Instructions to use sapienzanlp/Minerva-7B-instruct-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sapienzanlp/Minerva-7B-instruct-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="sapienzanlp/Minerva-7B-instruct-v1.0")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sapienzanlp/Minerva-7B-instruct-v1.0")
model = AutoModelForCausalLM.from_pretrained("sapienzanlp/Minerva-7B-instruct-v1.0", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sapienzanlp/Minerva-7B-instruct-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sapienzanlp/Minerva-7B-instruct-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sapienzanlp/Minerva-7B-instruct-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sapienzanlp/Minerva-7B-instruct-v1.0

SGLang

How to use sapienzanlp/Minerva-7B-instruct-v1.0 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 "sapienzanlp/Minerva-7B-instruct-v1.0" \
    --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": "sapienzanlp/Minerva-7B-instruct-v1.0",
		"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 "sapienzanlp/Minerva-7B-instruct-v1.0" \
        --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": "sapienzanlp/Minerva-7B-instruct-v1.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sapienzanlp/Minerva-7B-instruct-v1.0 with Docker Model Runner:
```
docker model run hf.co/sapienzanlp/Minerva-7B-instruct-v1.0
```

edobobo commited on Dec 3, 2024

Commit

7145d69

verified ·

1 Parent(s): 699c973

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -12

README.md CHANGED Viewed

@@ -53,7 +53,7 @@ This model is part of the Minerva LLM family:
 *This section identifies foreseeable harms and misunderstandings.*
-This is a chat foundation model, subject to some degree of alignment. However, the model may still:
 -   Overrepresent some viewpoints and underrepresent others
 -   Contain stereotypes
@@ -87,7 +87,7 @@ pipeline = transformers.pipeline(
 )
 # Input text for the model.
-input_conv = [{"role": "user", "content": "Qualle è la capitale dell'Italia?"}]
 # Compute the outputs.
 output = pipeline(
@@ -103,7 +103,7 @@ output
 ## Model Architecture
-Minerva-7B-base-v1.0 is a Transformer model based on the Mistral architecture.
 Please look at the configuration file for a detailed breakdown of the hyperparameters we chose for this model.
 The Minerva LLM family is composed of:
@@ -132,23 +132,23 @@ The SFT model was trained using [Llama-Factory](https://github.com/hiyouga/LLaMA
 | Dataset                              | Source                                                                 | Code     | English | Italian |
 |--------------------------------------|------------------------------------------------------------------------|----------|---------|---------|
 | Alpaca-cleaned                       | [Link](https://huggingface.co/datasets/yahma/alpaca-cleaned)            | 0        | 50,000  | 0       |
 | Databricks-dolly-15k                 | [Link](https://huggingface.co/datasets/databricks/databricks-dolly-15k) | 0        | 15,011  | 0       |
 | No-robots                            | [Link](https://huggingface.co/datasets/HuggingFaceH4/no_robots)         | 0        | 9,499   | 0       |
 | OASST2                               | [Link](https://huggingface.co/datasets/OpenAssistant/oasst2)            | 0        | 29,000  | 528     |
-| Tower-blocks_it                      | [Link](https://huggingface.co/datasets/sapienzanlp/tower_blocks-v0.2_it) | 0        | 0       | 7,276   |
-| Glaive-code-assistant                | [Link](https://huggingface.co/datasets/glaiveai/glaive-code-assistant)  | 100,000  | 0       | 0       |
-| Alpaca-python                        | [Link](https://huggingface.co/datasets/Vezora/Tested-143k-Python-Alpaca) | 20,000   | 0       | 0       |
