Name	Quant method	Size
Llama-3.1-Storm-8B.Q2_K.gguf	Q2_K	2.96GB
Llama-3.1-Storm-8B.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3.1-Storm-8B.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3.1-Storm-8B.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3.1-Storm-8B.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3.1-Storm-8B.Q3_K.gguf	Q3_K	3.74GB
Llama-3.1-Storm-8B.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3.1-Storm-8B.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3.1-Storm-8B.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3.1-Storm-8B.Q4_0.gguf	Q4_0	4.34GB
Llama-3.1-Storm-8B.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3.1-Storm-8B.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3.1-Storm-8B.Q4_K.gguf	Q4_K	4.58GB
Llama-3.1-Storm-8B.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3.1-Storm-8B.Q4_1.gguf	Q4_1	4.78GB
Llama-3.1-Storm-8B.Q5_0.gguf	Q5_0	5.21GB
Llama-3.1-Storm-8B.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3.1-Storm-8B.Q5_K.gguf	Q5_K	5.34GB
Llama-3.1-Storm-8B.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3.1-Storm-8B.Q5_1.gguf	Q5_1	5.65GB
Llama-3.1-Storm-8B.Q6_K.gguf	Q6_K	6.14GB
Llama-3.1-Storm-8B.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model: meta-llama/Meta-Llama-3.1-8B language:

en library_name: transformers license: llama3.1 tags:
llama-3
llama
meta
facebook
unsloth
transformers

Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!

We have a free Google Colab Tesla T4 notebook for Llama 3.1 (8B) here: https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp?usp=sharing

✨ Finetune for Free

All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.

Unsloth supports	Free Notebooks	Performance	Memory use
Llama-3.1 8b	▶️ Start on Colab	2.4x faster	58% less
Phi-3.5 (mini)	▶️ Start on Colab	2x faster	50% less
Gemma-2 9b	▶️ Start on Colab	2.4x faster	58% less

Llama 3.1 Storm

Authors: Ashvini Kumar Jindal, Pawan Kumar Rajpoot, Ankur Parikh, Akshita Sukhlecha

🤗 Hugging Face Announcement Blog: https://huggingface.co/blog/akjindal53244/llama31-storm8b

🚀Ollama: ollama run ajindal/llama3.1-storm:8b

TL;DR

We present the Llama-3.1-Storm-8B model that outperforms Meta AI's Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B models significantly across diverse benchmarks as shown in the performance comparison plot in the next section. Our approach consists of three key steps:

Self-Curation: We applied two self-curation methods to select approximately 1 million high-quality examples from a pool of ~2.8 million open-source examples. Our curation criteria focused on educational value and difficulty level, using the same SLM for annotation instead of larger models (e.g. 70B, 405B).
Targeted fine-tuning: We performed Spectrum-based targeted fine-tuning over the Llama-3.1-8B-Instruct model. The Spectrum method accelerates training by selectively targeting layer modules based on their signal-to-noise ratio (SNR), and freezing the remaining modules. In our work, 50% of layers are frozen.
Model Merging: We merged our fine-tuned model with the Llama-Spark model using SLERP method. The merging method produces a blended model with characteristics smoothly interpolated from both parent models, ensuring the resultant model captures the essence of both its parents. Llama-3.1-Storm-8B improves Llama-3.1-8B-Instruct across 10 diverse benchmarks. These benchmarks cover areas such as instruction-following, knowledge-driven QA, reasoning, truthful answer generation, and function calling.

🏆 Introducing Llama-3.1-Storm-8B

Llama-3.1-Storm-8B builds upon the foundation of Llama-3.1-8B-Instruct, aiming to enhance both conversational and function calling capabilities within the 8B parameter model class.

As shown in the left subplot of the above figure, Llama-3.1-Storm-8B model improves Meta-Llama-3.1-8B-Instruct across various benchmarks - Instruction-following (IFEval), Knowledge-driven QA benchmarks (GPQA, MMLU-Pro), Reasoning (ARC-C, MuSR, BBH), Reduced Hallucinations (TruthfulQA), and Function-Calling (BFCL). This improvement is particularly significant for AI developers and enthusiasts who work with limited computational resources.

We also benchmarked our model with the recently published model Hermes-3-Llama-3.1-8B built on top of the Llama-3.1-8B-Instruct model. As shown in the right subplot of the above figure, Llama-3.1-Storm-8B outperforms Hermes-3-Llama-3.1-8B on 7 out of 9 benchmarks, with Hermes-3-Llama-3.1-8B surpassing Llama-3.1-Storm-8B on the MuSR benchmark and both models showing comparable performance on the BBH benchmark.

Llama-3.1-Storm-8B Model Strengths

Llama-3.1-Storm-8B is a powerful generalist model useful for diverse applications. We invite the AI community to explore Llama-3.1-Storm-8B and look forward to seeing how it will be utilized in various projects and applications.

