commit 3bc64f25bc74c50483c4b00575397b45a50e1240 Author: ModelHub XC Date: Fri Jul 24 02:37:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5d0381 --- /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 +Llama-2-7b-chat-hf_fictional_chinese_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7b-chat-hf_fictional_chinese_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.IQ4_XS.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.IQ4_XS.gguf new file mode 100644 index 0000000..e4eefa4 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ef772209cceee5b8c619750a76b66e77de70aca584c07d6108e8f9990f4fcb +size 3647518688 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q2_K.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q2_K.gguf new file mode 100644 index 0000000..541788c --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f99d6f6b7fcb1f56870681c3a2a72696f975eb8ed3a8ae83e88dca1d4bad1b9 +size 2532866016 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_L.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_L.gguf new file mode 100644 index 0000000..affb180 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9db31d71332cf44388f8b51e5b5c2a589280ef3a381ea55e7972c5a7f12ec3e2 +size 3597113312 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_M.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_M.gguf new file mode 100644 index 0000000..55ed65f --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8015f6c786a4218ce64d417c3e5b10a4f1cd2b9b928823320df05a1a2816e35 +size 3298007008 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_S.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_S.gguf new file mode 100644 index 0000000..e6484f5 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25692f9be23c53a359b4201fa6e71d04f7dec43f10c4c7034fd122c6a96dba69 +size 2948306912 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_M.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_M.gguf new file mode 100644 index 0000000..84ea5d4 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:978304e354d7f469cdc34b37e0ebaee145c8eddff00ad0c54c44d151619c9489 +size 4081006560 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_S.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_S.gguf new file mode 100644 index 0000000..bf9e36c --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e33af91706ff2454edf557b64df2c6e8245f8a1bc0de24188ae4b67a7f82e1 +size 3856742368 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_M.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_M.gguf new file mode 100644 index 0000000..31b3cba --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3fcfad6d41141e9baae201d439a3926e27dd740f7483960144d4bbcc537a04f +size 4783159264 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_S.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_S.gguf new file mode 100644 index 0000000..3494369 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ff9838fc4021cf8e5a5dc84d0ef4dd3ec8818de0314b815366fe8727806e12 +size 4651694048 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q6_K.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q6_K.gguf new file mode 100644 index 0000000..f1e6b55 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7c2a74007e004f658b6fc351cf018caddc3d013de5a877e9b965c3d6dfd8ad4 +size 5529196512 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.Q8_0.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q8_0.gguf new file mode 100644 index 0000000..6a7e44b --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b389faa606d23682f3a1ac5d61798fad6b1399adc21817890a515bb5d42e76a +size 7161092064 diff --git a/Llama-2-7b-chat-hf_fictional_chinese_v1.f16.gguf b/Llama-2-7b-chat-hf_fictional_chinese_v1.f16.gguf new file mode 100644 index 0000000..65831f4 --- /dev/null +++ b/Llama-2-7b-chat-hf_fictional_chinese_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4fa7abf3f16742c8df417c412e6ad8164f219853d134376556f7a0901289805 +size 13478107104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c52722 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: yzhuang/Llama-2-7b-chat-hf_fictional_chinese_v1 +datasets: +- generator +language: +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- sft +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/yzhuang/Llama-2-7b-chat-hf_fictional_chinese_v1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF).*** + +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/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7b-chat-hf_fictional_chinese_v1-GGUF/resolve/main/Llama-2-7b-chat-hf_fictional_chinese_v1.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. + +