commit adeb5de74cf58c1667164a249269845db46f84fc Author: ModelHub XC Date: Sat Jun 13 04:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cendol-llama2-7b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d705f27 --- /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 +cendol-llama2-7b-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cendol-llama2-7b-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0f28910 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: indonlp/cendol-llama2-7b-chat +language: +- id +- su +- jv +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/indonlp/cendol-llama2-7b-chat + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cendol-llama2-7b-chat-GGUF/resolve/main/cendol-llama2-7b-chat.f16.gguf) | f16 | 13.6 | 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/cendol-llama2-7b-chat.IQ4_XS.gguf b/cendol-llama2-7b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..0d6e244 --- /dev/null +++ b/cendol-llama2-7b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1448dfa51d34db2e86a548a58753405ef26bfe8ad70bca66200a18bbddcfa37 +size 3647522912 diff --git a/cendol-llama2-7b-chat.Q2_K.gguf b/cendol-llama2-7b-chat.Q2_K.gguf new file mode 100644 index 0000000..4c1267a --- /dev/null +++ b/cendol-llama2-7b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0109ee481012ea44f29987a204172c59e36d24ab85bb7ea6ac1b7e2ad9dfa993 +size 2532869408 diff --git a/cendol-llama2-7b-chat.Q3_K_L.gguf b/cendol-llama2-7b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..472900e --- /dev/null +++ b/cendol-llama2-7b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:effe64d730a0f628e53432a4eb7dda37e52154005cb59430a290b4e3d861d7cc +size 3597117120 diff --git a/cendol-llama2-7b-chat.Q3_K_M.gguf b/cendol-llama2-7b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..dba42ad --- /dev/null +++ b/cendol-llama2-7b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce6b1d4ef7b15912278ba69c05cd373cb6a5a102988bc20944ce5081f41f00f +size 3298010816 diff --git a/cendol-llama2-7b-chat.Q3_K_S.gguf b/cendol-llama2-7b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..61dbc4c --- /dev/null +++ b/cendol-llama2-7b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d63028f55eb6759054a09ca47281a891640e536096296279195125d7cc5b5afc +size 2948310720 diff --git a/cendol-llama2-7b-chat.Q4_K_M.gguf b/cendol-llama2-7b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..490b0c7 --- /dev/null +++ b/cendol-llama2-7b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05cd7addeb600dec65c165bc30b6207826e044e36144fd17f19ea431ceb1b13d +size 4081010912 diff --git a/cendol-llama2-7b-chat.Q4_K_S.gguf b/cendol-llama2-7b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..4726ec1 --- /dev/null +++ b/cendol-llama2-7b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a6e5043682ca9c6985ab07ac8f806ecfa3b652cd67705efc819192c663293d +size 3856746720 diff --git a/cendol-llama2-7b-chat.Q5_K_M.gguf b/cendol-llama2-7b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..413e1f2 --- /dev/null +++ b/cendol-llama2-7b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce4726e3f23809f46651a14c7c0f459b5157bf822eea77bc1cb6893e1dac8cab +size 4783164128 diff --git a/cendol-llama2-7b-chat.Q5_K_S.gguf b/cendol-llama2-7b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..e9234e4 --- /dev/null +++ b/cendol-llama2-7b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6571e6ce45387900c6a1b888a0b4119cac1126ef3e2b411a754b58ee80070401 +size 4651698912 diff --git a/cendol-llama2-7b-chat.Q6_K.gguf b/cendol-llama2-7b-chat.Q6_K.gguf new file mode 100644 index 0000000..2ad6c8e --- /dev/null +++ b/cendol-llama2-7b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc836d604dc31a3a6d487dc84864e93360d4c91ba30f752abc2c35285e43f376 +size 5529201920 diff --git a/cendol-llama2-7b-chat.Q8_0.gguf b/cendol-llama2-7b-chat.Q8_0.gguf new file mode 100644 index 0000000..97faf5f --- /dev/null +++ b/cendol-llama2-7b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda8561b4a9b2a4cef33f070f16efa9afab5731f10cc831dd78332c3b53498a3 +size 7161099456 diff --git a/cendol-llama2-7b-chat.f16.gguf b/cendol-llama2-7b-chat.f16.gguf new file mode 100644 index 0000000..b59d272 --- /dev/null +++ b/cendol-llama2-7b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cafd1c268aec0b4cf9a3c727fce051af074c99add398c74ab9d0dc19708f604 +size 13478122176