Initial commit

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+LICENSE.pdf filter=lfs diff=lfs merge=lfs -text

LICENSE.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396d7de220f6b0e6fcfe33836f1b99a9943769b97c56330444f8efe1b441f607
+size 151612

README.md

@@ -0,0 +1,150 @@
+---
+base_model:
+- meta-llama/Llama-3.1-405B-Instruct
+license: llama3.1
+---
+# Model Overview
+
+## Description:
+The NVIDIA Llama 3.1 405B Instruct FP4 model is the quantized version of the Meta's Llama 3.1 405B Instruct model, which is an auto-regressive language model that uses an optimized transformer architecture. For more information, please check [here](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct). The NVIDIA Llama 3.1 405B Instruct FP4 model is quantized with [TensorRT Model Optimizer](https://github.com/NVIDIA/TensorRT-Model-Optimizer).
+
+This model is ready for commercial/non-commercial use.  <br>
+
+## Third-Party Community Consideration
+This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; see link to Non-NVIDIA [(Meta-Llama-3.1-405B-Instruct) Model Card](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct).
+
+### License/Terms of Use:
+[nvidia-open-model-license](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)
+
+[llama3.1](https://huggingface.co/meta-llama/Llama-3.1-405B-Instruct/blob/main/LICENSE)
+
+## Model Architecture:
+**Architecture Type:** Transformers  <br>
+**Network Architecture:** Llama3.1 <br>
+
+## Input:
+**Input Type(s):** Text <br>
+**Input Format(s):** String <br>
+**Input Parameters:** 1D (One Dimensional): Sequences <br>
+**Other Properties Related to Input:** Context length up to 128K <br>
+
+## Output:
+**Output Type(s):** Text <br>
+**Output Format:** String <br>
+**Output Parameters:** 1D (One Dimensional): Sequences <br>
+**Other Properties Related to Output:** N/A <br>
+
+## Software Integration:
+**Supported Runtime Engine(s):** <br>
+* Tensor(RT)-LLM <br>
+
+**Supported Hardware Microarchitecture Compatibility:** <br>
+* NVIDIA Blackwell <br>
+
+**Preferred Operating System(s):** <br>
+* Linux <br>
+
+## Model Version(s):
+The model is quantized with nvidia-modelopt **v0.23.0**  <br>
+
+## Datasets:
+* Calibration Dataset: [cnn_dailymail](https://huggingface.co/datasets/abisee/cnn_dailymail) <br>
+** Data collection method: Automated. <br>
+** Labeling method: Unknown. <br>
+
+
+## Inference:
+**Engine:** Tensor(RT)-LLM <br>
+**Test Hardware:** B200 <br>
+
+## Post Training Quantization
+This model was obtained by quantizing the weights and activations of Meta-Llama-3.1-405B-Instruct to FP4 data type, ready for inference with TensorRT-LLM. Only the weights and activations of the linear operators within transformers blocks are quantized. This optimization reduces the number of bits per parameter from 16 to 4, reducing the disk size and GPU memory requirements by approximately 3.5x.
+
+## Usage
+
+### Deploy with TensorRT-LLM
+
+To deploy the quantized checkpoint with [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM) LLM API, follow the sample codes below:
+
+* LLM API sample usage:
+```
+from tensorrt_llm import LLM, SamplingParams
+
+
+def main():
+
+    prompts = [
+        "Hello, my name is",
+        "The president of the United States is",
+        "The capital of France is",
+        "The future of AI is",
+    ]
+    sampling_params = SamplingParams(temperature=0.8, top_p=0.95)
+
+    llm = LLM(model="nvidia/Llama-3.1-405B-Instruct-FP4")
+
+    outputs = llm.generate(prompts, sampling_params)
+
+    # Print the outputs.
+    for output in outputs:
+        prompt = output.prompt
+        generated_text = output.outputs[0].text
+        print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
+
+
+# The entry point of the program need to be protected for spawning processes.
+if __name__ == '__main__':
+    main()
+
+```
+
+Please refer to the [TensorRT-LLM llm-api documentation](https://nvidia.github.io/TensorRT-LLM/llm-api/index.html) for more details.
+
+#### Evaluation
+The accuracy benchmark results are presented in the table below:
+<table>
+  <tr>
+   <td><strong>Precision</strong>
+   </td>
+   <td><strong>MMLU</strong>
+   </td>
+   <td><strong>GSM8K_COT</strong>
+   </td>
+   <td><strong>ARC Challenge</strong>
+   </td>
+   <td><strong>IFEVAL</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>BF16
+   </td>
+   <td>87.3
+   </td>
+   <td>96.8
+   </td>
+   <td>96.9
+   </td>
+   <td>88.6
+   </td>
+  </tr>
+  <tr>
+   <td>FP4
+   </td>
+   <td>87.2
+   </td>
+   <td>96.1
+   </td>
+   <td>96.6
+   </td>
+   <td>89.5
+   </td>
+  </tr>
+  <tr>
+</table>
+
+
+## Ethical Considerations
+
+NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
+
+Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "/opt/zhiyu_hf_ckpts/Llama-3.1-405B-Instruct/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 16384,
+  "initializer_range": 0.02,
+  "intermediate_size": 53248,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 128,
+  "num_hidden_layers": 126,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.1"
+}

