commit 37d6bc4393ab99f249250efa5de9d59ced98bef6 Author: ModelHub XC Date: Mon May 4 21:59:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama2-Chinese-7b-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a3eff6 --- /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 +Llama2-Chinese-7b-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama2-Chinese-7b-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama2-Chinese-7b-Chat.IQ4_XS.gguf b/Llama2-Chinese-7b-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..325eb87 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5639bdf23d57e321fe700d20c23fa6979c4b3a68673a9bb4fd23f0acf7b215e9 +size 3647517376 diff --git a/Llama2-Chinese-7b-Chat.Q2_K.gguf b/Llama2-Chinese-7b-Chat.Q2_K.gguf new file mode 100644 index 0000000..2c520a3 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dd29ae01b1262830121965a2057b2a7f2b3419201f740e094c24196013d1945 +size 2532864704 diff --git a/Llama2-Chinese-7b-Chat.Q3_K_L.gguf b/Llama2-Chinese-7b-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..85cc31f --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d6a8fe8aff4bbc62aad5f3eac0d7f930e9d868d8e13f85254c8646987ca6c5 +size 3597112000 diff --git a/Llama2-Chinese-7b-Chat.Q3_K_M.gguf b/Llama2-Chinese-7b-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..564ea71 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43880c8b8e8014071f9cdb37f2a38726568f8226aa8538d20d83fa13f956c131 +size 3298005696 diff --git a/Llama2-Chinese-7b-Chat.Q3_K_S.gguf b/Llama2-Chinese-7b-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..10bb9e9 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb9b3c6988a24cb34c8034b6dc216c96e02286225de1fc4e7fcecf3cfedfa7e +size 2948305600 diff --git a/Llama2-Chinese-7b-Chat.Q4_K_M.gguf b/Llama2-Chinese-7b-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..090a991 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2811975b236b0bb76a412643ee5c228a02390ecbd2832f2eaf24d50f5fb253a9 +size 4081005248 diff --git a/Llama2-Chinese-7b-Chat.Q4_K_S.gguf b/Llama2-Chinese-7b-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..2a2a52e --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3654d4cb7dd6f6555f69b46018aceaa69a8d2bc6f5eedaa87ba00cd46785e905 +size 3856741056 diff --git a/Llama2-Chinese-7b-Chat.Q5_K_M.gguf b/Llama2-Chinese-7b-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..d809754 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a19cea10cb07dbe2d7f0349dc5b02a4c1e9513e4a1b4706203eba2936d82e3 +size 4783157952 diff --git a/Llama2-Chinese-7b-Chat.Q5_K_S.gguf b/Llama2-Chinese-7b-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..3c6e792 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1605e861a9974cb2e29fbed7c14441a275dabadf6b823b1e588ee7bc597a8b03 +size 4651692736 diff --git a/Llama2-Chinese-7b-Chat.Q6_K.gguf b/Llama2-Chinese-7b-Chat.Q6_K.gguf new file mode 100644 index 0000000..6d59b68 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23b90d0f240fcd291bb460a36384104ed4e97a488de7826627917fccfa06db2 +size 5529195200 diff --git a/Llama2-Chinese-7b-Chat.Q8_0.gguf b/Llama2-Chinese-7b-Chat.Q8_0.gguf new file mode 100644 index 0000000..ab58b1a --- /dev/null +++ b/Llama2-Chinese-7b-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e78839776349a342ab25af8b59359869071c91f6db17cddd7a4a85103e88e00 +size 7161090752 diff --git a/Llama2-Chinese-7b-Chat.f16.gguf b/Llama2-Chinese-7b-Chat.f16.gguf new file mode 100644 index 0000000..36c1573 --- /dev/null +++ b/Llama2-Chinese-7b-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a486ec86bb27bf509fd1873a4f395608a13ed86cf0026fab1cdc89a327acc8c +size 13478105792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fff249d --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: FlagAlpha/Llama2-Chinese-7b-Chat +language: +- zh +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/FlagAlpha/Llama2-Chinese-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/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-7b-Chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama2-Chinese-7b-Chat-GGUF/resolve/main/Llama2-Chinese-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. 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. + +