Model Strength	Relevant Benchmarks
🎯 Improved Instruction Following	IFEval Strict (+3.93%)
🌐 Enhanced Knowledge Driven Question Answering	GPQA (+7.21%), MMLU-Pro (+0.55%), AGIEval (+3.77%)
🧠 Better Reasoning	ARC-C (+3.92%), MuSR (+2.77%), BBH (+1.67%), AGIEval (+3.77%)
🤖 Superior Agentic Capabilities	BFCL: Overall Acc (+7.92%), BFCL: AST Summary (+12.32%)
🚫 Reduced Hallucinations	TruthfulQA (+9%)

Note: All improvements are absolute gains over Meta-Llama-3.1-8B-Instruct.

Llama-3.1-Storm-8B Models

BF16: Llama-3.1-Storm-8B
⚡ FP8: Llama-3.1-Storm-8B-FP8-Dynamic
⚡ GGUF: Llama-3.1-Storm-8B-GGUF
🚀 Ollama: ollama run ajindal/llama3.1-storm:8b

💻 How to Use the Model

The Hugging Face transformers library loads the model in bfloat16 by default. This is the type used by the Llama-3.1-Storm-8B checkpoint, so it’s the recommended way to run to ensure the best results.

Installation

pip install --upgrade "transformers>=4.43.2" torch==2.3.1 accelerate vllm==0.5.3.post1

Developers can easily integrate Llama-3.1-Storm-8B into their projects using popular libraries like Transformers and vLLM. The following sections illustrate the usage with simple hands-on examples:

Conversational Use-case

Use with 🤗 Transformers

Using `transformers.pipeline()` API

python

import transformers
import torch

model_id = "akjindal53244/Llama-3.1-Storm-8B"
pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is 2+2?"}
]

outputs = pipeline(messages, max_new_tokens=128, do_sample=True, temperature=0.01, top_k=100, top_p=0.95)
print(outputs[0]["generated_text"][-1])  # Expected Output: {'role': 'assistant', 'content': '2 + 2 = 4'}

Using `model.generate()` API

pip install flash_attn==2.6.3

python

import torch
from transformers import AutoTokenizer, LlamaForCausalLM

# Apply Llama3.1 chat-template
def format_prompt(user_query):
    template = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n{}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n"""
    return template.format(user_query)


model_id = 'akjindal53244/Llama-3.1-Storm-8B'
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = LlamaForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    load_in_8bit=False,
    load_in_4bit=False,
    use_flash_attention_2=True
)

# Build final input prompt after applying chat-template
prompt = format_prompt("What is 2+2?")

input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to("cuda")
generated_ids = model.generate(input_ids, max_new_tokens=128, temperature=0.01, do_sample=True, eos_token_id=tokenizer.eos_token_id)
response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True)
print(response)  # Expected Output: '2 + 2 = 4'

Use with vLLM

python

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "akjindal53244/Llama-3.1-Storm-8B"  # FP8 model: "akjindal53244/Llama-3.1-Storm-8B-FP8-Dynamic"
num_gpus = 1

tokenizer = AutoTokenizer.from_pretrained(model_id)
llm = LLM(model=model_id, tensor_parallel_size=num_gpus)
sampling_params = SamplingParams(max_tokens=128, temperature=0.01, top_k=100, top_p=0.95)

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is 2+2?"}
]
prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize = False)
print(llm.generate([prompt], sampling_params)[0].outputs[0].text.strip())  # Expected Output: 2 + 2 = 4

Use with LitGPT

bash

pip install 'litgpt[all]'
litgpt download akjindal53244/Llama-3.1-Storm-8B --model_name meta-llama/Meta-Llama-3.1-8B

python

from litgpt import LLM

llm = LLM.load(model="akjindal53244/Llama-3.1-Storm-8B")
llm.generate("What do Llamas eat?")

Function Calling Use-case

Llama-3.1-Storm-8B has impressive function calling capabilities compared to Meta-Llama-3.1-8B-Instruct as demonstrated by the BFCL benchmark.

Prompt Format for Function Calling

Llama-3.1-Storm-8B is trained with specific system prompt for Function Calling:

You are a function calling AI model. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into function. The user may use the terms function calling or tool use interchangeably.

Here are the available functions:
<tools>LIST_OF_TOOLS</tools>

For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags in the format:
<tool_call>{"tool_name": <function-name>, "tool_arguments": <args-dict>}</tool_call>

Above system prompt should be used with passing LIST_OF_TOOLS as input.

Use with vLLM

python

import json
from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

model_id = "akjindal53244/Llama-3.1-Storm-8B"  # FP8 model: "akjindal53244/Llama-3.1-Storm-8B-FP8-Dynamic"
num_gpus = 1

tokenizer = AutoTokenizer.from_pretrained(model_id)
llm = LLM(model=model_id, tensor_parallel_size=num_gpus)
sampling_params = SamplingParams(max_tokens=128, temperature=0.01, top_k=100, top_p=0.95)


def create_system_prompt(tools_list):
    system_prompt_format = """You are a function calling AI model. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into function. The user may use the terms function calling or tool use interchangeably.

