JoyAI-LLM-Flash-AWQ-4bit
18
—
by
cyankiwi
Language Model
OTHER
4B params
New
18 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
9GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
4GB+ RAM
Code Examples
Chat Completionpythonopenai
from openai import OpenAI
client = OpenAI(base_url="http://IP:PORT/v1", api_key="EMPTY")
def simple_chat(client: OpenAI):
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": "which one is bigger, 9.11 or 9.9? think carefully.",
}
],
},
]
model_name = client.models.list().data[0].id
response = client.chat.completions.create(
model=model_name, messages=messages, stream=False, max_tokens=4096
)
print(f"response: {response.choices[0].message.content}")
if __name__ == "__main__":
simple_chat(client)Tool call Completionpythonopenai
import json
from openai import OpenAI
client = OpenAI(base_url="http://IP:PORT/v1", api_key="EMPTY")
def my_calculator(expression: str) -> str:
return str(eval(expression))
def rewrite(expression: str) -> str:
return str(expression)
def simple_tool_call(client: OpenAI):
messages = [
{
"role": "user",
"content": [
{
"type": "text",
"text": "use my functions to compute the results for the equations: 6+1",
},
],
},
]
tools = [
{
"type": "function",
"function": {
"name": "my_calculator",
"description": "A calculator that can evaluate a mathematical equation and compute its results.",
"parameters": {
"type": "object",
"properties": {
"expression": {
"type": "string",
"description": "The mathematical expression to evaluate.",
},
},
"required": ["expression"],
},
},
},
{
"type": "function",
"function": {
"name": "rewrite",
"description": "Rewrite a given text for improved clarity",
"parameters": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "The input text to rewrite",
}
},
},
},
},
]
model_name = client.models.list().data[0].id
response = client.chat.completions.create(
model=model_name,
messages=messages,
temperature=1.0,
max_tokens=1024,
tools=tools,
tool_choice="auto",
)
tool_calls = response.choices[0].message.tool_calls
results = []
for tool_call in tool_calls:
function_name = tool_call.function.name
function_args = tool_call.function.arguments
if function_name == "my_calculator":
result = my_calculator(**json.loads(function_args))
results.append(result)
messages.append({"role": "assistant", "tool_calls": tool_calls})
for tool_call, result in zip(tool_calls, results):
messages.append(
{
"role": "tool",
"tool_call_id": tool_call.id,
"name": tool_call.function.name,
"content": result,
}
)
response = client.chat.completions.create(
model=model_name,
messages=messages,
temperature=1.0,
max_tokens=1024,
)
print(response.choices[0].message.content)
if __name__ == "__main__":
simple_tool_call(client)Deploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.