 | WizardLM                             | [Link](https://huggingface.co/datasets/WizardLMTeam/WizardLM_evol_instruct_70k) | 0  | 29,810  | 0       |
 | LIMA                                 | [Link](https://huggingface.co/datasets/GAIR/lima?row=0)                 | 0        | 1,000   | 0       |
 | OPENORCA                              | [Link](https://huggingface.co/datasets/Open-Orca/OpenOrca)              | 0        | 30,000  | 0       |
 | Ultrachat                             | [Link](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)     | 0        | 50,000  | 0       |
 | MagpieMT                             | [Link](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-MT-300K-v0.1) | 0     | 30,000  | 0       |
 | Tulu-V2-Science                      | [Link](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture)    | 0        | 7,000   | 0       |
 | Bactrian-X                           | [Link](https://huggingface.co/datasets/MBZUAI/Bactrian-X)               | 0        | 0       | 67,000  |
 | Magpie (*Translated by us*)          | -                                                                      | 0        | 0       | 60,000  |
 | Everyday-conversations (*Translated by us*) | -                                                                  | 0        | 0       | 2,260   |
-| Aya_datasets                         | [Link](http://CohereForAI/aya_dataset)                                  | 0        | 3,944   | 738     |
 | alpaca-gpt4-it                       | [Link](https://huggingface.co/datasets/efederici/alpaca-gpt4-it)        | 0        | 0       | 15,000  |
 | capybara-claude-15k-ita              | [Link](https://huggingface.co/datasets/efederici/capybara-claude-15k-ita) | 0       | 0       | 15,000  |
 | Wildchat                             | [Link](https://huggingface.co/datasets/allenai/WildChat-1M)            | 0        | 0       | 5,000   |
@@ -156,13 +156,13 @@ The SFT model was trained using [Llama-Factory](https://github.com/hiyouga/LLaMA
 | Safety Italian                       | -                                                                      | 0        | 0       | 21,000  |
 | Handmade Italian                     | -                                                                      | 0        | 0       | 2,000   |
-For more details please check [our tech report](https://nlp.uniroma1.it/minerva/blog#from-a-base-model-to-an-instruct-model).
 ### Online DPO Training
-This model card is for our DPO model. Direct Preference Optimization (DPO) is a method that refines models based on user feedback, similar to Reinforcement Learning from Human Feedback (RLHF), but without the complexity of reinforcement learning. Online DPO further improves this by allowing real-time adaptation during training, continuously refining the model with new feedback. For training this model, we used the [Hugging Face TRL](https://github.com/huggingface/trl) library and Online DPO, with the [Skywork/Skywork-Reward-Llama-3.1-8B-v0.2](https://huggingface.co/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2) model as the judge to evaluate and guide optimization. For this stage we used just the prompts from HuggingFaceH4/ultrafeedback_binarized (English), efederici/evol-dpo-ita (Italian) and Babelscape/ALERT translated to Italian were used, with additional manually curated data for safety.
-For more details please check [our tech report](https://nlp.uniroma1.it/minerva/blog#from-a-base-model-to-an-instruct-model).
 ## Model Evaluation
@@ -275,5 +275,5 @@ Minerva-7B-base-v1.0 is a pretrained base model and, therefore, has no moderatio
 ## Acknowledgments
-This work was funded by the PNRR MUR project [PE0000013-FAIR](https://fondazione-fair.it).
-We acknowledge the [CINECA](https://www.cineca.it) award "IscB_medit" under the ISCRA initiative, for the availability of high performance computing resources and support.

