commit 35c97a3f285015b2827c7455302b651ed999bd2f Author: ModelHub XC Date: Sat Sep 26 09:48:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/FuseChat-7B-v2.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b53e581 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +FuseChat-7B-v2.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +FuseChat-7B-v2.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FuseChat-7B-v2.0.i1-IQ1_M.gguf b/FuseChat-7B-v2.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..bc295b6 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8528919d1a5994a84c013e92c3032d9bfda43538cfc982921869d3dae1e3ecc2 +size 1754455584 diff --git a/FuseChat-7B-v2.0.i1-IQ1_S.gguf b/FuseChat-7B-v2.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..cc0eb75 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6191d2ad63c6d30dd4ae50702a2d35bfd5cff29ca96e4000ea87094dffe620 +size 1612111392 diff --git a/FuseChat-7B-v2.0.i1-IQ2_M.gguf b/FuseChat-7B-v2.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..a62b0a7 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ff99fd538af2541c80c66deb0f3a0401c5313be5a8cc273b50c24a9f9face0 +size 2500723040 diff --git a/FuseChat-7B-v2.0.i1-IQ2_S.gguf b/FuseChat-7B-v2.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..cd710fc --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41dc9667e1d34cbf52759f1bde3bea66f0ef26e80484bcdb1bb0521492e1794 +size 2310930784 diff --git a/FuseChat-7B-v2.0.i1-IQ2_XS.gguf b/FuseChat-7B-v2.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d6286b4 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c9387eb658b490132b0d3851cf30af1332fd8f97416d079262e0a8ae24e86e +size 2198265376 diff --git a/FuseChat-7B-v2.0.i1-IQ2_XXS.gguf b/FuseChat-7B-v2.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..20c7a17 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c6664ffa7f7211c25b6f84dddf0a6a27238152249505cd1a86d1d1baa6cfa6 +size 1991695904 diff --git a/FuseChat-7B-v2.0.i1-IQ3_M.gguf b/FuseChat-7B-v2.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..e982033 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26714f07b28b473bd596c0aa97c422fc3268bcf72e2a266ffb4c554997080af5 +size 3284903328 diff --git a/FuseChat-7B-v2.0.i1-IQ3_S.gguf b/FuseChat-7B-v2.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..02cd75d --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010b561a980db26c9f2cc403b550813f8a0167d56b2fb90a8e5753f9f3eccd9d +size 3182405024 diff --git a/FuseChat-7B-v2.0.i1-IQ3_XS.gguf b/FuseChat-7B-v2.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..51fcc93 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a05f517fdd32f94c147cfb2611f13e1cc8308821c8fd66bb869fa3038b986612 +size 3018827168 diff --git a/FuseChat-7B-v2.0.i1-IQ3_XXS.gguf b/FuseChat-7B-v2.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..94fd5e9 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f4905425d2fce3365da9bb7f2b8cac4965ee2b868b61f3a57a782d847433fe +size 2827354464 diff --git a/FuseChat-7B-v2.0.i1-IQ4_XS.gguf b/FuseChat-7B-v2.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..715b9b8 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d838a283cab234f4b8b29f5aa3efc940e33a202f3d2379f30b33bd97be2b268 +size 3907700960 diff --git a/FuseChat-7B-v2.0.i1-Q2_K.gguf b/FuseChat-7B-v2.0.i1-Q2_K.gguf new file mode 100644 index 0000000..21c6335 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90c9d834beda71c3d97ebb007d656e68f4666aa7834ac11831d850304d6a926a +size 2719253088 diff --git a/FuseChat-7B-v2.0.i1-Q3_K_L.gguf b/FuseChat-7B-v2.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..108572f --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86bdd6f76232926f9881d239cce27c27612dd7c8dc5292e9c977ca077c7831e7 +size 3822036384 diff --git a/FuseChat-7B-v2.0.i1-Q3_K_M.gguf b/FuseChat-7B-v2.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1ebc719 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96cc5272b3f50de62e81e70a24eacae94ff4ebfdea8c7158ac3de819d9de37f4 +size 3518997920 diff --git a/FuseChat-7B-v2.0.i1-Q3_K_S.gguf b/FuseChat-7B-v2.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..0285d63 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24afbb76eccc52b50fcefc3409240bd9dbfab2706ff00c1d4cb9a1f0c5c1f567 +size 3164579232 diff --git a/FuseChat-7B-v2.0.i1-Q4_0.gguf b/FuseChat-7B-v2.0.i1-Q4_0.gguf new file mode 100644 index 0000000..59d76d2 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04ce18fd6fff210151836c91b82e25a2ebd1ae8d27663c71ba200248042985e +size 4123609568 diff --git a/FuseChat-7B-v2.0.i1-Q4_K_M.gguf b/FuseChat-7B-v2.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..c677981 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155684726cd12ea42077554ec08e9a0942e84b938d5d50e52bdb431d6cff5b4d +size 4368452064 diff --git a/FuseChat-7B-v2.0.i1-Q4_K_S.gguf b/FuseChat-7B-v2.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..fa4457f --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984a3551ed4c28f9cd90798a32ffd87e505169edbba44501a5ee9bc138944a6c +size 4140386784 diff --git a/FuseChat-7B-v2.0.i1-Q5_K_M.gguf b/FuseChat-7B-v2.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..31555dc --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ebc762d1a6e8de1857c238b5f22d3bd3428adc835ad55cae77304fc86e9a24 +size 5131423200 diff --git a/FuseChat-7B-v2.0.i1-Q5_K_S.gguf b/FuseChat-7B-v2.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..58960f3 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:546855423ddaa95cbf826a4d0796f6cdf18c9be4fcd7b27389c77557b7e7daf4 +size 4997729760 diff --git a/FuseChat-7B-v2.0.i1-Q6_K.gguf b/FuseChat-7B-v2.0.i1-Q6_K.gguf new file mode 100644 index 0000000..6ffc495 --- /dev/null +++ b/FuseChat-7B-v2.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5bf54f5f6685b96afc36e4a65a11426fea04f58b4616176b5d3f638ecdd5f69 +size 5942080032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a35cb18 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: FuseAI/FuseChat-7B-v2.0 +datasets: +- FuseAI/FuseChat-Mixture +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- model-fusion +- fusechat +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/FuseAI/FuseChat-7B-v2.0 + + +static quants are available at https://huggingface.co/mradermacher/FuseChat-7B-v2.0-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/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/FuseChat-7B-v2.0-i1-GGUF/resolve/main/FuseChat-7B-v2.0.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | 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..f72136d --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdbd1c81882fef99c27f55766308261ab2e34f36ec164532605f8c71747ce0a +size 4988157