commit 90b058a06cef9d6f7ea12c42285d0976a7aba9ea Author: ModelHub XC Date: Thu Jun 18 00:10:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/LongWriter-llama3.1-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f7ef4d7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +LongWriter-llama3.1-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LongWriter-llama3.1-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LongWriter-llama3.1-8b.Q2_K.gguf b/LongWriter-llama3.1-8b.Q2_K.gguf new file mode 100644 index 0000000..ae58149 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e654df5fd98fadab1ab01a614de783f311d71b8b32a1bd4e9963b3e30eb1fa2 +size 3179131424 diff --git a/LongWriter-llama3.1-8b.Q3_K_L.gguf b/LongWriter-llama3.1-8b.Q3_K_L.gguf new file mode 100644 index 0000000..a9710d5 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1cb1e6ce1360adc90e4c9956e9421ee561458b2bbd7a107a484a008390e928c +size 4321956384 diff --git a/LongWriter-llama3.1-8b.Q3_K_M.gguf b/LongWriter-llama3.1-8b.Q3_K_M.gguf new file mode 100644 index 0000000..9c9a0ae --- /dev/null +++ b/LongWriter-llama3.1-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2542e3806b0069523deedea36cb090566b490ff4cfd9dc59e7e538a524ed67e9 +size 4018917920 diff --git a/LongWriter-llama3.1-8b.Q3_K_S.gguf b/LongWriter-llama3.1-8b.Q3_K_S.gguf new file mode 100644 index 0000000..7ec5b94 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00ec0ed2f00fd534362607a98ce159d21dd2622c4ab41d28b9a37780019d5000 +size 3664499232 diff --git a/LongWriter-llama3.1-8b.Q4_0.gguf b/LongWriter-llama3.1-8b.Q4_0.gguf new file mode 100644 index 0000000..b2df5cf --- /dev/null +++ b/LongWriter-llama3.1-8b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92061b9d2a2e4f98391dc415de95a38d26007d88830389236ddd9f8b3281899 +size 4661211680 diff --git a/LongWriter-llama3.1-8b.Q4_1.gguf b/LongWriter-llama3.1-8b.Q4_1.gguf new file mode 100644 index 0000000..f7944c0 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed1e8007557285fafde24255f96e009c5b6463a4f66361d20f62a8f9d3f25b4 +size 5130252832 diff --git a/LongWriter-llama3.1-8b.Q4_K_M.gguf b/LongWriter-llama3.1-8b.Q4_K_M.gguf new file mode 100644 index 0000000..6c20563 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c70ec463165f414c62689dce52ca2cfc788c501d16917dc5e08dafea4d91dbf +size 4920734240 diff --git a/LongWriter-llama3.1-8b.Q4_K_S.gguf b/LongWriter-llama3.1-8b.Q4_K_S.gguf new file mode 100644 index 0000000..1b5ebbf --- /dev/null +++ b/LongWriter-llama3.1-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718f988d8d721e2d6223d8814a154773286344093842f2a86abf421aede80db1 +size 4692668960 diff --git a/LongWriter-llama3.1-8b.Q5_0.gguf b/LongWriter-llama3.1-8b.Q5_0.gguf new file mode 100644 index 0000000..bccaf7c --- /dev/null +++ b/LongWriter-llama3.1-8b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79aa7ed50946a0d7a16d3117947699e1e23622a272c2d546f5c6c19eee70228 +size 5599293984 diff --git a/LongWriter-llama3.1-8b.Q5_1.gguf b/LongWriter-llama3.1-8b.Q5_1.gguf new file mode 100644 index 0000000..577161c --- /dev/null +++ b/LongWriter-llama3.1-8b.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7eebc8e74ec71e7c189281f668b9d872a2e62a15b698fe6e67dd931fbeca06 +size 6068335136 diff --git a/LongWriter-llama3.1-8b.Q5_K_M.gguf b/LongWriter-llama3.1-8b.Q5_K_M.gguf new file mode 100644 index 0000000..1c08713 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d206872c19207b974d7826c076bbea22f8c25cc16c08ad77953d45624704c49c +size 5732987424 diff --git a/LongWriter-llama3.1-8b.Q5_K_S.gguf b/LongWriter-llama3.1-8b.Q5_K_S.gguf new file mode 100644 index 0000000..5a62a78 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837a6ec6056c1706f75a759749bdf11e52c73a31abb06d5d96b6b7c247088fe3 +size 5599293984 diff --git a/LongWriter-llama3.1-8b.Q6_K.gguf b/LongWriter-llama3.1-8b.Q6_K.gguf new file mode 100644 index 0000000..e6764e1 --- /dev/null +++ b/LongWriter-llama3.1-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805cbb51ca02a0c6d44ac97924ee5b0bebbb7f742dbd345178b42a1b575d058a +size 6596006432 diff --git a/LongWriter-llama3.1-8b.Q8_0.gguf b/LongWriter-llama3.1-8b.Q8_0.gguf new file mode 100644 index 0000000..1a3730c --- /dev/null +++ b/LongWriter-llama3.1-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b0f8e426e94137bff7c371d5a09f6d65e74cceb4088301264c2758ca6b3211 +size 8540770848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4fea9e7 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ + +--- + +language: +- en +- zh +library_name: transformers +tags: +- Long Context +- chatglm +- llama +datasets: +- THUDM/LongWriter-6k +license: llama3.1 + +--- + +![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) + +# QuantFactory/LongWriter-llama3.1-8b-GGUF +This is quantized version of [THUDM/LongWriter-llama3.1-8b](https://huggingface.co/THUDM/LongWriter-llama3.1-8b) created using llama.cpp + +# Original Model Card + +# LongWriter-llama3.1-8b + +

+ 🤗 [LongWriter Dataset] • 💻 [Github Repo] • 📃 [LongWriter Paper] +

+ +LongWriter-llama3.1-8b is trained based on [Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B), and is capable of generating 10,000+ words at once. + + +A simple demo for deployment of the model: +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch +tokenizer = AutoTokenizer.from_pretrained("THUDM/LongWriter-llama3.1-8b", trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained("THUDM/LongWriter-llama3.1-8b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto") +model = model.eval() +query = "Write a 10000-word China travel guide" +prompt = f"[INST]{query}[/INST]" +input = tokenizer(prompt, truncation=False, return_tensors="pt").to(device) +context_length = input.input_ids.shape[-1] +output = model.generate( + **input, + max_new_tokens=32768, + num_beams=1, + do_sample=True, + temperature=0.5, +)[0] +response = tokenizer.decode(output[context_length:], skip_special_tokens=True) +print(response) +``` +Please ahere to the prompt template (system prompt is optional): `<>\n{system prompt}\n<>\n\n[INST]{query1}[/INST]{response1}[INST]{query2}[/INST]{response2}...` + +License: [Llama-3.1 License](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE) + +## Citation + +If you find our work useful, please consider citing LongWriter: + +``` +@article{bai2024longwriter, + title={LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs}, + author={Yushi Bai and Jiajie Zhang and Xin Lv and Linzhi Zheng and Siqi Zhu and Lei Hou and Yuxiao Dong and Jie Tang and Juanzi Li}, + journal={arXiv preprint arXiv:2408.07055}, + year={2024} +} +``` diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9e26dfe --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{} \ No newline at end of file