llama3:8b-instruct-q5_K_M

8.1M 11 months ago

Meta Llama 3: The most capable openly available LLM to date

8b 70b

11 months ago

af3083b17cd4 · 5.7GB

model
llama
·
8.03B
·
Q5_K_M
params
{ "num_keep": 24, "stop": [ "<|start_header_id|>", "<|end_header_id|>",
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .P
license
META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024 “Agree

Readme

Llama 3

The most capable openly available LLM to date.

Meta Llama 3, a family of models developed by Meta Inc. are new state-of-the-art , available in both 8B and 70B parameter sizes (pre-trained or instruction-tuned).

Llama 3 instruction-tuned models are fine-tuned and optimized for dialogue/chat use cases and outperform many of the available open-source chat models on common benchmarks.

CLI

Open the terminal and run ollama run llama3

API

Example using curl:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "llama3",
  "prompt":"Why is the sky blue?"
 }'

API documentation

Model variants

Instruct is fine-tuned for chat/dialogue use cases.

Example: ollama run llama3 ollama run llama3:70b

Pre-trained is the base model.

Example: ollama run llama3:text ollama run llama3:70b-text

References

Introducing Meta Llama 3: The most capable openly available LLM to date