Instructions to use euclaise/crow-1b-attempt1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use euclaise/crow-1b-attempt1 with Transformers:

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

pipe = pipeline("text-generation", model="euclaise/crow-1b-attempt1", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("euclaise/crow-1b-attempt1", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("euclaise/crow-1b-attempt1", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use euclaise/crow-1b-attempt1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "euclaise/crow-1b-attempt1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "euclaise/crow-1b-attempt1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/euclaise/crow-1b-attempt1

SGLang

How to use euclaise/crow-1b-attempt1 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 "euclaise/crow-1b-attempt1" \
    --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": "euclaise/crow-1b-attempt1",
		"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 "euclaise/crow-1b-attempt1" \
        --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": "euclaise/crow-1b-attempt1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use euclaise/crow-1b-attempt1 with Docker Model Runner:
```
docker model run hf.co/euclaise/crow-1b-attempt1
```

Expirements in large-scale small-scale preference learning.

This one was a failure, it benchmarks horribly, despite responding okay to trivia questions in testing

falcon-rw-1b trained with PRO (preference ranking optimization, see https://arxiv.org/abs/2306.17492) on SuperMC and PRM800K (only stage 1) for 3 epochs, using my supertrainer2000 framework.

This is an expiremental model.

Benchmarks coming soon.

Hyperparameters:

AdamW, weight decay of 0.01, otherwise default hyperparams
Maximum LR of 1e-5
Cosine schedule with a warmup of 5400 steps
Batch size of 4 (2 real x 2 accumulated)
Maximum of 5 epochs, early stopping (visual observation), stopped after 3
Gradient clipping norm value of 1.0
PRO beta of 4

Training prompt format:

### Query
[insert instruction here]

### Answer
[insert response here]

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	29.12
AI2 Reasoning Challenge (25-Shot)	25.51
HellaSwag (10-Shot)	25.87
MMLU (5-Shot)	24.80
TruthfulQA (0-shot)	48.28
Winogrande (5-shot)	49.41
GSM8k (5-shot)	0.83

Downloads last month: 61

Safetensors

Model size

1B params

Tensor type

F32

Datasets used to train euclaise/crow-1b-attempt1

Paper for euclaise/crow-1b-attempt1

Preference Ranking Optimization for Human Alignment

Paper • 2306.17492 • Published Jun 30, 2023 • 6

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

25.510
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

25.870
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

24.800
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

48.280
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

49.410
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

0.830