partai / dorna-llama3

PartAI Dorna-Llama3: The most powerful Persian LLM to date, under 10B parameters

469 Pulls Updated 3 months ago

3 months ago

c18d18aaeb6e · 8.5GB

model
llama
·
8.03B
·
Q8_0
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>
params
{"stop":["<|start_header_id|>","<|end_header_id|>","<|eot_id|>"]}
system
You are a helpful Persian assistant. Please answer questions in the asked language.

Readme

Dorna-Llama3

The Dorna models are a family of decoder-only models, specifically trained/fine-tuned on Persian data, developed by Part AI. As an initial release, an 8B instruct model from this family is
Dorna-Llama3-8B-Instruct is built using the Meta Llama 3 Instruct model.

In this repo, we provide bf16 model and quantized models in the GGUF formats, including Q2_K, Q3_K, Q3_K_L, Q3_K_M, Q3_K_S, Q4_0, Q4_1, Q4_K_M, Q4_K_S, Q5_0, Q5_1, Q5_K_M, Q5_K_S and Q8_0

Here offers an in-depth report that includes several performance charts. Check it out.

CLI

Open the terminal and run ollama run dorna-llama3

API

Example using curl:

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "llama3",
  "prompt":"سلام!"
 }'