hf_quant_config.json

@@ -0,0 +1,14 @@
+{
+    "producer": {
+        "name": "modelopt",
+        "version": "0.23.0"
+    },
+    "quantization": {
+        "quant_algo": "NVFP4",
+        "kv_cache_quant_algo": "FP8",
+        "group_size": 16,
+        "exclude_modules": [
+            "lm_head"
+        ]
+    }
+}

model-00001-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae245809392c0ed4c60ab859eb5308559e30ba5cebd39655b44da9469a19a7f7
+size 4959766832

model-00002-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb135fbe71accbd8417bb5042136cfba855685cf39c27addc6dd3a17fa55f83
+size 4943194176

model-00003-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b64ea559ea5aad50529c2dd2d7158d79cc89cc2ecb7d5229605d0b6a4a127150
+size 4567735992

model-00004-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73971039f1c1f9f5bc722951622e28357afebe646a4bd14c0ea92590b94e0b85
+size 4888668004

model-00005-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1ae13a8ad0731a2e093e6b05128561bb617e58832f6077e2294a4f2afd4e06
+size 4888668044

model-00006-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20de05cc9193ca949ec7ec33906bd83f33e448c7bbd0afdbe37810a42e287acd
+size 4567736064

model-00007-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f866c6eee1a0cc4de7880f8d771cdae7ea9496a17b76a66f8dd4764340bca7b3
+size 4888668100

model-00008-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6820965c1988e515773c6153e8fe15d7d9422325c4cc31f845030af8ea3aa4c
+size 4888668092

model-00009-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71c04bdf6492d1a3bdbeac11651962e8921b7d580e9ef60697dc94aa6175666
+size 4567736064

model-00010-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8bba4817b7db58c530feca7ae7a27382c76c62092df1a61b34ad8fbe315575b
+size 4888668100

model-00011-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b41d8812d740c561867a7c509ad0c4870ae704ac3119da5bd5586caaca8d24
+size 4888668092

model-00012-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506cb7bc925f400b2bc92b4ffb2009a3ad81f9e32834dfe9a999bb0743becd74
+size 4567736064

model-00013-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d01c9776ed6c6dde194700dd6428121e590eb8cbe5f1f7159dea0e9529be67
+size 4888668100

model-00014-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e618d2f7b6892ab2b26a7e148af796e4289dda7089835023bb4dade7b02e28d
+size 4888668092

model-00015-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7403e06c981391c5990172f1c10b1d0968a285d33d8b3e04cae24e96d8964e38
+size 4567736064

model-00016-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103b474ae8cca52d433d51b2f76302fa62a7263622e669de95c775b6f567ac36
+size 4888668100

