commit 44927d10e75f60b45892ee61be6ede120136df22 Author: ModelHub XC Date: Tue Jun 30 09:54:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: IlyaGusev/saiga_yandexgpt_8b_gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2484186 --- /dev/null +++ b/README.md @@ -0,0 +1,33 @@ +--- +datasets: +- IlyaGusev/saiga_scored +- IlyaGusev/saiga_preferences +language: +- ru +inference: false +license: other +license_name: yandexgpt-5-lite-8b-pretrain +license_link: LICENSE +--- + +Llama.cpp compatible versions of an original [8B model](https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b). + +Download one of the versions, for example `saiga_yandexgpt_8b.Q4_K_M.gguf`. +``` +wget https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b_gguf/resolve/main/saiga_yandexgpt_8b.Q4_K_M.gguf +``` + +Download [interact_gguf.py](https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py) +``` +https://raw.githubusercontent.com/IlyaGusev/saiga/refs/heads/main/scripts/interact_gguf.py +``` + +How to run: +``` +pip install llama-cpp-python fire + +python3 interact_gguf.py saiga_yandexgpt_8b.Q4_K_M.gguf +``` + +System requirements: +* 9GB RAM for q8_0 and less for smaller quantizations \ No newline at end of file diff --git a/saiga_yandexgpt_8b.BF16.gguf b/saiga_yandexgpt_8b.BF16.gguf new file mode 100644 index 0000000..4ea4b94 --- /dev/null +++ b/saiga_yandexgpt_8b.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2ac37a3032bd2f1b40ebbc278ddc816749ffa20e9d0b3c365f0c801603ece0 +size 16082679616 diff --git a/saiga_yandexgpt_8b.Q2_K.gguf b/saiga_yandexgpt_8b.Q2_K.gguf new file mode 100644 index 0000000..f0d834c --- /dev/null +++ b/saiga_yandexgpt_8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91965080c36cd86fc54c3e8722b0eab6b92c67a36749d8f2752097d7f618a76 +size 3183949632 diff --git a/saiga_yandexgpt_8b.Q3_K_M.gguf b/saiga_yandexgpt_8b.Q3_K_M.gguf new file mode 100644 index 0000000..ab7b5bd --- /dev/null +++ b/saiga_yandexgpt_8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80fe041ddc5eb672882d1bce5da8cf3101cfeb08d97e5cb6dcb0c8ea9c75145b +size 4024055616 diff --git a/saiga_yandexgpt_8b.Q3_K_S.gguf b/saiga_yandexgpt_8b.Q3_K_S.gguf new file mode 100644 index 0000000..414510d --- /dev/null +++ b/saiga_yandexgpt_8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba6683f17a5c2cdc259b5d2434d4d287bdce387feb6d7694b60a466e894ec58 +size 3669636928 diff --git a/saiga_yandexgpt_8b.Q4_0.gguf b/saiga_yandexgpt_8b.Q4_0.gguf new file mode 100644 index 0000000..551c37f --- /dev/null +++ b/saiga_yandexgpt_8b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3082467140cdcabc06cbf62bd40276eede039989a7a0683f8005c98a7ecbf930 +size 4666767168 diff --git a/saiga_yandexgpt_8b.Q4_K_M.gguf b/saiga_yandexgpt_8b.Q4_K_M.gguf new file mode 100644 index 0000000..50716f9 --- /dev/null +++ b/saiga_yandexgpt_8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fa815411ee51b4f2b8cabfb01f969f1a919356c14c939b9b189e566ade145a8 +size 4926289728 diff --git a/saiga_yandexgpt_8b.Q4_K_S.gguf b/saiga_yandexgpt_8b.Q4_K_S.gguf new file mode 100644 index 0000000..5ef67fd --- /dev/null +++ b/saiga_yandexgpt_8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7168f21b58b290beb393a48b19b06e5533e9957af7ea980a6adab4e6a56b7a70 +size 4698224448 diff --git a/saiga_yandexgpt_8b.Q5_K_M.gguf b/saiga_yandexgpt_8b.Q5_K_M.gguf new file mode 100644 index 0000000..14da546 --- /dev/null +++ b/saiga_yandexgpt_8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d355b387da26d8be530ad5ac7aad21e5444fb7cc10b63e7367a085f2b8507cd4 +size 5738936128 diff --git a/saiga_yandexgpt_8b.Q5_K_S.gguf b/saiga_yandexgpt_8b.Q5_K_S.gguf new file mode 100644 index 0000000..8ac7350 --- /dev/null +++ b/saiga_yandexgpt_8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0b953c345fc7fda82c0f1434fdd56bdadc3fedef1d2bc812a032c7b6830c3a +size 5605242688 diff --git a/saiga_yandexgpt_8b.Q6_K.gguf b/saiga_yandexgpt_8b.Q6_K.gguf new file mode 100644 index 0000000..ae2d4d1 --- /dev/null +++ b/saiga_yandexgpt_8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df2aa876d9532b3c0bbbe539cb0b83d507863fe68ae6ba325feb9a83765453e7 +size 6602372928 diff --git a/saiga_yandexgpt_8b.Q8_0.gguf b/saiga_yandexgpt_8b.Q8_0.gguf new file mode 100644 index 0000000..8e09a6f --- /dev/null +++ b/saiga_yandexgpt_8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2689f3a0c26e69c2a6498289b4c24f610ab466ef165424294e86d57c24c15314 +size 8548661056