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, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- 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
|
@@ -416,9 +416,11 @@ class TorchBioBrainDecoder(nn.Module):
|
|
| 416 |
_,
|
| 417 |
bio_embed_dim,
|
| 418 |
) = projected_bio_embeddings.shape
|
| 419 |
-
|
| 420 |
# Insert the bio embeddings at the SEQ token positions
|
| 421 |
processed_tokens_ids = english_token_ids.clone()
|
|
|
|
|
|
|
| 422 |
for bio_seq_num in range(num_bio_sequences):
|
| 423 |
tokens_embeddings, processed_tokens_ids = self.insert_embeddings(
|
| 424 |
processed_tokens_ids,
|
|
@@ -426,6 +428,7 @@ class TorchBioBrainDecoder(nn.Module):
|
|
| 426 |
projected_bio_embeddings[:, bio_seq_num, :, :],
|
| 427 |
bio_seq_num=bio_seq_num,
|
| 428 |
)
|
|
|
|
| 429 |
|
| 430 |
# Regular GPT pass through
|
| 431 |
print("(debug) tokens embeddings shape : ", tokens_embeddings.shape)
|
|
|
|
| 416 |
_,
|
| 417 |
bio_embed_dim,
|
| 418 |
) = projected_bio_embeddings.shape
|
| 419 |
+
|
| 420 |
# Insert the bio embeddings at the SEQ token positions
|
| 421 |
processed_tokens_ids = english_token_ids.clone()
|
| 422 |
+
print("(debug) Inside : processed tokens ids shape : ", processed_tokens_ids.shape)
|
| 423 |
+
print("(debug) Inside : projected bio embeddings shape : ", projected_bio_embeddings.shape)
|
| 424 |
for bio_seq_num in range(num_bio_sequences):
|
| 425 |
tokens_embeddings, processed_tokens_ids = self.insert_embeddings(
|
| 426 |
processed_tokens_ids,
|
|
|
|
| 428 |
projected_bio_embeddings[:, bio_seq_num, :, :],
|
| 429 |
bio_seq_num=bio_seq_num,
|
| 430 |
)
|
| 431 |
+
print("After call : ", tokens_embeddings.shape)
|
| 432 |
|
| 433 |
# Regular GPT pass through
|
| 434 |
print("(debug) tokens embeddings shape : ", tokens_embeddings.shape)
|