Skip to content
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

Edit qwen-2.5-coder-32b, for support 4 and 8bit version #438

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Edit qwen-2.5-coder-32b, for support 4 and 8bit version #438

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 exo/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,8 @@
"qwen-2.5-coder-3b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-3B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=36),},
"qwen-2.5-coder-7b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-7B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=28),},
"qwen-2.5-coder-14b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-14B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=48),},
"qwen-2.5-coder-32b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-32B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=64),},
"qwen-2.5-coder-32b-4bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-32B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=64),},
"qwen-2.5-coder-32b-8bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Coder-32B-Instruct-8bit", start_layer=0, end_layer=0, n_layers=64),},
"qwen-2.5-7b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-7B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=28),},
"qwen-2.5-math-7b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-Math-7B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=28),},
"qwen-2.5-14b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Qwen2.5-14B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=48),},
Expand Down
5 changes: 3 additions & 2 deletions exo/tinychat/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,8 +50,9 @@
<option value="qwen-2.5-coder-3b">Qwen 2.5 Coder 3B</option>
<option value="qwen-2.5-coder-7b">Qwen 2.5 Coder 7B</option>
<option value="qwen-2.5-coder-14b">Qwen 2.5 Coder 14B</option>
<option value="qwen-2.5-coder-32b">Qwen 2.5 Coder 32B</option>
<option value="qwen-2.5-7b">Qwen 2.5 7B</option>
<option value="qwen-2.5-coder-32b-4bit">Qwen 2.5 Coder 32B (4-bit)</option>
<option value="qwen-2.5-coder-32b-8bit">Qwen 2.5 Coder 32B (8-bit)</option>
<option value="qwen-2.5-7b">Qwen 2.5 7B</option>
<option value="qwen-2.5-math-7b">Qwen 2.5 7B (Math)</option>
<option value="qwen-2.5-14b">Qwen 2.5 14B</option>
<option value="qwen-2.5-72b">Qwen 2.5 72B</option>
Expand Down