Instructions to use DedeProGames/NTX-350m-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DedeProGames/NTX-350m-Preview with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DedeProGames/NTX-350m-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DedeProGames/NTX-350m-Preview")
model = AutoModelForCausalLM.from_pretrained("DedeProGames/NTX-350m-Preview", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use DedeProGames/NTX-350m-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DedeProGames/NTX-350m-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/NTX-350m-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DedeProGames/NTX-350m-Preview

SGLang

How to use DedeProGames/NTX-350m-Preview 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 "DedeProGames/NTX-350m-Preview" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/NTX-350m-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "DedeProGames/NTX-350m-Preview" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DedeProGames/NTX-350m-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use DedeProGames/NTX-350m-Preview with Docker Model Runner:
```
docker model run hf.co/DedeProGames/NTX-350m-Preview
```

DedeProGames commited on Apr 18

Commit

c1ffe4e

verified ·

1 Parent(s): ee557fa

Ajusta model card para DedeProGames/NTX-350m-Preview

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 base_model: LiquidAI/LFM2.5-350M
 library_name: transformers
-model_name: lfm25_350m_grape_fft
 tags:
 - generated_from_trainer
 - sft
@@ -10,7 +10,7 @@ tags:
 licence: license
 ---
-# Model Card for lfm25_350m_grape_fft
 This model is a fine-tuned version of [LiquidAI/LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -21,7 +21,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
@@ -56,4 +56,4 @@ Cite TRL as:
 	publisher    = {GitHub},
 	howpublished = {\url{https://github.com/huggingface/trl}}
 }
-```

 ---
 base_model: LiquidAI/LFM2.5-350M
 library_name: transformers
+model_name: NTX-350m-Preview
 tags:
 - generated_from_trainer
 - sft
 licence: license
 ---
+# Model Card for NTX-350m-Preview
 This model is a fine-tuned version of [LiquidAI/LFM2.5-350M](https://huggingface.co/LiquidAI/LFM2.5-350M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="DedeProGames/NTX-350m-Preview", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 	publisher    = {GitHub},
 	howpublished = {\url{https://github.com/huggingface/trl}}
 }
+```