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

[WIP] Add support for new models #1391

Closed
wants to merge 12 commits into from
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -52,9 +52,9 @@ The following Environment Variables are available:
| Variable Name | Description | Default Value |
|-----------------------|---------------------------------------------------------|--------------------------------------|
| `SERGE_DATABASE_URL` | Database connection string | `sqlite:////data/db/sql_app.db` |
| `SERGE_JWT_SECRET` | Key for auth token encryption. Use a random string | `uF7FGN5uzfGdFiPzR` |
| `SERGE_JWT_SECRET` | Key for auth token encryption. Use a random string | `uF7FGN5uzfGdFiPzR` |
| `SERGE_SESSION_EXPIRY`| Duration in minutes before a user must reauthenticate | `60` |
| `NODE_ENV` | Node.js running environment | `production` |
| `NODE_ENV` | Node.js running environment | `production` |

## 🖥️ Windows

Expand Down Expand Up @@ -83,7 +83,7 @@ Instructions for setting up Serge on Kubernetes can be found in the [wiki](https
| **Medalpaca** | 13B |
| **Medicine** | Chat, LLM |
| **Meditron** | 7B, 7B-Chat, 70B |
| **Meta-LlaMA-3** | 8B, 8B-Instruct, 70B, 70B-Instruct |
| **Meta-LlaMA-3** | 3-8B, 3.1-8B, 3-8B-Instruct, 3.1-8B-Instruct, 3-70B, 3.1-70B, 3-70B-Instruct, 3.1-70B-Instruct |
| **Mistral** | 7B-V0.1, 7B-Instruct-v0.2, 7B-OpenOrca |
| **MistralLite** | 7B |
| **Mixtral** | 8x7B-v0.1, 8x7B-Dolphin-2.7, 8x7B-Instruct-v0.1 |
Expand Down
44 changes: 44 additions & 0 deletions api/src/serge/data/models.json
Original file line number Diff line number Diff line change
Expand Up @@ -605,6 +605,17 @@
}
]
},
{
"name": "Meta-Llama-3_1-8B",
"repo": "QuantFactory/Meta-Llama-3.1-8B-GGUF",
"files": [
{
"name": "q4_K_M",
"filename": "Meta-Llama-3.1-8B.Q4_K_M.gguf",
"disk_space": 4920733856.0
}
]
},
{
"name": "Meta-Llama-3-8B-Instruct",
"repo": "QuantFactory/Meta-Llama-3-8B-Instruct-GGUF",
Expand All @@ -616,6 +627,17 @@
}
]
},
{
"name": "Meta-Llama-3_1-8B-Instruct",
"repo": "QuantFactory/Meta-Llama-3.1-8B-Instruct-GGUF",
"files": [
{
"name": "q4_K_M",
"filename": "Meta-Llama-3.1-8B-Instruct.Q4_K_M.gguf",
"disk_space": 4920734240.0
}
]
},
{
"name": "Meta-Llama-3-70B",
"repo": "NousResearch/Meta-Llama-3-70B-GGUF",
Expand All @@ -627,6 +649,17 @@
}
]
},
{
"name": "Meta-Llama-3_1-70B",
"repo": "mradermacher/Meta-Llama-3.1-70B-GGUF",
"files": [
{
"name": "q4_K_M",
"filename": "Meta-Llama-3.1-70B.Q4_K_M.gguf",
"disk_space": 42520393600.0
}
]
},
{
"name": "Meta-Llama-3-70B-Instruct",
"repo": "QuantFactory/Meta-Llama-3-70B-Instruct-GGUF",
Expand All @@ -637,6 +670,17 @@
"disk_space": 42520906208.0
}
]
},
{
"name": "Meta-Llama-3_1-70B-Instruct",
"repo": "mradermacher/Meta-Llama-3.1-70B-Instruct-GGUF",
"files": [
{
"name": "q4_K_M",
"filename": "Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf",
"disk_space": 42520394080.0
}
]
}
]
},
Expand Down
2 changes: 1 addition & 1 deletion scripts/serge.env
Original file line number Diff line number Diff line change
@@ -1,3 +1,3 @@
LLAMA_PYTHON_VERSION=0.2.82
LLAMA_PYTHON_VERSION=0.2.84
SERGE_ENABLE_IPV4=true
SERGE_ENABLE_IPV6=false