Mixtral multipack (#928)

* mixtral multipack

* use mixtral model

* sample yml

* calculate cu_seqlens properly

* use updated flash ettention setting

* attn var checks

* force use of flash attention 2 for packing

* lint

* disable future fix for now

* update support table
This commit is contained in:
Wing Lian
2023-12-09 21:26:30 -05:00
committed by GitHub
parent 03c6318ba3
commit 68b227a7d8
8 changed files with 1793 additions and 25 deletions

View File

@@ -65,19 +65,21 @@ Features:
## Axolotl supports
| | fp16/fp32 | lora | qlora | gptq | gptq w/flash attn | flash attn | xformers attn |
|----------|:----------|:-----|-------|------|-------------------|------------|--------------|
| llama | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Pythia | ✅ | ✅ | ✅ | | | | |
| cerebras | ✅ | ✅ | ✅ | | | | ❓ |
| btlm | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| mpt | ✅ | | | ❌ | ❌ | ❌ | ❓ |
| falcon | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| gpt-j | ✅ | | | ❌ | ❌ | | ❓ |
| XGen | ✅ | | ✅ | | | | |
| phi | ✅ | ✅ | ✅ | | | ❓ | ❓ |
| RWKV | ✅ | ❓ | | ❓ | ❓ | ❓ | |
| Qwen | ✅ | ✅ | ✅ | ❓ | ❓ | ❓ | ❓ |
| | fp16/fp32 | lora | qlora | gptq | gptq w/flash attn | flash attn | xformers attn |
|-------------|:----------|:-----|-------|------|-------------------|------------|--------------|
| llama | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| Mistral | ✅ | ✅ | ✅ | | | | |
| Mixtral-MoE | ✅ | ✅ | ✅ | | | | ❓ |
| Pythia | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| cerebras | ✅ | | | ❌ | ❌ | ❌ | ❓ |
| btlm | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❓ |
| mpt | ✅ | | | ❌ | ❌ | | ❓ |
| falcon | ✅ | | ✅ | | | | |
| gpt-j | ✅ | ✅ | ✅ | | | ❓ | ❓ |
| XGen | ✅ | ❓ | | ❓ | ❓ | ❓ | |
| phi | ✅ | ✅ | ✅ | ❓ | ❓ | ❓ | ❓ |
| RWKV | ✅ | ❓ | ❓ | ❓ | ❓ | ❓ | ❓ |
| Qwen | ✅ | ✅ | ✅ | ❓ | ❓ | ❓ | ❓ |
## Quickstart ⚡