Instructions to use hishab/titulm-mpt-1b-v2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hishab/titulm-mpt-1b-v2.0 with Transformers:

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

pipe = pipeline("text-generation", model="hishab/titulm-mpt-1b-v2.0", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hishab/titulm-mpt-1b-v2.0", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("hishab/titulm-mpt-1b-v2.0", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hishab/titulm-mpt-1b-v2.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hishab/titulm-mpt-1b-v2.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hishab/titulm-mpt-1b-v2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hishab/titulm-mpt-1b-v2.0

SGLang

How to use hishab/titulm-mpt-1b-v2.0 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 "hishab/titulm-mpt-1b-v2.0" \
    --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": "hishab/titulm-mpt-1b-v2.0",
		"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 "hishab/titulm-mpt-1b-v2.0" \
        --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": "hishab/titulm-mpt-1b-v2.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hishab/titulm-mpt-1b-v2.0 with Docker Model Runner:
```
docker model run hf.co/hishab/titulm-mpt-1b-v2.0
```

nielsr HF Staff commited on Jun 9, 2025

Commit

7c96374

verified ·

1 Parent(s): bedfa50

Add library_name and link to code

Browse files

This PR adds the `library_name` tag to the model card metadata, specifying that the model uses the `transformers` library. A link to the Github repository is also added for easier access to the codebase.

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -1,5 +1,4 @@
 ---
-license: apache-2.0
 datasets:
 - togethercomputer/RedPajama-Data-V2
 - uonlp/CulturaX
@@ -7,7 +6,9 @@ datasets:
 language:
 - en
 - bn
 pipeline_tag: text-generation
 ---
 # TituLM-1B-ENBN-V1
@@ -95,3 +96,6 @@ print(en_output)
   publisher = {HuggingFace Models},
   howpublished = {https://huggingface.co/hishab/titulm-1b-enbn-v1},
 }

 ---
 datasets:
 - togethercomputer/RedPajama-Data-V2
 - uonlp/CulturaX
 language:
 - en
 - bn
+license: apache-2.0
 pipeline_tag: text-generation
+library_name: transformers
 ---
 # TituLM-1B-ENBN-V1
   publisher = {HuggingFace Models},
   howpublished = {https://huggingface.co/hishab/titulm-1b-enbn-v1},
 }
+```
+Code: https://github.com/Hishab/titulm