README.md

---
language:
- en
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- timdettmers/openassistant-guanaco
model-index:
- name: TinyLlama-1.1B-Chat-v0.1
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 14.79
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 3.36
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 0.0
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 0.0
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 3.9
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 1.09
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=TinyLlama/TinyLlama-1.1B-Chat-v0.1
      name: Open LLM Leaderboard
---
<div align="center">

# TinyLlama-1.1B
</div>

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
You will need the transformers>=4.31
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
```python
from transformers import AutoTokenizer
import transformers 
import torch
model = "PY007/TinyLlama-1.1B-Chat-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

prompt = "What are the values in open source projects?"
formatted_prompt = (
    f"### Human: {prompt}### Assistant:"
)


sequences = pipeline(
    formatted_prompt,
    do_sample=True,
    top_k=50,
    top_p = 0.7,
    num_return_sequences=1,
    repetition_penalty=1.1,
    max_new_tokens=500,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_TinyLlama__TinyLlama-1.1B-Chat-v0.1)

|      Metric       |Value|
|-------------------|----:|
|Avg.               | 3.86|
|IFEval (0-Shot)    |14.79|
|BBH (3-Shot)       | 3.36|
|MATH Lvl 5 (4-Shot)| 0.00|
|GPQA (0-shot)      | 0.00|
|MuSR (0-shot)      | 3.90|
|MMLU-PRO (5-shot)  | 1.09|