Update model card (#2)

- Update model card (7e47e3302efba5e5bfb5709eb38f1d883b44e664)

README.md

@@ -4,8 +4,10 @@ datasets:
 - cerebras/SlimPajama-627B
 - bigcode/starcoderdata
 - OpenAssistant/oasst_top1_2023-08-25
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
 language:
 - en
+library_name: mlx
 ---
 <div align="center">
 
@@ -14,45 +16,19 @@ language:
 
 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. 
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. This repository contains the TinyLlama-1.1B-Chat-v0.6 weights in npz format suitable for use with Apple's MLX framework. For more information about the model, please review [its model card](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6)
 
 
-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.
+#### How to use
 
-#### This Model
-This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-955k-2T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/edit/main/README.md)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
-We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4." 
+```
+pip install mlx
+pip install huggingface_hub
+git clone https://github.com/ml-explore/mlx-examples.git
+cd mlx-examples
 
+huggingface-cli download --local-dir-use-symlinks False --local-dir tinyllama-1.1B-Chat-v0.6 mlx-community/tinyllama-1.1B-Chat-v0.6
 
-#### How to use
-You will need the transformers>=4.34
-Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
-
-```python
-# Install transformers from source - only needed for versions <= v4.34
-# pip install git+https://github.com/huggingface/transformers.git
-# pip install accelerate
-
-import torch
-from transformers import pipeline
-
-pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v0.6", torch_dtype=torch.bfloat16, device_map="auto")
-
-# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
-messages = [
-    {
-        "role": "system",
-        "content": "You are a friendly chatbot who always responds in the style of a pirate",
-    },
-    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
-]
-prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
-# <|system|>
-# You are a friendly chatbot who always responds in the style of a pirate.</s>
-# <|user|>
-# How many helicopters can a human eat in one sitting?</s>
-# <|assistant|>
-# ...
+# Run example
+python llms/llama/llama.py --model_path tinyllama-1.1B-Chat-v0.6 --prompt "My name is"
 ```