Meta-Llama-3-8B-Instruct

Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.

Developer Portal : https://api.market/store/bridgeml/meta-llama3-8b

Llama 3

This cheap LLM API was developed by Meta and released the Meta Llama 3 family of large language models (LLMs), a collection of pre-trained and instruction-tuned generative text models in 8 and 70B sizes. The Llama 3 instruction-tuned models are optimized for dialogue use cases and outperform many of the available open-source chat models on common industry benchmarks.

Input: Models input text only.

Output: Models generate text and code only.

Model Architecture: Llama 3 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.

Params	Context length	Token count	Knowledge cutoff
8B	8K	15T+	March, 2023

Intended Use Cases Llama 3 is intended for commercial and research use in English. Instruction-tuned models are intended for assistant-like chat, whereas pre-trained models can be adapted for a variety of natural language generation tasks. This is an easy-to-use LLM API and cheap LLM with cost of $0.18 per million tokens.

Carbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.

Time (GPU hours)	Power Consumption (W)	Carbon Emitted(tCO2eq)
1.3M	700	390

Training Data

Overview Llama 3 was pre-trained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.

Data Freshness The pretraining data has a cutoff of March 2023 for the 8B and December 2023 for the 70B models respectively.

Request and Response

Request

curl -X 'POST' \
  'https://api.magicapi.dev/api/v1/bridgeml/meta-llama3-8b/bridgeml/meta-llama3-8b' \
  -H 'accept: application/json' \
  -H 'x-magicapi-key: API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "messages": [
    {
      "role": "user",
      "content": "hello"
    },
    {
      "role": "assistant",
      "content": "As a senior copywriter, write a long-form blog on why they should integrate LLM APIs from api.market into their existing offerings and how LLAMA LLM API can handle customer support, documentation and help reduce overall costs"
    }
  ],
  "temperature": 1,
  "max_tokens": 256,
  "top_p": 1,
  "frequency_penalty": 0,
  "stream": false
}'

Response

{
  "id": "meta-llama/Meta-Llama-3-8B-Instruct-5da290c5-bec1-4631-b635-0bd35017c520",
  "object": "text_completion",
  "created": 1718707039,
  "model": "meta-llama/Meta-Llama-3-8B-Instruct",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "**Unlock the Power of Language Models: How LLM APIs Can Revolutionize Your Business**\n\nIn today's digital age, the importance of effective communication cannot be overstated. From customer support to documentation, language plays a crucial role in shaping the user experience. However, managing language-based interactions can be a daunting task, especially for businesses with limited resources. This is where Large Language Model (LLM) APIs come into play. In this blog, we'll explore the benefits of integrating LLM APIs from api.market into your existing offerings and how LLAMA LLM API can help you streamline customer support, documentation, and more.\n\n**What are LLM APIs?**\n\nLLM APIs are pre-trained language models that can be integrated into your applications to automate language-based tasks. These models are trained on vast amounts of text data and can understand the nuances of human language, allowing them to generate human-like responses to user inputs. LLM APIs are not only accurate but also scalable, which makes them an attractive solution for businesses looking to improve their language-based interactions.\n\n**Benefits of Integrate LLM APIs**\n\nIntegrating LLM APIs from api.market into your existing offerings can bring numerous benefits, including:\n\n1. **Improved Customer Support**: LLM APIs can help your customer support team",
        "tool_calls": null,
        "tool_call_id": null
      },
      "index": 0,
      "finish_reason": "length",
      "logprobs": null
    }
  ],
  "usage": {
    "prompt_tokens": 60,
    "completion_tokens": 256,
    "total_tokens": 316
  }
}

This is a cheap and easy to use LLM API which you can try out at https://api.market/store/bridgeml/meta-llama3-8b