commit 347560f01d8297733017a467b629c9d2a2c7693e Author: ModelHub XC Date: Mon May 25 00:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ChiseLLM-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4b1b6e4 --- /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 +*.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 +ChiseLLM-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ChiseLLM-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ChiseLLM-7B.IQ4_XS.gguf b/ChiseLLM-7B.IQ4_XS.gguf new file mode 100644 index 0000000..037df40 --- /dev/null +++ b/ChiseLLM-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3d273e74ab00a34a9cb219d6f4c8409b1997b81d3b18dbe993f4b10da8ffbfd +size 4250298656 diff --git a/ChiseLLM-7B.Q2_K.gguf b/ChiseLLM-7B.Q2_K.gguf new file mode 100644 index 0000000..b8d8ba2 --- /dev/null +++ b/ChiseLLM-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100520a08e39fc3e696dec64b3368505167d4762b000d77e6c754e01dc5465fd +size 3015940384 diff --git a/ChiseLLM-7B.Q3_K_L.gguf b/ChiseLLM-7B.Q3_K_L.gguf new file mode 100644 index 0000000..463fc47 --- /dev/null +++ b/ChiseLLM-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56a30e32368c385f15c6c7d9a7967a9f1bec97880ab87f0a5eca1dfa5bbde9e1 +size 4088459552 diff --git a/ChiseLLM-7B.Q3_K_M.gguf b/ChiseLLM-7B.Q3_K_M.gguf new file mode 100644 index 0000000..f923c7c --- /dev/null +++ b/ChiseLLM-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8992ee0a64ea10cee8ac8c9ab6b90df3f047c5e6129cc44e8df3cc097285d7c +size 3808391456 diff --git a/ChiseLLM-7B.Q3_K_S.gguf b/ChiseLLM-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c8721a3 --- /dev/null +++ b/ChiseLLM-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04f8d9c84ec7f39eeda29c76c78c0f2c172927430945918aab5de433db9623b +size 3492368672 diff --git a/ChiseLLM-7B.Q4_K_M.gguf b/ChiseLLM-7B.Q4_K_M.gguf new file mode 100644 index 0000000..8be1699 --- /dev/null +++ b/ChiseLLM-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0c7e946bf7928b6ef2ff3e49b0106bbce3919a152a590b317b8bfc6a356271 +size 4683073824 diff --git a/ChiseLLM-7B.Q4_K_S.gguf b/ChiseLLM-7B.Q4_K_S.gguf new file mode 100644 index 0000000..204fae2 --- /dev/null +++ b/ChiseLLM-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7338b04644f19d2021f4ade0cb507f3d24f79392c6e628b92385895915ea1a +size 4457769248 diff --git a/ChiseLLM-7B.Q5_K_M.gguf b/ChiseLLM-7B.Q5_K_M.gguf new file mode 100644 index 0000000..3c33e39 --- /dev/null +++ b/ChiseLLM-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13cdcb826d429c4d2c4586e51dc8dc257f26a3cdd743ab653f1877ca1a978905 +size 5444831520 diff --git a/ChiseLLM-7B.Q5_K_S.gguf b/ChiseLLM-7B.Q5_K_S.gguf new file mode 100644 index 0000000..3aacc8c --- /dev/null +++ b/ChiseLLM-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d72e893a03443491429fda111298254a55da958519c4dc13de1f9d9e55250b9 +size 5315176736 diff --git a/ChiseLLM-7B.Q6_K.gguf b/ChiseLLM-7B.Q6_K.gguf new file mode 100644 index 0000000..142dd0d --- /dev/null +++ b/ChiseLLM-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba59ec6d300c4ee6a6a9a5ba779ab97abe4ecd90f5be5702bec67ff278c9cb00 +size 6254199072 diff --git a/ChiseLLM-7B.Q8_0.gguf b/ChiseLLM-7B.Q8_0.gguf new file mode 100644 index 0000000..fe6bcb8 --- /dev/null +++ b/ChiseLLM-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753061214ae5055c8b228048e5baf097739aa930b3d7720fdcbc55c698af5f9b +size 8098525472 diff --git a/ChiseLLM-7B.f16.gguf b/ChiseLLM-7B.f16.gguf new file mode 100644 index 0000000..ad48995 --- /dev/null +++ b/ChiseLLM-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d019ea347371588e1fe11c2e6db724b0beff36cb03ef817af6bfdcf461b1eec7 +size 15237853472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5b16fca --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: observerw/ChiseLLM-7B +datasets: +- observerw/ChiseLLM-Completion +- observerw/ChiseLLM-Decompile +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/observerw/ChiseLLM-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ChiseLLM-7B-i1-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/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ChiseLLM-7B-GGUF/resolve/main/ChiseLLM-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill | + +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. + +