Instructions to use InstaDeepAI/ChatNT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InstaDeepAI/ChatNT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="InstaDeepAI/ChatNT", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("InstaDeepAI/ChatNT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use InstaDeepAI/ChatNT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "InstaDeepAI/ChatNT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "InstaDeepAI/ChatNT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/InstaDeepAI/ChatNT
- SGLang
How to use InstaDeepAI/ChatNT 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 "InstaDeepAI/ChatNT" \ --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": "InstaDeepAI/ChatNT", "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 "InstaDeepAI/ChatNT" \ --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": "InstaDeepAI/ChatNT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use InstaDeepAI/ChatNT with Docker Model Runner:
docker model run hf.co/InstaDeepAI/ChatNT
Update chatNT.py
Browse files
chatNT.py
CHANGED
|
@@ -590,7 +590,6 @@ class TorchMultiOmicsModel(PreTrainedModel):
|
|
| 590 |
def __init__(self, config: ChatNTConfig) -> None:
|
| 591 |
print("(debug) Entering in class")
|
| 592 |
if isinstance(config, dict):
|
| 593 |
-
print("(debug) going in if condition")
|
| 594 |
# If config is a dictionary instead of ChatNTConfig (which can happen
|
| 595 |
# depending how the config was saved), we convert it to the config
|
| 596 |
config["gpt_config"]["rope_config"] = RotaryEmbeddingConfig(
|
|
@@ -598,14 +597,24 @@ class TorchMultiOmicsModel(PreTrainedModel):
|
|
| 598 |
)
|
| 599 |
config["gpt_config"] = GptConfig(**config["gpt_config"])
|
| 600 |
config["esm_config"] = ESMTransformerConfig(**config["esm_config"])
|
| 601 |
-
print("(debug) Type esm_config : ", type(config["esm_config"]))
|
| 602 |
-
print("(debug) esm_config : ", config["esm_config"])
|
| 603 |
config["perceiver_resampler_config"] = PerceiverResamplerConfig(
|
| 604 |
**config["perceiver_resampler_config"]
|
| 605 |
)
|
| 606 |
config = ChatNTConfig(**config) # type: ignore
|
| 607 |
-
print("(debug) Type config : ", type(config))
|
| 608 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 609 |
print("(debug) config : ", config)
|
| 610 |
print("(debug) config type : ", type(config))
|
| 611 |
print("(debug) gpt config : ", config.gpt_config)
|
|
|
|
| 590 |
def __init__(self, config: ChatNTConfig) -> None:
|
| 591 |
print("(debug) Entering in class")
|
| 592 |
if isinstance(config, dict):
|
|
|
|
| 593 |
# If config is a dictionary instead of ChatNTConfig (which can happen
|
| 594 |
# depending how the config was saved), we convert it to the config
|
| 595 |
config["gpt_config"]["rope_config"] = RotaryEmbeddingConfig(
|
|
|
|
| 597 |
)
|
| 598 |
config["gpt_config"] = GptConfig(**config["gpt_config"])
|
| 599 |
config["esm_config"] = ESMTransformerConfig(**config["esm_config"])
|
|
|
|
|
|
|
| 600 |
config["perceiver_resampler_config"] = PerceiverResamplerConfig(
|
| 601 |
**config["perceiver_resampler_config"]
|
| 602 |
)
|
| 603 |
config = ChatNTConfig(**config) # type: ignore
|
|
|
|
| 604 |
|
| 605 |
+
else:
|
| 606 |
+
if isinstance(config.gpt_config, dict):
|
| 607 |
+
config.gpt_config["rope_config"] = RotaryEmbeddingConfig(
|
| 608 |
+
**config.gpt_config.["rope_config"]
|
| 609 |
+
)
|
| 610 |
+
config.gpt_config = GptConfig(**config.gpt_config)
|
| 611 |
+
|
| 612 |
+
if isinstance(config.esm_config, dict):
|
| 613 |
+
config.esm_config = ESMTransformerConfig(**config.esm_config)
|
| 614 |
+
|
| 615 |
+
if isinstance(config.perceiver_resampler_config, dict):
|
| 616 |
+
config.esm_config = PerceiverResamplerConfig(**config.perceiver_resampler_config)
|
| 617 |
+
|
| 618 |
print("(debug) config : ", config)
|
| 619 |
print("(debug) config type : ", type(config))
|
| 620 |
print("(debug) gpt config : ", config.gpt_config)
|