwen2_7B-IQ4_NL.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Very_Berry_Qwen2_7B-IQ4_XS.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Very_Berry_Qwen2_7B-Q3_K_L.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. | +| [Very_Berry_Qwen2_7B-Q3_K_M.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. | +| [Very_Berry_Qwen2_7B-IQ3_M.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Very_Berry_Qwen2_7B-Q2_K_L.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_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. | +| [Very_Berry_Qwen2_7B-Q3_K_S.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. | +| [Very_Berry_Qwen2_7B-IQ3_XS.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Very_Berry_Qwen2_7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Very_Berry_Qwen2_7B-Q2_K.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_7B-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. | +| [Very_Berry_Qwen2_7B-IQ2_M.gguf](https://huggingface.co/bartowski/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF/blob/main/ChaoticNeutrals_Very_Berry_Qwen2_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/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF --include "ChaoticNeutrals_Very_Berry_Qwen2_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/ChaoticNeutrals_Very_Berry_Qwen2_7B-GGUF --include "ChaoticNeutrals_Very_Berry_Qwen2_7B-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (ChaoticNeutrals_Very_Berry_Qwen2_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/ggerganov/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/ggerganov/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/ggerganov/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/ggerganov/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