Instructions to use nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy with Transformers:

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

pipe = pipeline("text-generation", model="nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy")
model = AutoModelForCausalLM.from_pretrained("nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy

SGLang

How to use nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy 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 "nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy" \
    --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": "nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy",
		"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 "nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy" \
        --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": "nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy with Docker Model Runner:
```
docker model run hf.co/nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy
```

nikitastheo/goldfish-eng-ell-sequential_interleaved-dummy

Trained with train_clm.py, a Hugging Face Accelerate causal-LM training script (no Trainer).

Training details

Base config: gpt_dummy_config.json
Tokenizer: nikitastheo/goldfish-eng-ell-tokenizer
Max steps: 12
Learning rate: 0.0001
LR scheduler: linear
Warmup steps: 16
Batch size (per device): 32
Gradient accumulation steps: 1
Total train batch size: 32
Language switch epoch: 3

Artifacts

input_config.json / training_metadata.json: the exact config and training arguments this run was launched with, plus num_steps_switch and the full save_steps list.
Intermediate checkpoints are pushed as separate branches named by step number (e.g. 0, 1, ... up to the final step), with the final model on main.

Downloads last month: 35

Safetensors

Model size

3.41M params

Tensor type

F32