Instructions to use HF1BitLLM/Llama3-8B-1.58-100B-tokens with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HF1BitLLM/Llama3-8B-1.58-100B-tokens with Transformers:

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

pipe = pipeline("text-generation", model="HF1BitLLM/Llama3-8B-1.58-100B-tokens")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("HF1BitLLM/Llama3-8B-1.58-100B-tokens")
model = AutoModelForCausalLM.from_pretrained("HF1BitLLM/Llama3-8B-1.58-100B-tokens", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HF1BitLLM/Llama3-8B-1.58-100B-tokens with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HF1BitLLM/Llama3-8B-1.58-100B-tokens"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HF1BitLLM/Llama3-8B-1.58-100B-tokens",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HF1BitLLM/Llama3-8B-1.58-100B-tokens

SGLang

How to use HF1BitLLM/Llama3-8B-1.58-100B-tokens 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 "HF1BitLLM/Llama3-8B-1.58-100B-tokens" \
    --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": "HF1BitLLM/Llama3-8B-1.58-100B-tokens",
		"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 "HF1BitLLM/Llama3-8B-1.58-100B-tokens" \
        --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": "HF1BitLLM/Llama3-8B-1.58-100B-tokens",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HF1BitLLM/Llama3-8B-1.58-100B-tokens with Docker Model Runner:
```
docker model run hf.co/HF1BitLLM/Llama3-8B-1.58-100B-tokens
```

medmekk commited on Sep 14, 2024

Commit

716ec0d

verified ·

1 Parent(s): 2465824

Update README.md

Browse files

Files changed (1) hide show

README.md +32 -128

README.md CHANGED Viewed

@@ -15,7 +15,6 @@ For a deeper dive into the methods and results, check out our [blog post](https:
 ## Model Details
 ### Model Sources
 <!-- Provide the basic links for the model. -->
@@ -23,39 +22,6 @@ For a deeper dive into the methods and results, check out our [blog post](https:
 - **Repository:** [Model](https://huggingface.co/HF1BitLLM/Llama3-8B-1.58-100B-tokens)
 - **Paper:** [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764)
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
 ## How to Get Started with the Model
@@ -71,7 +37,7 @@ input_ids = tokenizer.encode(input_text, return_tensors="pt").cuda()
 output = model.generate(input_ids, max_length=10, do_sample=False)
 generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 print(generated_text)
 ## Training Details
@@ -79,112 +45,50 @@ print(generated_text)
 The model was trained on a subset of [FineWeb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
-[More Information Needed]
-### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ## Model Details
 ### Model Sources
 <!-- Provide the basic links for the model. -->
 - **Repository:** [Model](https://huggingface.co/HF1BitLLM/Llama3-8B-1.58-100B-tokens)
 - **Paper:** [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://arxiv.org/abs/2402.17764)
 ## How to Get Started with the Model
 output = model.generate(input_ids, max_length=10, do_sample=False)
 generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 print(generated_text)
+```
 ## Training Details
 The model was trained on a subset of [FineWeb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu)
+### Training Process
+1. **Starting Point**
+   - Best-performing checkpoint from the 10 billion token runs with a linear lambda scheduler
+2. **Training Duration**
+   - Fine-tuned for an additional 45,000 steps
+   - Reached a total of 100 billion tokens
+3. **Dataset**
+   - FineWeb-edu dataset
+4. **Batch Size**
+   - 2 million tokens per step
+   - Total per run: 45,000 steps * 2 million tokens = 90 billion tokens
+   - Combined with initial 10 billion tokens to reach 100 billion
+5. **Learning Rate Experiments**
+   - Tested various learning rates to find optimal setting, according the to experiments, the best performing peak lr is 1e-5
+6. **Performance**
+   - Close to Llama3 8B on some metrics
+   - Behind Llama3 8B in overall average performance
+7. **Evaluation**
+   - Metrics included perplexity, MMLU scores, and other standard benchmarks
+These extended training runs on 100 billion tokens pushed the boundaries of highly quantized models, bringing performance closer to half-precision models like Llama3.
+## Evaluation
+The evaluation of the models is done on the nanotron checkpoints using LightEval :
+![results](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/blog/1.58llm_extreme_quantization/metrics_100B_table.png)
+## Citation
+```bash
+@misc{,
+      title={1.58-Bit LLM: A New Era of Extreme Quantization},
+      author={Mohamed Mekkouri and Marc Sun and Leandro von Werra and Thomas Wolf},
+      year={2024},
+}
+```