commit f27ced44cf7ad1e56fc9e9b29c3c5d90c6a98660 Author: ModelHub XC Date: Wed Sep 2 16:20:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/AlchemistCoder-L-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..27454d4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,54 @@ +*.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 +AlchemistCoder-L-7B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B-f32.gguf filter=lfs diff=lfs merge=lfs -text +AlchemistCoder-L-7B.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/AlchemistCoder-L-7B-IQ2_M.gguf b/AlchemistCoder-L-7B-IQ2_M.gguf new file mode 100644 index 0000000..a7a2eda --- /dev/null +++ b/AlchemistCoder-L-7B-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e648467818cd3f04370086094919576fd620c5696a082649bdeef96ac1b66346 +size 2359750816 diff --git a/AlchemistCoder-L-7B-IQ2_S.gguf b/AlchemistCoder-L-7B-IQ2_S.gguf new file mode 100644 index 0000000..d652eaa --- /dev/null +++ b/AlchemistCoder-L-7B-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22dd83ac782f4837b82644d102dc232fc6aa60d4a5f7989d87fc9338a79a7802 +size 2196566176 diff --git a/AlchemistCoder-L-7B-IQ2_XS.gguf b/AlchemistCoder-L-7B-IQ2_XS.gguf new file mode 100644 index 0000000..6b3c123 --- /dev/null +++ b/AlchemistCoder-L-7B-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992f99f9d2113b3c722ae98f4fca0545bbd2cf487b6b79633233b9d7e861aa25 +size 2034913440 diff --git a/AlchemistCoder-L-7B-IQ3_M.gguf b/AlchemistCoder-L-7B-IQ3_M.gguf new file mode 100644 index 0000000..cfb9947 --- /dev/null +++ b/AlchemistCoder-L-7B-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33cc641e04f7e12d5812721966df1111f848453a2632ce94360509fd854cd299 +size 3114864800 diff --git a/AlchemistCoder-L-7B-IQ3_XS.gguf b/AlchemistCoder-L-7B-IQ3_XS.gguf new file mode 100644 index 0000000..629f048 --- /dev/null +++ b/AlchemistCoder-L-7B-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d842aa12d169553ee19e726fe006ae38e43effdb668f41802fe464e642257656 +size 2796523680 diff --git a/AlchemistCoder-L-7B-IQ3_XXS.gguf b/AlchemistCoder-L-7B-IQ3_XXS.gguf new file mode 100644 index 0000000..cace3b7 --- /dev/null +++ b/AlchemistCoder-L-7B-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a86b27f217d9727eff2f50aae83c9cc9f99f6d3d145f5a75e2f28bed9d2a1948 +size 2585391264 diff --git a/AlchemistCoder-L-7B-IQ4_XS.gguf b/AlchemistCoder-L-7B-IQ4_XS.gguf new file mode 100644 index 0000000..a5fcdad --- /dev/null +++ b/AlchemistCoder-L-7B-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc24251eddd5cc94f9fe081b9797a137415c18518e4dbfe6fa35968b986147ec +size 3619336352 diff --git a/AlchemistCoder-L-7B-Q2_K.gguf b/AlchemistCoder-L-7B-Q2_K.gguf new file mode 100644 index 0000000..c9455ee --- /dev/null +++ b/AlchemistCoder-L-7B-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296bab39b94c3b95da9cd7d3df61579761fe3439dc06719ced60f3826b06ae97 +size 2532864160 diff --git a/AlchemistCoder-L-7B-Q3_K_L.gguf b/AlchemistCoder-L-7B-Q3_K_L.gguf new file mode 100644 index 0000000..d8f326f --- /dev/null +++ b/AlchemistCoder-L-7B-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a27fd8457ae8b2eae8eb3fc31d2dea310e08a05aa2a2ad48629d1d7332689e +size 3597111456 diff --git a/AlchemistCoder-L-7B-Q3_K_M.gguf b/AlchemistCoder-L-7B-Q3_K_M.gguf new file mode 100644 index 0000000..710f3c4 --- /dev/null +++ b/AlchemistCoder-L-7B-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e24fc67f52f680e0d6db10328c0665e22dd17cbae9443d7c82d00453d551ebfb +size 3298005152 diff --git a/AlchemistCoder-L-7B-Q3_K_S.gguf b/AlchemistCoder-L-7B-Q3_K_S.gguf new file mode 100644 index 0000000..cb5bf4e --- /dev/null +++ b/AlchemistCoder-L-7B-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40df7afae7674b338195185d82592691f360bcf3c1f19ca5826f566dad84670 +size 2948305056 diff --git a/AlchemistCoder-L-7B-Q4_K_M.gguf b/AlchemistCoder-L-7B-Q4_K_M.gguf new file mode 100644 index 0000000..c96e8fc --- /dev/null +++ b/AlchemistCoder-L-7B-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23beed9b49245f8beecb99d740a36b32e1f01dbe5db15a15950754d06e94b075 +size 4081004704 diff --git a/AlchemistCoder-L-7B-Q4_K_S.gguf b/AlchemistCoder-L-7B-Q4_K_S.gguf new file mode 100644 index 0000000..a815886 --- /dev/null +++ b/AlchemistCoder-L-7B-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7e399cef83bbd9e933356e29c5d49adb099edd6e52110c834663a428218823 +size 3856740512 diff --git a/AlchemistCoder-L-7B-Q5_K_M.gguf b/AlchemistCoder-L-7B-Q5_K_M.gguf new file mode 100644 index 0000000..423ede4 --- /dev/null +++ b/AlchemistCoder-L-7B-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44bae87dfeff51ea39c72401b4acaddc16e68d78e740851e88157dbb1558a66c +size 4783157408 diff --git