update config

.gitignore

@@ -0,0 +1 @@
+.DS_Store

README.md

@@ -1,32 +0,0 @@
----
-license: apache-2.0
-datasets:
-- cerebras/SlimPajama-627B
-- bigcode/starcoderdata
-- timdettmers/openassistant-guanaco
-language:
-- en
----
-
-# TinyLlama-1.1B pre-built lib & weights for mlc-chat iOS.
-
-https://github.com/jzhang38/TinyLlama
-
-The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
-
-<div align="center">
-  <img src="./TinyLlama_logo.png" width="300"/>
-</div>
-
-We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
-
-#### This Model
-This is the chat model finetuned on [PY007/TinyLlama-1.1B-intermediate-step-240k-503b](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-240k-503b). The dataset used is [openassistant-guananco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco).
-
-#### How to use
-
-Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
-
-https://github.com/mlc-ai/mlc-llm
-
-https://mlc.ai/mlc-llm/docs/deploy/ios.html

TinyLlama-1.1B-Chat-v0.2-q8f16_1-iphone.tar

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b319dee9dd9d5c6d48ae661e02a1efecd9ad4d84ab2625d6abb7ff54ab0ab06a
-size 270577

mlc-chat-config.json

@@ -1,7 +1,7 @@
 {
     "model_lib": "TinyLlama-1.1B-Chat-v0.2-q8f16_1",
     "local_id": "TinyLlama-1.1B-Chat-v0.2-q8f16_1",
-    "conv_template": "llama_default",
+    "conv_template": "chatml",
     "temperature": 0.7,
     "repetition_penalty": 1.0,
     "top_p": 0.95,
@@ -18,4 +18,4 @@
     "model_category": "llama",
     "model_name": "TinyLlama-1.1B-Chat-v0.2",
     "vocab_size": 32003
-}
+}