Skip to content

Add Step 3.5 Flash model support with MTP #94

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
janhilgard wants to merge 1 commit into from
Closed

Add Step 3.5 Flash model support with MTP #94

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ python examples/tts_multilingual.py --list-languages

### Reasoning Models

Extract the thinking process from reasoning models like Qwen3 and DeepSeek-R1:
Extract the thinking process from reasoning models like Qwen3, DeepSeek-R1, and Step 3.5 Flash:

```bash
# Start server with reasoning parser
Expand All @@ -187,6 +187,7 @@ print("Answer:", response.choices[0].message.content)
|--------|--------|-------------|
| `qwen3` | Qwen3 series | Requires both `<think>` and `</think>` tags |
| `deepseek_r1` | DeepSeek-R1 | Handles implicit `<think>` tag |
| `step3p5` | Step 3.5 Flash | Alias for `deepseek_r1`, `<think>` tags |

### Embeddings

Expand Down
1 change: 1 addition & 0 deletions docs/reference/models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@ Browse thousands of pre-optimized models at: **https://huggingface.co/mlx-commun
| Phi-3 | 3.8B, 14B | 4-bit |
| Granite 3.x, 4.x | Various | 4-bit |
| Nemotron | 3 Nano 30B | 6-bit |
| Step 3.5 | Flash 196B (MoE, 11B active) | 4-bit |

### Recommended Models

Expand Down
Loading
Loading