Instructions to use juinron/Hummingbird-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juinron/Hummingbird-V1 with Transformers:

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

pipe = pipeline("text-generation", model="juinron/Hummingbird-V1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("juinron/Hummingbird-V1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use juinron/Hummingbird-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juinron/Hummingbird-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juinron/Hummingbird-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/juinron/Hummingbird-V1

SGLang

How to use juinron/Hummingbird-V1 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 "juinron/Hummingbird-V1" \
    --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": "juinron/Hummingbird-V1",
		"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 "juinron/Hummingbird-V1" \
        --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": "juinron/Hummingbird-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use juinron/Hummingbird-V1 with Docker Model Runner:
```
docker model run hf.co/juinron/Hummingbird-V1
```

Hummingbird-V1 / training /provenance.json

juinron

Release Hummingbird-V1 500M natural continuation checkpoint

d03200e verified 4 days ago

Raw

History Blame Contribute Delete

2.25 kB

	{
	"base_checkpoint": "artifacts/runs/variant_v1_muon_500m/checkpoint-tokens-1500000000",
	"base_token_presentations": 1500000000,
	"checkpoint_selection": {
	"evaluated_continuation_checkpoints": [
	250000000,
	500000000,
	750000000,
	1000000000
	],
	"reason": "highest observed chance-normalized Open SLM Intelligence Index",
	"selected_continuation_checkpoint": 500000000,
	"used_public_evaluations": true
	},
	"continuation_checkpoint_metrics": {
	"elapsed_seconds": 4661.750659100002,
	"gradient_norm": 0.7176291942596436,
	"learning_rate": 0.0003,
	"step": 1908,
	"tokens_seen": 500170752,
	"train_loss": 2.8427783250808716,
	"validation_loss": 2.7994241237640383
	},
	"continuation_token_presentations": 500170752,
	"cumulative_token_presentations": 2000170752,
	"format_version": 1,
	"release_name": "Hummingbird-V1",
	"source_checkpoint": "artifacts/runs/natural20b_pilot_muon_b32/checkpoint-tokens-0500000000",
	"training_config": {
	"adam_beta1": 0.9,
	"adam_beta2": 0.95,
	"adam_eps": 1e-08,
	"compile": false,
	"context_length": 512,
	"corpus_path": "artifacts\\natural20b_pilot\\packed",
	"deterministic": false,
	"device": null,
	"gradient_accumulation_steps": 16,
	"init_from": "artifacts/runs/variant_v1_muon_500m/checkpoint-tokens-1500000000",
	"learning_rate": 0.0003,
	"lr_decay_fraction": 0.15,
	"lr_min_ratio": 0.1,
	"lr_schedule": "wsd",
	"lr_warmup_steps": 100,
	"max_grad_norm": 1.0,
	"micro_batch_size": 32,
	"model_config_path": "configs\\model_4k_14l_sdpa_qk_clamp.yaml",
	"mtp_final_loss_weight": null,
	"mtp_loss_weight": 0.0,
	"num_workers": 0,
	"optimizer": "muon",
	"pin_memory": true,
	"precision": "bf16",
	"prepared_data_dir": "artifacts\\natural20b_pilot\\packed",
	"run_dir": "artifacts\\runs\\natural20b_pilot_muon_b32",
	"save_every_steps": 500,
	"save_every_tokens": 250000000,
	"seed": 42,
	"tokenizer_path": "artifacts\\runs\\e3_tokenizers\\tok_4k_digit",
	"tokens_target": 1000000000,
	"validate_every_steps": 100,
	"validation_tokens": 65536,
	"weight_decay": 0.1
	}
	}