qwen-0.5b-stocks-news-v2-GGUF – AI Model by VaibTFU | AlphaNeural AI

You can deploy this model and start earning money today!

VaibTFU/
qwen-0.5b-stocks-news-v2-GGUF

like

0

Qwen/Qwen2.5-0.5B-Instruct

endpoints_compatible

Views

No views yet

qwen-0.5b-stocks-news-v2 (GGUF)

GGUF quantized versions of qwen-0.5b-stocks-news-v2.

Model Description

Fine-tuned Qwen2.5-0.5B-Instruct for financial news analysis. Outputs structured JSON with:

impactTerm: LONGTERM / SHORTTERM
impactScope: GLOBAL / INDUSTRY / STOCK
scopeItems: list of affected stocks/industries
highlights: key information summary
sentiment: POSITIVE / NEGATIVE / NEUTRAL

Available Quantizations

Quantization	Size	Quality	Use Case
F16	~1 GB	Highest	Reference / GPU inference
Q8_0	~530 MB	Very High	Desktop / server inference
Q4_K_M	~320 MB	Good	Mobile / edge / low-RAM

Usage

With llama.cpp

bash

./llama-cli -m qwen-0.5b-stocks-news-v2-q4_k_m.gguf \
  -p '<|im_start|>system
You are a financial news AI. Analyze the given news article and output its scope, impact, highlights, and sentiment in JSON format. /no_think<|im_end|>
<|im_start|>user
RBI holds repo rate at 6.5% in MPC meeting<|im_end|>
<|im_start|>assistant
' \
  -n 256 --temp 0.7

With Ollama

Create a Modelfile:

FROM ./qwen-0.5b-stocks-news-v2-q4_k_m.gguf

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
{{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

SYSTEM "You are a financial news AI. Analyze the given news article and output its scope, impact, highlights, and sentiment in JSON format. /no_think"

PARAMETER temperature 0.7
PARAMETER top_p 0.8
PARAMETER stop <|im_end|>

Then:

bash

ollama create qwen-0.5b-stocks-news-v2 -f Modelfile
ollama run qwen-0.5b-stocks-news-v2 "Infosys Q3 profit rises 11%"