update

README.md

@@ -1,3 +1,80 @@
----
-license: llama3.1
----
+---
+library_name: transformers
+language:
+- en
+---
+
+# Model Information
+
+We introduce **UltraLong-8B**, a series of ultra-long context language models designed to process extensive sequences of text (up to 1M, 2M, and 4M tokens) while maintaining competitive performance on standard benchmarks. Built on the Llama-3.1, UltraLong-8B leverages a systematic training recipe that combines efficient continued pretraining with instruction tuning to enhance long-context understanding and instruction-following capabilities. This approach enables our models to efficiently scale their context windows without sacrificing general performance.
+
+
+## The UltraLong Models
+
+- [ultralong/Llama-3.1-8B-UltraLong-1M-Instruct](https://huggingface.co/ultralong/Llama-3.1-8B-UltraLong-1M-Instruct)
+- [ultralong/Llama-3.1-8B-UltraLong-2M-Instruct](https://huggingface.co/ultralong/Llama-3.1-8B-UltraLong-2M-Instruct)
+- [ultralong/Llama-3.1-8B-UltraLong-4M-Instruct](https://huggingface.co/ultralong/Llama-3.1-8B-UltraLong-4M-Instruct)
+
+
+## Uses
+
+Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
+
+Make sure to update your transformers installation via `pip install --upgrade transformers`.
+
+```python
+import transformers
+import torch
+
+model_id = "ultralong/Llama-3.1-8B-UltraLong-2M-Instruct"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+)
+print(outputs[0]["generated_text"][-1])
+```
+
+## Model Card
+
+* Base model: [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct)
+* Continued Pretraining: 1B tokens on 2M Per-source upsampled SlimPajama data.
+* Supervised fine-tuning (SFT): 1B tokens on open-source instruction datasets across general, mathematics, and code domains.
+* Maximum context window: 2M tokens
+
+## Evaluation Results
+
+We evaluate UltraLong-8B on a diverse set of benchmarks, including long-context tasks (e.g., RULER, LV-Eval, and InfiniteBench) and standard tasks (e.g., MMLU, MATH, GSM-8K, and HumanEval). UltraLong-8B achieves superior performance on ultra-long context tasks while maintaining competitive results on standard benchmarks.
+
+### Needle in a Haystack
+
+<img width="80%" alt="image" src="Llama-3.1-8B-UltraLong-2M-Instruct.png">
+
+### Long context evaluation
+
+<img width="80%" alt="image" src="long_benchmark.png">
+
+### Standard capability evaluation
+
+<img width="80%" alt="image" src="standard_benchmark.png">
+
+## Correspondence to
+Chejian Xu (chejian2@illinois.edu), Wei Ping (wping@nvidia.com)
+
+## Citation
+
+<pre>
+
+</pre>

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c30ec309609a6eeb45b6bb41e0c75e0f4b16815bbdf8e4329d9ad3051a928ca
+size 897

generation_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abcf8ce084298b021f1d6f42b4c08d141d1897eff20428e987a9e8dbcfd2e42
+size 121

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b23e21856ccb15703d4467e12cb399d46635a92a7f467bdfec8b76c9bc3e52
+size 4899049080

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502e5b0ccc5e8d3d3ae7796429e748f2bc1815579db4426fad3724f658c12122
+size 4832007448

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f177f817c37c7435d9f74be85db7f27df0fabf813729d5be937de6c813e5dd83
+size 4999813112

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90bd3ea49f7126f1cb151d6d5a115b092c0f28bb0b6648b911f572fcbf8d90d
+size 4999813128

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa26dd4160d6404924d34ef1c7961807c068c7dc2143874738d65bd52cefb186
+size 4832007496

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b465c470dc8c955445189650bd0224bd4dafa37c3b73cb358056dbdf607b3826
+size 4999813120

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ff2cf9d167f093efc4497594741c20f7b65274bf05d0f72445f7d3e71ec763
+size 2583741096

model.safetensors.index.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fde2fcc0ec44f067e7429e647bfbeeb159a649a8fd9f209ff315ec5411af6b4
+size 23950

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f38c73729248f6c127296386e3cdde96e254636cc58b4169d3fd32328d9a8ec
+size 296

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5965bf8c62811c97bff003a2198c7ccb5c0589ae9310e9c796a008a336e1c9
+size 55377