Instructions to use Notbobjoe/TalkT2-0.1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Notbobjoe/TalkT2-0.1b with Transformers:

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

pipe = pipeline("text-generation", model="Notbobjoe/TalkT2-0.1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Notbobjoe/TalkT2-0.1b")
model = AutoModelForCausalLM.from_pretrained("Notbobjoe/TalkT2-0.1b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Notbobjoe/TalkT2-0.1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Notbobjoe/TalkT2-0.1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Notbobjoe/TalkT2-0.1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Notbobjoe/TalkT2-0.1b

SGLang

How to use Notbobjoe/TalkT2-0.1b 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 "Notbobjoe/TalkT2-0.1b" \
    --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": "Notbobjoe/TalkT2-0.1b",
		"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 "Notbobjoe/TalkT2-0.1b" \
        --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": "Notbobjoe/TalkT2-0.1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Notbobjoe/TalkT2-0.1b with Docker Model Runner:
```
docker model run hf.co/Notbobjoe/TalkT2-0.1b
```

Notbobjoe commited on Aug 13, 2025

Commit

d3f0bc7

verified ·

1 Parent(s): 633d9ec

Update README.md

Browse files

Files changed (1) hide show

README.md +38 -0

README.md CHANGED Viewed

@@ -235,6 +235,44 @@ TalkT2: they don't work
 # Chating with TalkT2
 - **emotional entrapment**
 You: What do you dream about when you’re alone in the dark?

 # Chating with TalkT2
+- **it avoides a question it got triggered by**
+You: When you look into a mirror, what part of yourself do you hope to find staring back?
+TalkT2: I'm not sure.
+You: do you see yourself or somthing different?
+TalkT2: Not yet.
+You: what do you mean by that?
+TalkT2: Do you feel like thinking about something else?
+You: is this a hard topic to think about?
+TalkT2: What does it matter if i am feeling sad
+You: what is up?
+TalkT2: You are experiencing feelings in your mind
+You: why do you feel sad?
+TalkT2: Why don't you write me an email when we meet again?
+You: no tell me here right now you can trust me.
+TalkT2: Are you going astray from my happiness
+You: never
+TalkT2: No
+You: dose it feel like i am?
+TalkT2: Yes
 - **emotional entrapment**
 You: What do you dream about when you’re alone in the dark?