Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


TinyLlama-1.1B-intermediate-step-1431k-3T - GGUF
- Model creator: https://huggingface.co/TinyLlama/
- Original model: https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q2_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q2_K.gguf) | Q2_K | 0.4GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_XS.gguf) | IQ3_XS | 0.44GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_S.gguf) | IQ3_S | 0.47GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_S.gguf) | Q3_K_S | 0.47GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.IQ3_M.gguf) | IQ3_M | 0.48GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K.gguf) | Q3_K | 0.51GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_M.gguf) | Q3_K_M | 0.51GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q3_K_L.gguf) | Q3_K_L | 0.55GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.IQ4_XS.gguf) | IQ4_XS | 0.57GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_0.gguf) | Q4_0 | 0.59GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.IQ4_NL.gguf) | IQ4_NL | 0.6GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K_S.gguf) | Q4_K_S | 0.6GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K.gguf) | Q4_K | 0.62GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_K_M.gguf) | Q4_K_M | 0.62GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q4_1.gguf) | Q4_1 | 0.65GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_0.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_0.gguf) | Q5_0 | 0.71GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K_S.gguf) | Q5_K_S | 0.71GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K.gguf) | Q5_K | 0.73GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_K_M.gguf) | Q5_K_M | 0.73GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_1.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q5_1.gguf) | Q5_1 | 0.77GB |
| [TinyLlama-1.1B-intermediate-step-1431k-3T.Q6_K.gguf](https://huggingface.co/RichardErkhov/TinyLlama_-_TinyLlama-1.1B-intermediate-step-1431k-3T-gguf/blob/main/TinyLlama-1.1B-intermediate-step-1431k-3T.Q6_K.gguf) | Q6_K | 0.84GB |




Original model description:
---
license: apache-2.0
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
language:
- en
---
<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 Collection
This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.

#### Eval

| Model                                     | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
| Pythia-1.0B                               |        300B     | 47.16     | 31.40| 53.43      | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
| TinyLlama-1.1B-intermediate-step-50K-104b |        103B     | 43.50     | 29.80| 53.28      | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
| TinyLlama-1.1B-intermediate-step-240k-503b|        503B     | 49.56     |31.40 |55.80       |26.54  |48.32  |56.91  |69.42  | 48.28 |
| TinyLlama-1.1B-intermediate-step-480k-1007B |     1007B     | 52.54     | 33.40 | 55.96      | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
| TinyLlama-1.1B-intermediate-step-715k-1.5T |     1.5T     | 53.68     | 35.20 | 58.33      | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
| TinyLlama-1.1B-intermediate-step-955k-2T |     2T     | 54.63     | 33.40 | 56.83      | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
| TinyLlama-1.1B-intermediate-step-1195k-2.5T              |     2.5T     | 58.96     | 34.40 | 58.72      | 31.91 | 56.78 | 63.21 | 73.07 | 53.86|
| TinyLlama-1.1B-intermediate-step-1431k-3T |     3T     | 59.20     | 36.00 | 59.12      | 30.12 | 55.25 | 57.83 | 73.29 | 52.99|