commit 6861a2dcbba3fcc949d8de4490a6338f460434f5 Author: ModelHub XC Date: Wed Jun 17 15:38:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/internlm2_5-7b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c75921e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +internlm2_5-7b-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +internlm2_5-7b-chat.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..912f0a7 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: internlm/internlm2_5-7b-chat +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/internlm/internlm2_5-7b-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/internlm2_5-7b-chat-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/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q5_K_M.gguf) | Q5_K_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q6_K.gguf) | Q6_K | 6.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.Q8_0.gguf) | Q8_0 | 8.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/internlm2_5-7b-chat-GGUF/resolve/main/internlm2_5-7b-chat.f16.gguf) | f16 | 15.6 | 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. + + diff --git a/internlm2_5-7b-chat.IQ4_XS.gguf b/internlm2_5-7b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..c0a7315 --- /dev/null +++ b/internlm2_5-7b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c15245b7f7f7f2870131ad2f5d823b3b15f31a574c39a989a1f44173320ace +size 4280968736 diff --git a/internlm2_5-7b-chat.Q2_K.gguf b/internlm2_5-7b-chat.Q2_K.gguf new file mode 100644 index 0000000..0459ae8 --- /dev/null +++ b/internlm2_5-7b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccf41a7efcf8970fb7706f390fa9a8d0175dec8a4fb191b2e97dbf84b935ad6c +size 3005449760 diff --git a/internlm2_5-7b-chat.Q3_K_L.gguf b/internlm2_5-7b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..5edb6b0 --- /dev/null +++ b/internlm2_5-7b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35c3eb184a7c2d9b4c55ca7d159775055fce1559b6c24717981f4de715ef9a1 +size 4133418528 diff --git a/internlm2_5-7b-chat.Q3_K_M.gguf b/internlm2_5-7b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..7ce3598 --- /dev/null +++ b/internlm2_5-7b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3d0b380558f5b62d7a4fc486dbbd1d4d22ef59c178577d699a49b2a9e7b243 +size 3830380064 diff --git a/internlm2_5-7b-chat.Q3_K_S.gguf b/internlm2_5-7b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..7c16818 --- /dev/null +++ b/internlm2_5-7b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:827a1dfbca43ba01561dad69a303084c79de9be7d396233e316dc2359b6f2cbd +size 3475961376 diff --git a/internlm2_5-7b-chat.Q4_0_4_4.gguf b/internlm2_5-7b-chat.Q4_0_4_4.gguf new file mode 100644 index 0000000..562eaef --- /dev/null +++ b/internlm2_5-7b-chat.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:640aff238a062528ad69f21c96009d854877a201e1667708c85c9ce41cda08a8 +size 4453246496 diff --git a/internlm2_5-7b-chat.Q4_K_M.gguf b/internlm2_5-7b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..d20a5d5 --- /dev/null +++ b/internlm2_5-7b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50eccf544efe61a525999e23075d3ecd02beab1a5c59b8681b51e04a548be94e +size 4712769056 diff --git a/internlm2_5-7b-chat.Q4_K_S.gguf b/internlm2_5-7b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..e8be942 --- /dev/null +++ b/internlm2_5-7b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68fb24ecf91e24d0eb5f04a133bc8fde47d2286b26bafadf35725c8a8b4b5c3a +size 4484703776 diff --git a/internlm2_5-7b-chat.Q5_K_M.gguf b/internlm2_5-7b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..500fc74 --- /dev/null +++ b/internlm2_5-7b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e09f5ac6ae9664aedfad2991eb90984dc9e9c6fca25c7ed4c626180766dd9392 +size 5506737696 diff --git a/internlm2_5-7b-chat.Q5_K_S.gguf b/internlm2_5-7b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..d069ed4 --- /dev/null +++ b/internlm2_5-7b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cb055427ac5cb6b7c3e899ce4f4326acf1828b47b8486283cfcee1aed7a63d +size 5373044256 diff --git a/internlm2_5-7b-chat.Q6_K.gguf b/internlm2_5-7b-chat.Q6_K.gguf new file mode 100644 index 0000000..1c39f97 --- /dev/null +++ b/internlm2_5-7b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92adc157b6d02fb7729ad28b3e507d695d5ea472c1d231c2d875fa912c3ae68 +size 6350329376 diff --git a/internlm2_5-7b-chat.Q8_0.gguf b/internlm2_5-7b-chat.Q8_0.gguf new file mode 100644 index 0000000..8e6d5f0 --- /dev/null +++ b/internlm2_5-7b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0426dbd047dc0772fb8d314c0aa0440520e33ccfbd7018e21f22b52fb8b54f6b +size 8224241184 diff --git a/internlm2_5-7b-chat.f16.gguf b/internlm2_5-7b-chat.f16.gguf new file mode 100644 index 0000000..cee1c8d --- /dev/null +++ b/internlm2_5-7b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb24b7643e6d3788cd81c386597be3b0ee67e46c1cb5eda578b6c6c47e351e3 +size 15478093344