model-00017-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41468e40a10ce6ca8bf999c361f77c66941a7a4b1d4ced53b6ae7ff32cdf8e3f
+size 4888668092

model-00018-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d92d2c35c0883f6b14415f9a3697f7771079147713120d6c395f5a2f458b31ed
+size 4567736064

model-00019-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6950fe691d5076435c3f077628f3729332a078f4ba1cb1a3161799d74523622b
+size 4888668100

model-00020-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bcb68ed2a29411aa397223064b235b23f857c5480b1d7aebec2a067c320600
+size 4888668092

model-00021-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81281c4294db7de4a0797eae869b9279b5450ab2e9205520b953fbc05c66ca32
+size 4567736064

model-00022-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda066e460bfb809602bf50cb36bf6e5fc203217c14bc916c48b9ad99c0b5817
+size 4888668100

model-00023-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:791443b724c55e723790527c5bd2c2779594b78f384d35be59718d4dc2e5728f
+size 4888668092

model-00024-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:581a4c392541d7af732b48056405205b0994936adb06d3738deaa80ba71ae329
+size 4567736064

model-00025-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae82099eace40fa703a541b44387d80177c3576d7146ac55163fa2dc2a319af
+size 4888668100

model-00026-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e6c034c822a23090a7ab4d89ed060c4514e9140fb63259903a3f1c4ae50a6ef
+size 4888668092

model-00027-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399078236b1fc65808265c12b65e5ac866ccf59eaea9833bd773380d4f7d1aec
+size 4567736064

model-00028-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36143b4f100110a677f117c4473816d93b7d7e116b13caeb0fe709ccce707875
+size 4888668100

model-00029-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aaa96ae6e8a8ef2dbe0d52b924bb3c31ea364ed8b42b8e933a30e7d045db69b
+size 4888668092

model-00030-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df39cbb75eaf5174904febff8e74ba8e71b7a6e404b505973c2ba4bbc1773a5f
+size 4567736064

model-00031-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a5c83270b57452abec403ba5a5985ad0ddcd78e18248943415afff7bf14de2
+size 4888668100

model-00032-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c700ad452de733f7c0a7814dd00119d625f60ea97a045efdaf32e7100b2070c8
+size 4888668092

model-00033-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47479d3fd8589b19ce0a715e1f1529687f56b8785579f4482e3bb63cc7f86eab
+size 4567736064

model-00034-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2b56e4cc1fa1cf216191c48e454fd2bbe4cfd6829b7701bded58c6488c142f8
+size 4888668100

model-00035-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35239e92e1c8ac0f5d70bb99c60bf68e537ac87a67a1bc65b63aa1281acf9a29
+size 4888668092

model-00036-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924f580f16febc4a785e66b7cc256e741ba4723eeaf59fecc1df72f4aebeb204
+size 4567736064

model-00037-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:625ce20a19e0f3ae7e00501e925847d43bbc6ca9b2b76c78e5dfeb66791bd311
+size 4888668100

model-00038-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc275ac5bedcdb942b6d6c0906634f62f3fff6d29167790dc1159e2931ae2d78
+size 4888668092

model-00039-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bcab1328a675c8223d4de75dd278bc7a2c7418f0d98fd93b41ebf77d757bb4
+size 4567736112

model-00040-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a25c63de95938497751ebefae6dd9593453fac3df449eb788e311823d615dade
+size 4888668188

model-00041-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059ae6abdfe38a49647749230a192c5bed0fb22a7137173b737fb8627a91d704
+size 4888668180

model-00042-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe46588d82435c4b43519fb17855401a54a8091f805e1d0fa1d4a1e51fe6ce27
+size 4567736136

model-00043-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ea117d5f8df6a8dc91bd232d2e041a836fb7f30bb2d4d0e1be4a7f236cd84a
+size 4888668188

model-00044-of-00049.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23507fab35ecfd41d22d9ec28bec680a4644c8252f75c3633aa82ff1dab893d
+size 4888668180