 *This section identifies foreseeable harms and misunderstandings.*
+This is a chat foundation model, subject to model alignment and safety risk mitigation strategies. However, the model may still:
 -   Overrepresent some viewpoints and underrepresent others
 -   Contain stereotypes
 )
 # Input text for the model.
+input_conv = [{"role": "user", "content": "Qual è la capitale dell'Italia?"}]
 # Compute the outputs.
 output = pipeline(
 ## Model Architecture
+Minerva-7B-base-v1.0 is a Transformer model based on the [Mistral](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) architecture.
 Please look at the configuration file for a detailed breakdown of the hyperparameters we chose for this model.
 The Minerva LLM family is composed of:
 | Dataset                              | Source                                                                 | Code     | English | Italian |
 |--------------------------------------|------------------------------------------------------------------------|----------|---------|---------|
+| Glaive-code-assistant                | [Link](https://huggingface.co/datasets/glaiveai/glaive-code-assistant)  | 100,000  | 0       | 0       |
+| Alpaca-python                        | [Link](https://huggingface.co/datasets/Vezora/Tested-143k-Python-Alpaca) | 20,000   | 0       | 0       |
 | Alpaca-cleaned                       | [Link](https://huggingface.co/datasets/yahma/alpaca-cleaned)            | 0        | 50,000  | 0       |
 | Databricks-dolly-15k                 | [Link](https://huggingface.co/datasets/databricks/databricks-dolly-15k) | 0        | 15,011  | 0       |
 | No-robots                            | [Link](https://huggingface.co/datasets/HuggingFaceH4/no_robots)         | 0        | 9,499   | 0       |
 | OASST2                               | [Link](https://huggingface.co/datasets/OpenAssistant/oasst2)            | 0        | 29,000  | 528     |
 | WizardLM                             | [Link](https://huggingface.co/datasets/WizardLMTeam/WizardLM_evol_instruct_70k) | 0  | 29,810  | 0       |
 | LIMA                                 | [Link](https://huggingface.co/datasets/GAIR/lima?row=0)                 | 0        | 1,000   | 0       |
 | OPENORCA                              | [Link](https://huggingface.co/datasets/Open-Orca/OpenOrca)              | 0        | 30,000  | 0       |
 | Ultrachat                             | [Link](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k)     | 0        | 50,000  | 0       |
 | MagpieMT                             | [Link](https://huggingface.co/datasets/Magpie-Align/Magpie-Pro-MT-300K-v0.1) | 0     | 30,000  | 0       |
 | Tulu-V2-Science                      | [Link](https://huggingface.co/datasets/allenai/tulu-v2-sft-mixture)    | 0        | 7,000   | 0       |
+| Aya_datasets                         | [Link](http://CohereForAI/aya_dataset)                                  | 0        | 3,944   | 738     |
+| Tower-blocks_it                      | [Link](https://huggingface.co/datasets/sapienzanlp/tower_blocks-v0.2_it) | 0        | 0       | 7,276   |
 | Bactrian-X                           | [Link](https://huggingface.co/datasets/MBZUAI/Bactrian-X)               | 0        | 0       | 67,000  |
 | Magpie (*Translated by us*)          | -                                                                      | 0        | 0       | 60,000  |
 | Everyday-conversations (*Translated by us*) | -                                                                  | 0        | 0       | 2,260   |
 | alpaca-gpt4-it                       | [Link](https://huggingface.co/datasets/efederici/alpaca-gpt4-it)        | 0        | 0       | 15,000  |
 | capybara-claude-15k-ita              | [Link](https://huggingface.co/datasets/efederici/capybara-claude-15k-ita) | 0       | 0       | 15,000  |
 | Wildchat                             | [Link](https://huggingface.co/datasets/allenai/WildChat-1M)            | 0        | 0       | 5,000   |
 | Safety Italian                       | -                                                                      | 0        | 0       | 21,000  |
 | Handmade Italian                     | -                                                                      | 0        | 0       | 2,000   |
+For more details, please check [our tech report](https://nlp.uniroma1.it/minerva/blog#from-a-base-model-to-an-instruct-model).
 ### Online DPO Training
+This model card is for our DPO model. Direct Preference Optimization (DPO) is a method that refines models based on user feedback, similar to Reinforcement Learning from Human Feedback (RLHF), but without the complexity of reinforcement learning. Online DPO further improves this by allowing real-time adaptation during training, continuously refining the model with new feedback. For training this model, we used the [Hugging Face TRL](https://github.com/huggingface/trl) library and Online DPO, with the [Skywork/Skywork-Reward-Llama-3.1-8B-v0.2](https://huggingface.co/Skywork/Skywork-Reward-Llama-3.1-8B-v0.2) model as the judge to evaluate and guide optimization. For this stage we used just the prompts from HuggingFaceH4/ultrafeedback_binarized (English), efederici/evol-dpo-ita (Italian) and Babelscape/ALERT translated to Italian, with additional manually curated data for safety.
+For more details, please check [our tech report](https://nlp.uniroma1.it/minerva/blog#from-a-base-model-to-an-instruct-model).
 ## Model Evaluation
 ## Acknowledgments
+This work was funded by the PNRR MUR project [PE0000013-FAIR](https://fondazione-fair.it) and the CREATIVE PRIN Project.
+We acknowledge the [CINECA](https://www.cineca.it) award "IscB_medit" under the ISCRA initiative for the availability of high-performance computing resources and support.