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.

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

compose and model list update #44

Merged
merged 1 commit into from
Jul 5, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 public/docker-compose.yml
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ services:
- perm_storage:/perm_storage
ports:
- 8008:8008
shm_size: "256m"
deploy:
resources:
reservations:
Expand All @@ -15,7 +16,7 @@ services:
count: all
capabilities: [ gpu ]
environment:
- ENTERPRISE_DATABASE_HOST=refact_db
- REFACT_DATABASE_HOST=refact_db
- ENTERPRISE_ADMIN_TOKEN=12345 # change this token to restrict access to the admin panel
links:
- refact_db
Expand Down
58 changes: 32 additions & 26 deletions src/content/docs/supported-models.md
Original file line number Diff line number Diff line change
Expand Up @@ -50,68 +50,68 @@ In Refact self-hosted you can select between the following models:
<td></td>
</tr>
<tr>
<td>deepseek-coder/1.3b/base</td>
<td>starcoder/7b/base</td>
<td>✓</td>
</tr>
<tr>
<td>deepseek-coder/1.3b/vllm</td>
<td></td>
<td>starcoder/7b/vllm</td>
<td></td>
</tr>
<tr>
<td>deepseek-coder/5.7b/mqa-base</td>
<td></td>
<td>starcoder/15b/base</td>
<td></td>
</tr>
<tr>
<td>deepseek-coder/5.7b/vllm</td>
<td></td>
<td>starcoder/15b/plus</td>
<td></td>
</tr>
<tr>
<td>codellama/7b</td>
<td>starcoder2/3b/base</td>
<td>✓</td>
</tr>
<tr>
<td>stable/3b/code</td>
<td></td>
<td>starcoder2/3b/vllm</td>
<td></td>
</tr>
<tr>
<td>starcoder/15b/base</td>
<td></td>
<td>starcoder2/7b/base</td>
<td></td>
</tr>
<tr>
<td>starcoder/15b/plus</td>
<td></td>
<td>starcoder2/7b/vllm</td>
<td></td>
</tr>
<tr>
<td>starcoder/7b/base</td>
<td>starcoder2/15b/base</td>
<td>✓</td>
</tr>
<tr>
<td>starcoder/7b/vllm</td>
<td></td>
<td>deepseek-coder/1.3b/base</td>
<td></td>
</tr>
<tr>
<td>wizardcoder/15b</td>
<td></td>
<td>deepseek-coder/1.3b/vllm</td>
<td></td>
</tr>
<tr>
<td>starcoder2/15b/base</td>
<td>deepseek-coder/5.7b/mqa-base</td>
<td>✓</td>
</tr>
<tr>
<td>starcoder2/3b/base</td>
<td>deepseek-coder/5.7b/vllm</td>
<td>✓</td>
</tr>
<tr>
<td>starcoder2/3b/vllm</td>
<td>codellama/7b</td>
<td>✓</td>
</tr>
<tr>
<td>starcoder2/7b/base</td>
<td></td>
<td>stable/3b/code</td>
<td></td>
</tr>
<tr>
<td>starcoder2/7b/vllm</td>
<td></td>
<td>wizardcoder/15b</td>
<td></td>
</tr>
</tbody>
</table>
Expand Down Expand Up @@ -163,6 +163,12 @@ In Refact self-hosted you can select between the following models:
<tr>
<td>mixtral/8x7b/instruct-v0.1</td>
</tr>
<tr>
<td>llama3/8b/instruct</td>
</tr>
<tr>
<td>llama3/8b/instruct/vllm</td>
</tr>
</tbody>
</table>

Expand Down
Loading