Instructions to use juinron/Hummingbird-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juinron/Hummingbird-V2 with Transformers:

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

pipe = pipeline("text-generation", model="juinron/Hummingbird-V2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("juinron/Hummingbird-V2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use juinron/Hummingbird-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juinron/Hummingbird-V2"
# 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-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/juinron/Hummingbird-V2

SGLang

How to use juinron/Hummingbird-V2 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-V2" \
    --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-V2",
		"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-V2" \
        --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-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use juinron/Hummingbird-V2 with Docker Model Runner:
```
docker model run hf.co/juinron/Hummingbird-V2
```

juinron commited on Sep 23

Commit

4ca0fdc

verified ·

1 Parent(s): e312506

Show condensed training mix on model card

Browse files

Files changed (2) hide show

README.md +14 -4
export_manifest.json +2 -2

README.md CHANGED Viewed

@@ -44,10 +44,20 @@ in the same small language model series. V2 was trained from a fresh initializat
 ## Training and data
-The model was trained on a balanced mix of educational web and synthetic text,
-worked mathematics, science, grounded question answering, and code. Training used Muon
-and AdamW with a 512-token context. See [training data](TRAINING_DATA.md) for source
-details and [training provenance](training/provenance.json) for the full recipe.
 ## Zero-shot evaluation

 ## Training and data
+The model was trained on this balanced mix:
+| Source | Share |
+|---|---:|
+| FineWeb-Edu sources | 55% |
+| Cosmopedia v2 | 15% |
+| FineMath 4+ | 10% |
+| DCLM baseline | 10% |
+| Dolma 3 science, question answering, and code | 7% |
+| FinePDFs-Edu | 3% |
+Training used Muon and AdamW with a 512-token context. See
+[training data](TRAINING_DATA.md) for source details and
+[training provenance](training/provenance.json) for the full recipe.
 ## Zero-shot evaluation

export_manifest.json CHANGED Viewed

@@ -13,8 +13,8 @@
       "sha256": "6125f403571b9c2bdf9995946836026822688f56db5ee15ac3e93292573e1ff2"
     },
     "README.md": {
-      "bytes": 3106,
-      "sha256": "cf3bbf4af6505c82b31ff779e4a07eea7e7215fab487120ac8b07381129a33e1"
     },
     "TRAINING_DATA.md": {
       "bytes": 1953,

       "sha256": "6125f403571b9c2bdf9995946836026822688f56db5ee15ac3e93292573e1ff2"
     },
     "README.md": {
+      "bytes": 3212,
+      "sha256": "cba301faaae037afc9ba67df6c8c82bc377f24239e81238e6e09b1152f889a11"
     },
     "TRAINING_DATA.md": {
       "bytes": 1953,