Update with v2 model and config

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 nemo/*.nemo filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -5,7 +5,7 @@ license_link: >-
   https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf
 ---
 
-# Minitron 8B Base
+# Nemotron-4 Minitron 8B Base
 
 Minitron is a family of small language models (SLMs) obtained by pruning NVIDIA's [Nemotron-4 15B](https://arxiv.org/abs/2402.16819) model. We prune model embedding size, attention heads, and MLP intermediate dimension, following which, we perform continued training with distillation to arrive at the final models.
 
@@ -15,22 +15,20 @@ Minitron models are for research and development only.
 
 ## HuggingFace Quickstart
 
-The [PR](https://github.com/huggingface/transformers/pull/31699) to support our models in Hugging Face in under review and expected to be merged soon. In the meantime, this [branch](https://github.com/suiyoubi/transformers/tree/aot/nemotron-support) at [commit ID 63d9cb0](https://github.com/suiyoubi/transformers/commit/63d9cb0afd2bf5d4cb5431ba1b2c4e353752a937) can be used for Minitron models:
+The [pull request](https://github.com/huggingface/transformers/pull/32495) to support this model in Hugging Face Transformers is under review and expected to be merged soon. In the meantime, please follow the installation instructions below:
 
 ```
-git clone git@github.com:suiyoubi/transformers.git
-cd transformers
-git checkout 63d9cb0
-pip install .
+$ git clone -b aot/head_dim_rope --single-branch https://github.com/suiyoubi/transformers.git && cd transformers
+$ pip install -e .
 ```
-The following code provides an example of how to load the Minitron-8B model and use it to perform text generation.
+The following code provides an example of how to load the Nemotron-4-Minitron-8B model and use it to perform text generation.
 
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load the tokenizer and model
-model_path = "nvidia/Minitron-8B-Base"
+model_path = "nvidia/Nemotron-4-Minitron-8B-Base"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
 
 device='cuda'
@@ -59,13 +57,13 @@ Minitron is released under the [NVIDIA Open Model License Agreement](https://dev
 
 | Average |
 | :---- |
-| 63.8 |
+| 64.5 |
 
 *Zero-shot performance.* Evaluated using select datasets from the [LM Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) with additions:
 
 HellaSwag | Winogrande | GSM8K| ARC-C | XLSum |
 | :------------- | :------------- | :------------- | :------------- | :------------- |
-| 80.7 | 79.0 | 51.3  | 52.6 | 31.2
+| 81.6 | 80.3 | 54.2  | 49.2 | 31.1
 
 
 *Code generation performance*. Evaluated using [HumanEval](https://github.com/openai/human-eval):

config.json

@@ -13,15 +13,14 @@
   "model_type": "nemotron",
   "num_attention_heads": 48,
   "num_hidden_layers": 32,
-  "kv_channels": 128,
   "num_key_value_heads": 8,
   "norm_eps": 1e-05,
   "rope_theta": 10000,
-  "rope_percent": 0.5,
-  "rope_scaling": null,
+  "partial_rotary_factor": 0.5,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.44.0",
   "use_cache": true,
-  "vocab_size": 256000
-}
+  "vocab_size": 256000,
+  "head_dim": 128
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c84c2ed78c94d103bbf81f4205206a8e022e0c7c1135c693e7574535fa470
+oid sha256:debb954a1720801fa4c054f0c761fe344758ef659419d45e5b9a5e7b10722a11
 size 16543512498

special_tokens_map.json

@@ -1,23 +1,4 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>"
 }

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d0648daa0467fb02ddef7ff25460321dab2fbb20c280ae0bc1ea8052f7df90
+size 18143149

tokenizer.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
-size 4545602