commit 72004948ed880694f4b7ce67662c67494a2e3362 Author: ModelHub XC Date: Thu Sep 10 10:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: yasserrmd/Fanar-1-9B-Instruct-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c4018ad --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.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 +Fanar-1-9B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-F16.gguf filter=lfs diff=lfs merge=lfs -text +Fanar-1-9B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Fanar-1-9B-Instruct-F16.gguf b/Fanar-1-9B-Instruct-F16.gguf new file mode 100644 index 0000000..7f96a9d --- /dev/null +++ b/Fanar-1-9B-Instruct-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53294558ff1222444aa7052b31f4d6f0c52136f09a972b9a2d0f710dda01a5f3 +size 17572001344 diff --git a/Fanar-1-9B-Instruct-Q2_K.gguf b/Fanar-1-9B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..a914293 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a0f60eff797bb15a08440da9298b09a8b8222f1197ee1c5d153eb1b0ade7253 +size 3426820672 diff --git a/Fanar-1-9B-Instruct-Q3_K_M.gguf b/Fanar-1-9B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..4e1a202 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aabaadff0aae264bb92d836c53251113e031d0ad699d23e3c438b4117517e67f +size 4383203904 diff --git a/Fanar-1-9B-Instruct-Q4_0.gguf b/Fanar-1-9B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..f9cff75 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2011ec5ece88c884720c8c16663cc933ee1026bedb881433e08816e73d098bb1 +size 5064565312 diff --git a/Fanar-1-9B-Instruct-Q4_K_M.gguf b/Fanar-1-9B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..dcd08cf --- /dev/null +++ b/Fanar-1-9B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be8fe9c90b651e0b164941561dda90aeea780d4339ad58c87257b55a0cc9f3b0 +size 5382480448 diff --git a/Fanar-1-9B-Instruct-Q5_0.gguf b/Fanar-1-9B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..48510d0 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3594e1be63ec493a499a24bed0e1910d2b770a410909b82da4b15afc9563ad0c +size 6105014848 diff --git a/Fanar-1-9B-Instruct-Q5_K_M.gguf b/Fanar-1-9B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..b404850 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac3c77fb9bf621a81a938783294f82d8ffc4ef676f20347a409f7bd4533dfb8 +size 6268789312 diff --git a/Fanar-1-9B-Instruct-Q6_K.gguf b/Fanar-1-9B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..57ff548 --- /dev/null +++ b/Fanar-1-9B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6318966c57c3de3fd08f7aacf0f0f55bb31c23be4743b6e4826702cf3ac5c53c +size 3061312 diff --git a/Fanar-1-9B-Instruct-Q8_0.gguf b/Fanar-1-9B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..4adfe8c --- /dev/null +++ b/Fanar-1-9B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050795f7f9c3572c3b06fd467263f3c2dfaf821afcd4e176b69678a364b203aa +size 9337689664 diff --git a/Fanar-1-9B-Instruct-f32.gguf b/Fanar-1-9B-Instruct-f32.gguf new file mode 100644 index 0000000..5f4b94b --- /dev/null +++ b/Fanar-1-9B-Instruct-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97142a41a042e338105e7790b79e2caba36529fc94894ae1ac2826c7047ad74f +size 17572001344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e6e7ccb --- /dev/null +++ b/README.md @@ -0,0 +1,61 @@ +--- +language: +- ar +- en +base_model: +- QCRI/Fanar-1-9B-Instruct +pipeline_tag: text-generation +--- + +# Fanar-1-9B-Instruct — GGUF quantized + +This repo contains multiple **GGUF** builds of the Arabic-English LLM **Fanar-1-9B-Instruct**, the instruction-tuned variant of Fanar-1-9B created by QCRI / HBKU. The base model is a 9 B-parameter continuation of **gemma-2-9b** trained on ≈1 T Arabic + English tokens and aligned through SFT → DPO (4.5 M / 250 K pairs). License remains **Apache-2.0** and the context window is **4 096 tokens**. :contentReference[oaicite:0]{index=0} + +--- + +## Available files + +| Bits | Format | Size (≈) | +|------|--------|----------| +| Q2_K | 2-bit | 3.4 GB | +| Q3_K_M | 3-bit | 4.4 GB | +| Q4_0 / Q4_K_M | 4-bit | 5.1 GB / 5.4 GB | +| Q5_0 / Q5_K_M | 5-bit | 6.1 GB / 6.3 GB | +| Q6_K | 6-bit | 8 GB* | +| Q8_0 | 8-bit | 9.3 GB | +| F16 / F32 | 16 / 32-bit | 17.6 GB | :contentReference[oaicite:1]{index=1} + +\*value shown on the HF page is a placeholder. + +--- + +## Quick start (llama.cpp ≥ 0.2) + +```bash +git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make -j +./main -m Fanar-1-9B-Instruct.Q4_K_M.gguf -p "ما هي عاصمة قطر؟" +```` + +## Python (llama-cpp-python) + +```python +from llama_cpp import Llama +llm = Llama( + model_path="Fanar-1-9B-Instruct.Q4_K_M.gguf", + n_ctx=4096, + chat_format="gemma" # Fanar follows Gemma chat template +) +print(llm.create_chat_completion( + messages=[{"role":"user","content":"Translate 'peace' to Arabic"}] +).choices[0].message.content) +``` + +--- + +### Credits & notes + +* **Original model:** [`QCRI/Fanar-1-9B-Instruct`](https://huggingface.co/QCRI/Fanar-1-9B-Instruct) (please consult its model card for training data, evaluation results and limitations). ([Hugging Face][1]) +* This repository only supplies GGUF conversions for efficient local inference on CPU/GPU; no weights were changed. +* Use responsibly—outputs may be inaccurate, biased, or culturally sensitive. + +[1]: https://huggingface.co/QCRI/Fanar-1-9B-Instruct?utm_source=chatgpt.com "QCRI/Fanar-1-9B-Instruct - Hugging Face"