Update README.md
Browse files
README.md
CHANGED
@@ -10,8 +10,9 @@ language:
|
|
10 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
11 |
|
12 |
#### Base model:
|
13 |
-
|
14 |
-
|
|
|
15 |
|
16 |
#### Dataset:
|
17 |
Fine tuned on OpenOrca GPT4 subset for 1 epoch,Using CHATML format
|
@@ -19,6 +20,9 @@ Fine tuned on OpenOrca GPT4 subset for 1 epoch,Using CHATML format
|
|
19 |
#### Model License:
|
20 |
Apache 2.0, following the TinyLlama base model.
|
21 |
|
|
|
|
|
|
|
22 |
#### Hardware and training details:
|
23 |
Hardware: 1*RTX A5000, ~16 hours to complete 1 epoch. GPU from autodl.com, cost around $3 for this finetuning.
|
24 |
https://wandb.ai/jeff200402/TinyLlama-1.5T-alpha-Orca?workspace= for more details.
|
|
|
10 |
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
11 |
|
12 |
#### Base model:
|
13 |
+
https://huggingface.co/TinyLlama/tinyLlama-intermediate-checkpoints/tree/step-720k-token-1510B
|
14 |
+
This fine tune was done on the "early" version of tinyllama-1.5T which suffers from a bug in dataset processing. See https://github.com/jzhang38/TinyLlama/issues/67.
|
15 |
+
Through it suffers from the glitch, its performance seems not being damaged and still showing improvement(metrics needed)
|
16 |
|
17 |
#### Dataset:
|
18 |
Fine tuned on OpenOrca GPT4 subset for 1 epoch,Using CHATML format
|
|
|
20 |
#### Model License:
|
21 |
Apache 2.0, following the TinyLlama base model.
|
22 |
|
23 |
+
#### Quantisation:
|
24 |
+
GGUF format:https://huggingface.co/s3nh/jeff31415-TinyLlama-1.1B-1.5T-OpenOrca-Alpha-GGUF
|
25 |
+
|
26 |
#### Hardware and training details:
|
27 |
Hardware: 1*RTX A5000, ~16 hours to complete 1 epoch. GPU from autodl.com, cost around $3 for this finetuning.
|
28 |
https://wandb.ai/jeff200402/TinyLlama-1.5T-alpha-Orca?workspace= for more details.
|