Update config and instructions

.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 4B Base
+# Nemotron-4-Minitron-4B-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.
 
@@ -15,14 +15,12 @@ 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:
+Support for Nemotron models will be added in the upcoming transformers library release. In the meantime, please install the library from source:
 
 ```
-git clone git@github.com:suiyoubi/transformers.git
-cd transformers
-git checkout 63d9cb0
-pip install .
+pip install git+https://github.com/huggingface/transformers
 ```
+
 The following code provides an example of how to load the Minitron-4B model and use it to perform text generation.
 
 ```python
@@ -30,7 +28,7 @@ import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load the tokenizer and model
-model_path = 'nvidia/Minitron-4B-Base'
+model_path = 'nvidia/Nemotron-4-Minitron-4B-Base'
 tokenizer  = AutoTokenizer.from_pretrained(model_path)
 
 device = 'cuda'

config.json

@@ -16,11 +16,11 @@
   "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",
   "use_cache": true,
-  "vocab_size": 256000
+  "vocab_size": 256000,
+  "head_dim": 128
 }

special_tokens_map.json

@@ -1,23 +1 @@
-{
-  "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
-  }
-}
+{}

tokenizer.model → tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dfd8b970f437002fc445214304969fe59e64d4f48500bd0b77ba55340f2d811
-size 4545602
+oid sha256:83d0648daa0467fb02ddef7ff25460321dab2fbb20c280ae0bc1ea8052f7df90
+size 18143149