Instructions to use HuggingFaceFW/ablation-model-fineweb-edu with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceFW/ablation-model-fineweb-edu with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceFW/ablation-model-fineweb-edu")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceFW/ablation-model-fineweb-edu")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceFW/ablation-model-fineweb-edu", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HuggingFaceFW/ablation-model-fineweb-edu with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HuggingFaceFW/ablation-model-fineweb-edu

SGLang

How to use HuggingFaceFW/ablation-model-fineweb-edu 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 "HuggingFaceFW/ablation-model-fineweb-edu" \
    --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": "HuggingFaceFW/ablation-model-fineweb-edu",
		"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 "HuggingFaceFW/ablation-model-fineweb-edu" \
        --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": "HuggingFaceFW/ablation-model-fineweb-edu",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceFW/ablation-model-fineweb-edu with Docker Model Runner:
```
docker model run hf.co/HuggingFaceFW/ablation-model-fineweb-edu
```

loubnabnl HF Staff commited on Jun 5, 2024

Commit

87e359a

verified ·

1 Parent(s): 7aaee30

Update README.md

Browse files

Files changed (1) hide show

README.md +53 -17

README.md CHANGED Viewed

@@ -1,34 +1,70 @@
 ---
 library_name: transformers
 license: apache-2.0
 ---
 # Model Card for HuggingFaceFW/ablation-model-fineweb-edu
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This the model trained on 350B tokens of [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu/) as part of the FineWeb ablations. We uploaded intermediate model checkpoints as separate commits in this repository, check the commit [history](https://huggingface.co/HuggingFaceFW/ablation-model-fineweb-edu/commits/main).
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]

