Commit
•
5b4d67e
1
Parent(s):
e637c65
ADD GGUF (#8)
Browse files- ADD GGUF (1f7460f994d73ff45efcba6404d7a3336f31f645)
README.md
CHANGED
|
@@ -24,6 +24,10 @@ This model extends LLama-3 8B's context length from 8k to > 160K, developed by G
|
|
| 24 |
|
| 25 |
We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster.
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
**Data:**
|
| 28 |
|
| 29 |
For training data, we generate long contexts by augmenting [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B).
|
|
|
|
| 24 |
|
| 25 |
We build on top of the EasyContext Blockwise RingAttention library [3] to scalably and efficiently train on contexts up to 262144 tokens on [Crusoe Energy](https://huggingface.co/crusoeai) high performance L40S cluster.
|
| 26 |
|
| 27 |
+
**Quantized versions and GGUF**
|
| 28 |
+
|
| 29 |
+
GGUF is available on on Crusoe's huggingface account. Check it out here: [crusoeai/Llama-3-8B-Instruct-262k-GGUF](https://huggingface.co/crusoeai/Llama-3-8B-Instruct-262k-GGUF)
|
| 30 |
+
|
| 31 |
**Data:**
|
| 32 |
|
| 33 |
For training data, we generate long contexts by augmenting [SlimPajama](https://huggingface.co/datasets/cerebras/SlimPajama-627B).
|