Instructions to use zai-org/cogagent-chat-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zai-org/cogagent-chat-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zai-org/cogagent-chat-hf", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("zai-org/cogagent-chat-hf", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use zai-org/cogagent-chat-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "zai-org/cogagent-chat-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/cogagent-chat-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/zai-org/cogagent-chat-hf
- SGLang
How to use zai-org/cogagent-chat-hf with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "zai-org/cogagent-chat-hf" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/cogagent-chat-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "zai-org/cogagent-chat-hf" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "zai-org/cogagent-chat-hf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use zai-org/cogagent-chat-hf with Docker Model Runner:
docker model run hf.co/zai-org/cogagent-chat-hf
Commit ·
7201d1c
1
Parent(s): f1ed53e
Update modeling_cogagent.py
Browse files- modeling_cogagent.py +0 -2
modeling_cogagent.py
CHANGED
|
@@ -284,8 +284,6 @@ class CrossAttention(nn.Module):
|
|
| 284 |
self.cross_head_dim = self.cross_compute_hidden_size // self.num_heads
|
| 285 |
self.max_position_embeddings = config.max_position_embeddings
|
| 286 |
|
| 287 |
-
# self.rotary_emb = RotaryEmbedding(self.hidden_size // self.num_heads)
|
| 288 |
-
self.rotary_emb = FastRotaryEmbedding(dim=self.head_dim, pos_idx_in_fp32=False)
|
| 289 |
self.query = nn.Linear(self.hidden_size, self.cross_compute_hidden_size, bias=False)
|
| 290 |
self.key_value = nn.Linear(self.cross_hidden_size, self.cross_compute_hidden_size * 2, bias=False)
|
| 291 |
self.dense = nn.Linear(self.cross_compute_hidden_size, self.hidden_size, bias=False)
|
|
|
|
| 284 |
self.cross_head_dim = self.cross_compute_hidden_size // self.num_heads
|
| 285 |
self.max_position_embeddings = config.max_position_embeddings
|
| 286 |
|
|
|
|
|
|
|
| 287 |
self.query = nn.Linear(self.hidden_size, self.cross_compute_hidden_size, bias=False)
|
| 288 |
self.key_value = nn.Linear(self.cross_hidden_size, self.cross_compute_hidden_size * 2, bias=False)
|
| 289 |
self.dense = nn.Linear(self.cross_compute_hidden_size, self.hidden_size, bias=False)
|