Instructions to use CogwiseAI/testchatexample with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CogwiseAI/testchatexample with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CogwiseAI/testchatexample", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("CogwiseAI/testchatexample", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CogwiseAI/testchatexample with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CogwiseAI/testchatexample" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CogwiseAI/testchatexample", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CogwiseAI/testchatexample
- SGLang
How to use CogwiseAI/testchatexample 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 "CogwiseAI/testchatexample" \ --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": "CogwiseAI/testchatexample", "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 "CogwiseAI/testchatexample" \ --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": "CogwiseAI/testchatexample", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CogwiseAI/testchatexample with Docker Model Runner:
docker model run hf.co/CogwiseAI/testchatexample
Update config.json
Browse files- config.json +5 -5
config.json
CHANGED
|
@@ -7,8 +7,8 @@
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"auto_map": {
|
| 10 |
-
"AutoConfig": "
|
| 11 |
-
"AutoModelForCausalLM": "
|
| 12 |
},
|
| 13 |
"bias": false,
|
| 14 |
"bos_token_id": 11,
|
|
@@ -22,8 +22,8 @@
|
|
| 22 |
"n_head": 71,
|
| 23 |
"n_layer": 32,
|
| 24 |
"parallel_attn": true,
|
| 25 |
-
"torch_dtype": "
|
| 26 |
-
"transformers_version": "4.
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 65024
|
| 29 |
-
}
|
|
|
|
| 7 |
],
|
| 8 |
"attention_dropout": 0.0,
|
| 9 |
"auto_map": {
|
| 10 |
+
"AutoConfig": "configuration_RW.RWConfig",
|
| 11 |
+
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
|
| 12 |
},
|
| 13 |
"bias": false,
|
| 14 |
"bos_token_id": 11,
|
|
|
|
| 22 |
"n_head": 71,
|
| 23 |
"n_layer": 32,
|
| 24 |
"parallel_attn": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.27.4",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 65024
|
| 29 |
+
}
|