commit d49f3cd7a2a674a6e8aa92f35011e00b9bacd796 Author: ModelHub XC Date: Thu May 21 18:16:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: KBTG-Labs/THaLLE-0.1-7B-fa-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..7ae73ef --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: KBTG-Labs/THaLLE-0.1-7B-fa +language: + - en +license: apache-2.0 +pipeline_tag: text-generation +tags: + - finance + - llama-cpp +--- + +# KBTG-Labs/THaLLE-0.1-7B-fa-GGUF + +This model was converted to GGUF format from [`KBTG-Labs/THaLLE-0.1-7B-fa`](https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa) using llama.cpp. +Refer to the [original model card](https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa) for more details on the model. + +## Use with llama.cpp + +Install llama.cpp through brew (works on Mac and Linux) + +```bash +brew install llama.cpp + +``` + +Invoke the llama.cpp server or the CLI with your perfered quantization level ("q2_k", "q3_k_m", "q4_k_m", "q5_k_m", "q6_k", "q8_0", "f16"). +Smaller quantization is faster and use less memory, but will be less accurate. + +### CLI: + +```bash +llama-cli --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-.gguf -p "The meaning to life and the universe is" +``` + +### Server: + +```bash +llama-server --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-.gguf -c 2048 +``` + +Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. + +Step 1: Clone llama.cpp from GitHub. + +``` +git clone https://github.com/ggerganov/llama.cpp +``` + +Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). + +``` +cd llama.cpp && LLAMA_CURL=1 make +``` + +Step 3: Run inference through the main binary. + +``` +./llama-cli --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-.gguf -p "The meaning to life and the universe is" +``` + +or + +``` +./llama-server --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-.gguf -c 2048 +``` diff --git a/thalle-0.1-7b-fa-f16.gguf b/thalle-0.1-7b-fa-f16.gguf new file mode 100644 index 0000000..aa92350 --- /dev/null +++ b/thalle-0.1-7b-fa-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55affa3ae08a34c55d4466860df4a2aa384e24aae8e3629dd25b08cd0c8d4fbb +size 15237850880 diff --git a/thalle-0.1-7b-fa-q2_k.gguf b/thalle-0.1-7b-fa-q2_k.gguf new file mode 100644 index 0000000..7d80192 --- /dev/null +++ b/thalle-0.1-7b-fa-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1bba5767f1d4677f692bfd72a4802fc1f4d9c296059e8d905276885b0b22f1 +size 3015937792 diff --git a/thalle-0.1-7b-fa-q3_k_m.gguf b/thalle-0.1-7b-fa-q3_k_m.gguf new file mode 100644 index 0000000..c7e50c2 --- /dev/null +++ b/thalle-0.1-7b-fa-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebeda614b979b5ac5d4c90408f5c7d35df95e88e4688312bd24434997d08cf3 +size 3808388864 diff --git a/thalle-0.1-7b-fa-q4_k_m.gguf b/thalle-0.1-7b-fa-q4_k_m.gguf new file mode 100644 index 0000000..6949318 --- /dev/null +++ b/thalle-0.1-7b-fa-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b32da1bf1df5f5e27a0074d7fce00b66232a414a0fcf97fe2f6ae5aad7488df2 +size 4683071232 diff --git a/thalle-0.1-7b-fa-q5_k_m.gguf b/thalle-0.1-7b-fa-q5_k_m.gguf new file mode 100644 index 0000000..828fe55 --- /dev/null +++ b/thalle-0.1-7b-fa-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9be06d4ef08888d29e996c0528c7b9c1f57e8ab2c38c3e4c0e3ee3c0645e4de +size 5444828928 diff --git a/thalle-0.1-7b-fa-q6_k.gguf b/thalle-0.1-7b-fa-q6_k.gguf new file mode 100644 index 0000000..a7d740e --- /dev/null +++ b/thalle-0.1-7b-fa-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36afc5777f4e7c6a67082d04c1b4a3be9d1e9a062727ca40e1fc0f7ca0d70f77 +size 6254196480 diff --git a/thalle-0.1-7b-fa-q8_0.gguf b/thalle-0.1-7b-fa-q8_0.gguf new file mode 100644 index 0000000..d20f398 --- /dev/null +++ b/thalle-0.1-7b-fa-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6585f7c14a43262297cd6d30febfda9346ac87945a86123fb4a07bcedc07273c +size 8098522880