 ---
 library_name: transformers
 license: apache-2.0
+language:
+- en
+datasets:
+- HuggingFaceFW/fineweb-edu
 ---
 # Model Card for HuggingFaceFW/ablation-model-fineweb-edu
+## Model summary
+This model is part of the 🍷 [FineWeb](https://huggingface.co/datasets/HuggingFaceFW/fineweb) ablations, detailed in this [technical report](https://huggingface.co/spaces/HuggingFaceFW/blogpost-fineweb-v1).
+The model has 1.82B parameters, 2048 context length and uses Llama architecture with RoPE. It was trained on 350B tokens from [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu), tokenized using `gpt2` tokenizer.
+- Paper: 🍷 FineWeb: decanting the web for the finest text data at scale https://hf.co/spaces/HuggingFaceFW/blogpost-fineweb-v1
+- License: Apache-2
+- Languages: English
+## Use
+### Intended use
+This model was trained on English web data, and is intended for text completion in English. It is not instruction-tuned.
+### Generation
+```python
+# pip install -q transformers
+from transformers import AutoModelForCausalLM, AutoTokenizer
+checkpoint = MODEL_ID
+device = "cuda" # for GPU usage or "cpu" for CPU usage
+tokenizer = AutoTokenizer.from_pretrained(checkpoint)
+model = AutoModelForCausalLM.from_pretrained(checkpoint).to(device)
+inputs = tokenizer.encode("Machine Learning is", return_tensors="pt").to(device)
+outputs = model.generate(inputs)
+print(tokenizer.decode(outputs[0]))
+```
+## Training
+### Model
+- Architecture: Llama model
+- Pretraining steps: 167k
+- Pretraining tokens: 350B
+- Precision: bfloat16
+### Hardware
+- GPUs: 64 H100
+- Training time: 5 GPU hours pretraining
+### Software
+- [nanotron](https://github.com/huggingface/nanotron/) for training
+- [datatrove](https://github.com/huggingface/datatrove) for tokenization
+- [lighteval](https://github.com/huggingface/lighteval) for evaluation
+## Evaluation
+We used the same setup to evaluate all our ablation models with `lighteval`. To reproduce our numbers, make sure to follow the instruction [here](https://huggingface.co/datasets/HuggingFaceFW/fineweb/blob/main/lighteval_tasks.py#L12).
+```bash
+# download https://huggingface.co/datasets/HuggingFaceFW/fineweb/blob/main/lighteval_tasks.py and run:
+accelerate launch --num_processes=1 lighteval/run_evals_accelerate.py --model_args="pretrained=HuggingFaceFW/ablation-model-fineweb-edu" \
+    --custom_tasks "lighteval_tasks.py" --output_dir [OUTPUTPATH] --max_samples 1000 \
+    --tasks "custom|hellaswag|0|1,custom|winogrande|0|1,custom|piqa|0|1,custom|siqa|0|1,custom|openbookqa|0|1,custom|arc:easy|0|1,custom|arc:challenge|0|1,custom|commonsense_qa|0|1,custom|mmlu:abstract_algebra|0|1,custom|mmlu:anatomy|0|1,custom|mmlu:astronomy|0|1,custom|mmlu:business_ethics|0|1,custom|mmlu:clinical_knowledge|0|1,custom|mmlu:college_biology|0|1,custom|mmlu:college_chemistry|0|1,custom|mmlu:college_computer_science|0|1,custom|mmlu:college_mathematics|0|1,custom|mmlu:college_medicine|0|1,custom|mmlu:college_physics|0|1,custom|mmlu:computer_security|0|1,custom|mmlu:conceptual_physics|0|1,custom|mmlu:econometrics|0|1,custom|mmlu:electrical_engineering|0|1,custom|mmlu:elementary_mathematics|0|1,custom|mmlu:formal_logic|0|1,custom|mmlu:global_facts|0|1,custom|mmlu:high_school_biology|0|1,custom|mmlu:high_school_chemistry|0|1,custom|mmlu:high_school_computer_science|0|1,custom|mmlu:high_school_european_history|0|1,custom|mmlu:high_school_geography|0|1,custom|mmlu:high_school_government_and_politics|0|1,custom|mmlu:high_school_macroeconomics|0|1,custom|mmlu:high_school_mathematics|0|1,custom|mmlu:high_school_microeconomics|0|1,custom|mmlu:high_school_physics|0|1,custom|mmlu:high_school_psychology|0|1,custom|mmlu:high_school_statistics|0|1,custom|mmlu:high_school_us_history|0|1,custom|mmlu:high_school_world_history|0|1,custom|mmlu:human_aging|0|1,custom|mmlu:human_sexuality|0|1,custom|mmlu:international_law|0|1,custom|mmlu:jurisprudence|0|1,custom|mmlu:logical_fallacies|0|1,custom|mmlu:machine_learning|0|1,custom|mmlu:management|0|1,custom|mmlu:marketing|0|1,custom|mmlu:medical_genetics|0|1,custom|mmlu:miscellaneous|0|1,custom|mmlu:moral_disputes|0|1,custom|mmlu:moral_scenarios|0|1,custom|mmlu:nutrition|0|1,custom|mmlu:philosophy|0|1,custom|mmlu:prehistory|0|1,custom|mmlu:professional_accounting|0|1,custom|mmlu:professional_law|0|1,custom|mmlu:professional_medicine|0|1,custom|mmlu:professional_psychology|0|1,custom|mmlu:public_relations|0|1,custom|mmlu:security_studies|0|1,custom|mmlu:sociology|0|1,custom|mmlu:us_foreign_policy|0|1,custom|mmlu:virology|0|1,custom|mmlu:world_religions|0|1"
+```
+In particular the MMLU prompts are slightly different from those in `lm-evaluation-harness` and the Open LLM Leaderboard, more in this [blogpost](https://huggingface.co/blog/open-llm-leaderboard-mmlu#1001-flavors-of-mmlu).
+## Limitations
+This model was predominantly trained on English data, potentially limiting its performance in other languages. Furthermore, the model's behavior is influenced by the quality and diversity of its training data, which may include biases and harmful content.