Instructions to use himalaya-ai/himalayagpt-0.5b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use himalaya-ai/himalayagpt-0.5b-it with Transformers:

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

pipe = pipeline("text-generation", model="himalaya-ai/himalayagpt-0.5b-it", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("himalaya-ai/himalayagpt-0.5b-it", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("himalaya-ai/himalayagpt-0.5b-it", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use himalaya-ai/himalayagpt-0.5b-it with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/himalaya-ai/himalayagpt-0.5b-it

SGLang

How to use himalaya-ai/himalayagpt-0.5b-it 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 "himalaya-ai/himalayagpt-0.5b-it" \
    --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": "himalaya-ai/himalayagpt-0.5b-it",
		"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 "himalaya-ai/himalayagpt-0.5b-it" \
        --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": "himalaya-ai/himalayagpt-0.5b-it",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use himalaya-ai/himalayagpt-0.5b-it with Docker Model Runner:
```
docker model run hf.co/himalaya-ai/himalayagpt-0.5b-it
```

himalayagpt-0.5b-it / README.md

HimalayaGPT

Re-export SFT 49164 with HF parity fixes

654ec22 verified 3 months ago

951 Bytes

library_name: transformers
tags:
  - nanochat
  - causal-lm
  - trust-remote-code

local/nanochat-export

Exported from nanochat checkpoints with custom transformers remote code.

Load

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

repo = "local/nanochat-export"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo,
    trust_remote_code=True,
    torch_dtype="auto",
    device_map="auto" if torch.cuda.is_available() else None,
)

prompt = "नेपालको राजधानी "
ids = tok(prompt, return_tensors="pt").input_ids.to(model.device)
out = model.generate(ids, max_new_tokens=64)
print(tok.decode(out[0], skip_special_tokens=True))

Notes

This repo uses custom model/tokenizer code (trust_remote_code=True).
Checkpoint source: sft
Model tag: d15_harl_fulltokens_sdpa_bs32
Step: 49164