a/AlchemistCoder-L-7B-Q5_K_S.gguf b/AlchemistCoder-L-7B-Q5_K_S.gguf new file mode 100644 index 0000000..1ada20f --- /dev/null +++ b/AlchemistCoder-L-7B-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630b31ec7e7ca2fa515653d61eeee258d3bbc4d9b46a15abd3366509db774534 +size 4651692192 diff --git a/AlchemistCoder-L-7B-Q6_K.gguf b/AlchemistCoder-L-7B-Q6_K.gguf new file mode 100644 index 0000000..68234fe --- /dev/null +++ b/AlchemistCoder-L-7B-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666647b0af8b3fa03de960bbb906b9e2243fe6d329251050b076e8abd7ce877d +size 5529194656 diff --git a/AlchemistCoder-L-7B-Q8_0.gguf b/AlchemistCoder-L-7B-Q8_0.gguf new file mode 100644 index 0000000..afc1123 --- /dev/null +++ b/AlchemistCoder-L-7B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0f6657818009ee3bec283ee246893a3863ac4ea2f004cec76d0e817c7a0d156 +size 7161090208 diff --git a/AlchemistCoder-L-7B-f32.gguf b/AlchemistCoder-L-7B-f32.gguf new file mode 100644 index 0000000..ea71113 --- /dev/null +++ b/AlchemistCoder-L-7B-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac7775a86e9f2e768d8e9f3b6ce3b7d563a86dacf2259fb9638a375141af1de +size 26954403712 diff --git a/AlchemistCoder-L-7B.imatrix b/AlchemistCoder-L-7B.imatrix new file mode 100644 index 0000000..7c58d00 --- /dev/null +++ b/AlchemistCoder-L-7B.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9aaaf639f9af4c23f3c927647bd74ba7528e595c75f96388898c946c0ff4a5 +size 4562187 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de495b9 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +license: apache-2.0 +tags: +- code generation +quantized_by: bartowski +pipeline_tag: text-generation +--- + +## Llamacpp imatrix Quantizations of AlchemistCoder-L-7B + +Using llama.cpp release b3024 for quantization. + +Original model: https://huggingface.co/internlm/AlchemistCoder-L-7B + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +## Prompt format + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` + [INST] <> +{system_prompt} +<> + +{prompt} [/INST] +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Description | +| -------- | ---------- | --------- | ----------- | +| [AlchemistCoder-L-7B-Q8_0.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q8_0.gguf) | Q8_0 | 7.16GB | Extremely high quality, generally unneeded but max available quant. | +| [AlchemistCoder-L-7B-Q6_K.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q6_K.gguf) | Q6_K | 5.53GB | High quality, *recommended*. | +| [AlchemistCoder-L-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q5_K_M.gguf) | Q5_K_M | 4.78GB | High quality, *recommended*. | +| [AlchemistCoder-L-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q5_K_S.gguf) | Q5_K_S | 4.65GB | High quality, *recommended*. | +| [AlchemistCoder-L-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q4_K_M.gguf) | Q4_K_M | 4.08GB | High quality, *recommended*. | +| [AlchemistCoder-L-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q4_K_S.gguf) | Q4_K_S | 3.86GB | Good quality, uses about 4.83 bits per weight, *recommended*. | +| [AlchemistCoder-L-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ4_XS.gguf) | IQ4_XS | 3.61GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [AlchemistCoder-L-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_M.gguf) | Q3_K_M | 3.29GB | Even lower quality. | +| [AlchemistCoder-L-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_M.gguf) | Q3_K_M | 3.29GB | Even lower quality. | +| [AlchemistCoder-L-7B-IQ3_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_M.gguf) | IQ3_M | 3.11GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [AlchemistCoder-L-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_S.gguf) | Q3_K_S | 2.94GB | Low quality, not recommended. | +| [AlchemistCoder-L-7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_XXS.gguf) | IQ3_XXS | 2.58GB | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [AlchemistCoder-L-7B-Q2_K.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q2_K.gguf) | Q2_K | 2.53GB | Very low quality but surprisingly usable. | + +## Downloading using huggingface-cli + +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/AlchemistCoder-L-7B-GGUF --include "AlchemistCoder-L-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/AlchemistCoder-L-7B-GGUF --include "AlchemistCoder-L-7B-Q8_0.gguf/*" --local-dir AlchemistCoder-L-7B-Q8_0 +``` + +You can either specify a new local-dir (AlchemistCoder-L-7B-Q8_0) or download them all in place (./) + +## Which file should I choose? + +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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. + +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