feat: add non model files and update README

README.md

@@ -1,3 +1,18 @@
+---
+language: 
+  - en
+tags:
+  - deepspeed
+  - visualchat
+  - multi-image
+  - causal
+  - chat
+license: apache-2.0
+datasets:
+  - openai/clip-vit-large-patch14
+---
+---
+
 # Llama-2-13b-deepspeed-visualchat
 
 DeepSpeed-VisualChat is a scalable, efficient, and user-friendly multi-modal training pipeline that leverages a novel multi-modal causal attention mechanism for better alignment of visual and text features. It uses data blending techniques to address the scarcity of interleaved text-and-image inputs in datasets. 

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "### Image:": 32000,
+  "<PAD>": 32002,
+  "<image>": 32001
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "fast_tokenizer": true,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}

train_args.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac941f24f66792c52aae9e2cd68c02b953b9de46d9ae3fa89c3e3c7ea4f19e18
+size 2293