Instructions to use dbishwarup/TagoreGPT-29M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dbishwarup/TagoreGPT-29M with Transformers:

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

pipe = pipeline("text-generation", model="dbishwarup/TagoreGPT-29M")
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("dbishwarup/TagoreGPT-29M")
model = AutoModelForCausalLM.from_pretrained("dbishwarup/TagoreGPT-29M", 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

llama.cpp

How to use dbishwarup/TagoreGPT-29M with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dbishwarup/TagoreGPT-29M:F16
# Run inference directly in the terminal:
llama cli -hf dbishwarup/TagoreGPT-29M:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf dbishwarup/TagoreGPT-29M:F16
# Run inference directly in the terminal:
llama cli -hf dbishwarup/TagoreGPT-29M:F16

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf dbishwarup/TagoreGPT-29M:F16
# Run inference directly in the terminal:
./build/bin/llama cli -hf dbishwarup/TagoreGPT-29M:F16

Use Docker

docker model run hf.co/dbishwarup/TagoreGPT-29M:F16

Llama new
LM Studio
Jan

vLLM

How to use dbishwarup/TagoreGPT-29M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dbishwarup/TagoreGPT-29M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dbishwarup/TagoreGPT-29M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dbishwarup/TagoreGPT-29M:F16

SGLang

How to use dbishwarup/TagoreGPT-29M 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 "dbishwarup/TagoreGPT-29M" \
    --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": "dbishwarup/TagoreGPT-29M",
		"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 "dbishwarup/TagoreGPT-29M" \
        --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": "dbishwarup/TagoreGPT-29M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use dbishwarup/TagoreGPT-29M with Ollama:
```
ollama run hf.co/dbishwarup/TagoreGPT-29M:F16
```
Unsloth Desktop
Docker Model Runner
How to use dbishwarup/TagoreGPT-29M with Docker Model Runner:
```
docker model run hf.co/dbishwarup/TagoreGPT-29M:F16
```

Lemonade

How to use dbishwarup/TagoreGPT-29M with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull dbishwarup/TagoreGPT-29M:F16

Run and chat with the model

lemonade run user.TagoreGPT-29M-F16

List all available models

lemonade list

Atomic Chat

TagoreGPT-29M / README.md

dbishwarup

v8: Ollama / LM Studio read the request (language, type, topic) like the app; 4 Ollama recipes

b0c2a01 verified 1 day ago

preview code

Raw History Blame Contribute Delete

4.31 kB

---
language: [bn, en]
license: cc-by-sa-4.0
pipeline_tag: text-generation
library_name: transformers
tags: [llama, bengali, tagore, poetry, small-model, gguf]
---
# TagoreGPT 29M

A small (29 million parameter) model that writes **poems, songs, stories, letters, essays and plays in the style of
Rabindranath Tagore (1861–1941)**, in **Bengali or English**. Trained from scratch on a laptop.

Sir Rabindranath Tagore (Gurudev) was the first non-European to win the Nobel Prize in Literature (1913, for
*Gitanjali*) and wrote the national anthems of India and Bangladesh.

## How to ask

The model writes from **a topic + hidden labels** (language, type, length, rhyme); it does not read free-form requests.
The chat template in the GGUF does that step for you, like the TagoreGPT app: it finds the language (Bengali letters or
not), the type (poem / song / story / letter / essay / play / novel words) and the topic (the request minus
"write a poem about ..."). Examples that work:

- `write a poem about the river` · `write a song about the rain` · `Write a story about a boatman`
- `নদী নিয়ে একটা কবিতা লেখো` · `বৃষ্টি নিয়ে একটা গান লেখো`

Settings that work well (= the app): temperature 0.75 (poem) / 0.7 (song) / 0.8 (story), top-k 40, top-p 0.95,
min-p 0.02, **repeat penalty 1.3** (last 256 tokens).

### Ollama: type just the topic

Four ready recipes, one per language + type:

```
ollama create tagoregpt-poem-en  -f Modelfile.poem-en    # then: ollama run tagoregpt-poem-en  "The River"
ollama create tagoregpt-story-en -f Modelfile.story-en   #       ollama run tagoregpt-story-en "The old boatman"
ollama create tagoregpt-poem-bn  -f Modelfile.poem-bn    #       ollama run tagoregpt-poem-bn  "নদী"
ollama create tagoregpt-song-bn  -f Modelfile.song-bn    #       ollama run tagoregpt-song-bn  "বৃষ্টি"
```

### LM Studio / llama.cpp

- File: `tagoregpt-29m-f16.gguf` (Llama layout, 85 MB). Its chat template reads the request as described above.
- llama.cpp: `llama-cli -m tagoregpt-29m-f16.gguf -cnv --jinja --temp 0.75 --top-k 40 --repeat-penalty 1.3`
- English is weaker than Bengali in this version; the TagoreGPT app adds topic guidance and line rules that plain
  llama.cpp / Ollama / LM Studio do not have.

