Downloads · 30 days
22
7% of all-time downloads
deevo-arch/qwen2.5-heritage-india-7b-gguf
qwen2.5-heritage-india-7b-gguf is a text generation model from deevo-arch. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
A fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct specialized in Indian heritage, monuments, and UNESCO World Heritage sites across Indian states.
Downloads · 30 days
22
7% of all-time downloads
All-time downloads
314
Public
Repo size
8.1 GB
Likes
1
Public
Click a slice to open those files.
.gguf8.1 GB · 100%
From the Hugging Face model README
A fine-tuned version of Qwen/Qwen2.5-Coder-7B-Instruct specialized in Indian heritage, monuments, and UNESCO World Heritage sites across Indian states.
Run directly in terminal without downloading manually:
ollama run hf.co/deevo-arch/qwen2.5-heritage-india-7b-gguf:heritage-qwen-7b-q8.gguf
## USAGE on RUN THIS WITH Collab,Kaggle etc.
from llama_cpp import Llama
# Download and initialize from Hugging Face Hub
llm = Llama.from_pretrained(
repo_id="deevo-arch/qwen2.5-heritage-india-7b-gguf",
filename="heritage-qwen-7b-q8.gguf",
n_gpu_layers=-1, # Offload all layers to GPU if available, or 0 for CPU
n_ctx=2048
)
# Chat completion with required system prompt
response = llm.create_chat_completion(
messages=[
{
"role": "system",
"content": "You are a knowledgeable historian and travel guide specializing in Indian heritage sites."
},
{
"role": "user",
"content": "Tell me about the Sun Temple in Konark."
}
],
temperature=0.7,
top_p=0.9
)
print(response["choices"][0]["message"]["content"])