Here are the available functions:
<tools>{}</tools>

For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags in the format:
<tool_call>{"tool_name": <function-name>, "tool_arguments": <args-dict>}</tool_call>"""
    
    # Convert the tools list to a string representation
    tools_str = json.dumps(tools_list, ensure_ascii=False)
    # Format the system prompt with the tools list
    system_prompt = system_prompt_format.format(tools_str)
    return system_prompt


# Example tools list
tools_list = [
    {
        "name": "peers",
        "description": "Retrieves a list of company peers given a stock symbol.",
        "parameters": {
            "symbol": {
                "description": "The stock symbol for the company.",
                "type": "str",
                "default": ""
            }
        }
    },
    {
        "name": "web_chain_details",
        "description": "python",
        "parameters": {
            "chain_slug": {
                "description": "The slug identifier for the blockchain (e.g., 'ethereum' for Ethereum mainnet).",
                "type": "str",
                "default": "ethereum"
            }
        }
    }
]

# Create the system prompt with the tools list
system_prompt = create_system_prompt(tools_list)

messages = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": "I need to understand the details of the Ethereum blockchain for my cryptocurrency project. Can you fetch the details for 'ethereum'?"}
]

prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize = False)
print(llm.generate([prompt], sampling_params)[0].outputs[0].text.strip())  # Expected Output: <tool_call>{'tool_name': 'web_chain_details', 'tool_arguments': {'chain_slug': 'ethereum'}}</tool_call>

Use with Ollama

import ollama

tools = [{
      'type': 'function',
      'function': {
        'name': 'get_current_weather',
        'description': 'Get the current weather for a city',
        'parameters': {
          'type': 'object',
          'properties': {
            'city': {
              'type': 'string',
              'description': 'The name of the city',
            },
          },
          'required': ['city'],
        },
      },
    },
    {
      'type': 'function',
      'function': {
        'name': 'get_places_to_vist',
        'description': 'Get places to visit in a city',
        'parameters': {
          'type': 'object',
          'properties': {
            'city': {
              'type': 'string',
              'description': 'The name of the city',
            },
          },
          'required': ['city'],
        },
      },
    },
  ]

response = ollama.chat(
    model='ajindal/llama3.1-storm:8b',
    messages=[
        {'role': 'system', 'content': 'Do not answer to nay vulgar questions.'},
        {'role': 'user', 'content': 'What is the weather in Toronto and San Francisco?'}
        ],
    tools=tools
)

print(response['message'])  # Expected Response: {'role': 'assistant', 'content': "<tool_call>{'tool_name': 'get_current_weather', 'tool_arguments': {'city': 'Toronto'}}</tool_call>"}

Alignment Note

While Llama-3.1-Storm-8B did not undergo an explicit model alignment process, it may still retain some alignment properties inherited from the Meta-Llama-3.1-8B-Instruct model.

Cite Our Work

@misc {ashvini_kumar_jindal_2024,
    author       = { {Ashvini Kumar Jindal, Pawan Kumar Rajpoot, Ankur Parikh, Akshita Sukhlecha} },
    title        = { Llama-3.1-Storm-8B },
    year         = 2024,
    url          = { https://huggingface.co/akjindal53244/Llama-3.1-Storm-8B },
    doi          = { 10.57967/hf/2902 },
    publisher    = { Hugging Face }
}

Support Our Work

With 3 team-members spanned across 3 different time-zones, we have won NeurIPS LLM Efficiency Challenge 2023 and 4 other competitions in Finance and Arabic LLM space. We have also published SOTA mathematical reasoning model.

Llama-3.1-Storm-8B is our most valuable contribution so far towards the open-source community. We are committed in developing efficient generalist LLMs. We're seeking both computational resources and innovative collaborators to drive this initiative forward.

RichardErkhov/unsloth_-_Llama-3.1-Storm-8B-gguf

Original model description:

Finetune Llama 3.1, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!

✨ Finetune for Free

Llama 3.1 Storm

TL;DR

🏆 Introducing Llama-3.1-Storm-8B

Llama-3.1-Storm-8B Model Strengths

Llama-3.1-Storm-8B Models

💻 How to Use the Model

Installation

Conversational Use-case

Use with 🤗 Transformers

Using transformers.pipeline() API

Using model.generate() API

Use with vLLM

Use with LitGPT

Function Calling Use-case

Prompt Format for Function Calling

Use with vLLM

Use with Ollama

Alignment Note

Cite Our Work

Support Our Work

RichardErkhov/
unsloth_-_Llama-3.1-Storm-8B-gguf

Using `transformers.pipeline()` API

Using `model.generate()` API