### Transformers

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("PATH_OR_REPO")
model = AutoModelForCausalLM.from_pretrained("PATH_OR_REPO")
ids = tok.apply_chat_template([{"role": "user", "content": "write a poem about the river"}], return_tensors="pt")
out = model.generate(ids, max_new_tokens=300)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
```

## What it cannot do

- It is not a chatbot: it does not answer questions, explain, or translate. It only writes.
- Topics given in English for a Bengali piece are not translated outside the TagoreGPT app.
- It sees about 1,024 word pieces (~3,300 letters) at a time; longer pieces can wander. (The TagoreGPT app also
  keeps the title and opening paragraph in view; plain llama.cpp / LM Studio do not.)
- It is small: lines can be beautiful or nonsensical. It is a style imitation, never Tagore's real words.

## Training

- Llama layout: 8 layers, width 512, 8 heads, SwiGLU 1344, rotary positions, tied embeddings. 8,000 SentencePiece word pieces (Bengali + English).
- Phase 1 (warm-up): simple practice stories (TinyStories, CDLA-Sharing-1.0; Regional-TinyStories Bengali, Apache-2.0),
  other Bengali writers (Bengali Wikisource) + 19th-century English (Project Gutenberg) + Tagore.
- Phase 2: Tagore only (Bengali scans from the Digital Library of India / Internet Archive, English from Project Gutenberg).
- Every training piece starts with hidden labels (language, type, author); its title and opening paragraph stay in view, which keeps long pieces on their hero and topic.
- Weights in this release: tagore step -1. Unseen-text loss per word piece: tagore_en: 3.229, tagore_bn: 3.677.

## Data and licence

Tagore's works are in the public domain. The Bengali warm-up text comes from **Bengali Wikisource**
(CC BY-SA 4.0), so this model is released under **CC BY-SA 4.0**. English text from Project Gutenberg (public domain).

	---
	language: [bn, en]
	license: cc-by-sa-4.0
	pipeline_tag: text-generation
	library_name: transformers
	tags: [llama, bengali, tagore, poetry, small-model, gguf]
	---

	# TagoreGPT 29M

	A small (29 million parameter) model that writes **poems, songs, stories, letters, essays and plays in the style of
	Rabindranath Tagore (1861–1941), in Bengali or English**. Trained from scratch on a laptop.

	Sir Rabindranath Tagore (Gurudev) was the first non-European to win the Nobel Prize in Literature (1913, for
	Gitanjali) and wrote the national anthems of India and Bangladesh.

	## How to ask

	The model writes from a topic + hidden labels (language, type, length, rhyme); it does not read free-form requests.
	The chat template in the GGUF does that step for you, like the TagoreGPT app: it finds the language (Bengali letters or
	not), the type (poem / song / story / letter / essay / play / novel words) and the topic (the request minus
	"write a poem about ..."). Examples that work:

	- `write a poem about the river` · `write a song about the rain` · `Write a story about a boatman`
	- `নদী নিয়ে একটা কবিতা লেখো` · `বৃষ্টি নিয়ে একটা গান লেখো`

	Settings that work well (= the app): temperature 0.75 (poem) / 0.7 (song) / 0.8 (story), top-k 40, top-p 0.95,
	min-p 0.02, repeat penalty 1.3 (last 256 tokens).

	### Ollama: type just the topic

	Four ready recipes, one per language + type:

	```
	ollama create tagoregpt-poem-en -f Modelfile.poem-en # then: ollama run tagoregpt-poem-en "The River"
	ollama create tagoregpt-story-en -f Modelfile.story-en # ollama run tagoregpt-story-en "The old boatman"
	ollama create tagoregpt-poem-bn -f Modelfile.poem-bn # ollama run tagoregpt-poem-bn "নদী"
	ollama create tagoregpt-song-bn -f Modelfile.song-bn # ollama run tagoregpt-song-bn "বৃষ্টি"
	```

	### LM Studio / llama.cpp

	- File: `tagoregpt-29m-f16.gguf` (Llama layout, 85 MB). Its chat template reads the request as described above.
	- llama.cpp: `llama-cli -m tagoregpt-29m-f16.gguf -cnv --jinja --temp 0.75 --top-k 40 --repeat-penalty 1.3`
	- English is weaker than Bengali in this version; the TagoreGPT app adds topic guidance and line rules that plain
	llama.cpp / Ollama / LM Studio do not have.

	### Transformers

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM
	tok = AutoTokenizer.from_pretrained("PATH_OR_REPO")
	model = AutoModelForCausalLM.from_pretrained("PATH_OR_REPO")
	ids = tok.apply_chat_template([{"role": "user", "content": "write a poem about the river"}], return_tensors="pt")
	out = model.generate(ids, max_new_tokens=300)
	print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
	```

	## What it cannot do

	- It is not a chatbot: it does not answer questions, explain, or translate. It only writes.
	- Topics given in English for a Bengali piece are not translated outside the TagoreGPT app.
	- It sees about 1,024 word pieces (~3,300 letters) at a time; longer pieces can wander. (The TagoreGPT app also
	keeps the title and opening paragraph in view; plain llama.cpp / LM Studio do not.)
	- It is small: lines can be beautiful or nonsensical. It is a style imitation, never Tagore's real words.

	## Training

	- Llama layout: 8 layers, width 512, 8 heads, SwiGLU 1344, rotary positions, tied embeddings. 8,000 SentencePiece word pieces (Bengali + English).
	- Phase 1 (warm-up): simple practice stories (TinyStories, CDLA-Sharing-1.0; Regional-TinyStories Bengali, Apache-2.0),
	other Bengali writers (Bengali Wikisource) + 19th-century English (Project Gutenberg) + Tagore.
	- Phase 2: Tagore only (Bengali scans from the Digital Library of India / Internet Archive, English from Project Gutenberg).
	- Every training piece starts with hidden labels (language, type, author); its title and opening paragraph stay in view, which keeps long pieces on their hero and topic.
	- Weights in this release: tagore step -1. Unseen-text loss per word piece: tagore_en: 3.229, tagore_bn: 3.677.

	## Data and licence

	Tagore's works are in the public domain. The Bengali warm-up text comes from Bengali Wikisource
	(CC BY-SA 4.0), so this model is released under CC BY-SA 4.0. English text from Project Gutenberg (public domain).