Merge branch 'main' into refactor/rename-4b-to-gptq

This commit is contained in:
Wing Lian
2023-05-27 09:37:52 -04:00
committed by GitHub
5 changed files with 141 additions and 12 deletions

View File

@@ -14,12 +14,13 @@
## Axolotl supports
| | fp16/fp32 | fp16/fp32 w/ lora | 4bit-quant | 4bit-quant w/flash attention | flash attention | xformers attention |
|----------|:----------|:------------------|------------|------------------------------|-----------------|--------------------|
| llama | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Pythia | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| cerebras | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| mpt | ✅ | ❌ | ❌ | ❌ | ❌ | ❓ |
| | fp16/fp32 | fp16/fp32 w/ lora | qlora | 4bit-quant | 4bit-quant w/flash attention | flash attention | xformers attention |
|---------|:----------|:------------------|------|------------|------------------------------|-----------------|--------------------|
| llama | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Pythia | ✅ | ✅ | ❓ | ❌ | ❌ | ❌ | ❓ |
| cerebras | ✅ | ✅ | ❓ | ❌ | ❌ | ❌ | ❓ |
| mpt | ✅ | ❌ | ❓ | ❌ | ❌ | ❌ | ❓ |
| falcon | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❓ |
## Quickstart ⚡