Instructions to use rostlabs/rost-1b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rostlabs/rost-1b-base with Transformers:

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

pipe = pipeline("text-generation", model="rostlabs/rost-1b-base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("rostlabs/rost-1b-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rostlabs/rost-1b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rostlabs/rost-1b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rostlabs/rost-1b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rostlabs/rost-1b-base

SGLang

How to use rostlabs/rost-1b-base 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 "rostlabs/rost-1b-base" \
    --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": "rostlabs/rost-1b-base",
		"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 "rostlabs/rost-1b-base" \
        --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": "rostlabs/rost-1b-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rostlabs/rost-1b-base with Docker Model Runner:
```
docker model run hf.co/rostlabs/rost-1b-base
```

stefaniancu commited on 2 days ago

Commit

28ceeaa

verified ·

1 Parent(s): bfc5158

Add English evaluation battery (lm-evaluation-harness 0.4.12, zero-shot + 5-shot MMLU)

Browse files

Files changed (1) hide show

README.md +26 -0

README.md CHANGED Viewed

@@ -172,6 +172,32 @@ understates them. For scale rather than ranking: RoLlama2-7b-Base reports a 42.0
 four-task accuracy average against this model's 34.12 -- from a model 5x larger
 trained on far more data.
 Also measured: CORE metric 0.2450 on the base model (0.1608 at step 2,000), and
 0.3021 validation bits-per-byte for the instruct checkpoint against 0.5113 for the
 base model it started from.

 four-task accuracy average against this model's 34.12 -- from a model 5x larger
 trained on far more data.
+**English suite**, base checkpoint, EleutherAI lm-evaluation-harness **0.4.12**,
+zero-shot except where marked, full test sets, scored by likelihood over the
+options -- the standard method for base models, so these are comparable to
+published tables produced at the same settings:
+| task | accuracy | normalised | chance |
+|---|---:|---:|---:|
+| sciq | **77.8** | 73.3 | 25.0 |
+| hellaswag | 37.7 | **46.5** | 25.0 |
+| piqa | 61.6 | **61.6** | 50.0 |
+| boolq | **58.1** | -- | ~50 |
+| arc_easy | **43.0** | 41.8 | 25.0 |
+| lambada_openai | 34.5 | -- | -- |
+| winogrande | 52.5 | -- | 50.0 |
+| arc_challenge | 23.9 | 27.9 | 25.0 |
+| openbookqa | 16.6 | 26.0 | 25.0 |
+| mmlu (5-shot) | 26.7 | -- | 25.0 |
+The same reading rule applies: judge against the chance column. Science QA,
+sentence completion and physical common sense are clearly learned; winogrande,
+arc_challenge, openbookqa and mmlu are at or near chance; and lambada is the weakest
+skill, consistent with English being the minority share of an 11.68B-token
+budget. For scale rather than ranking: on the completion tasks this sits
+between Pythia-410M and Pythia-1B -- models that saw roughly 40x more English
+text.
 Also measured: CORE metric 0.2450 on the base model (0.1608 at step 2,000), and
 0.3021 validation bits-per-byte for the instruct checkpoint against 0.5113 for the
 base model it started from.