Text Generation
Transformers
Safetensors
English
llama
thinking
reasoning
instruct
economics
finance
analysis
llama3.3
unsloth
finetune
bfloat16
128k context
conversational
text-generation-inference
Instructions to use Gaston895/aegisconduct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gaston895/aegisconduct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gaston895/aegisconduct") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Gaston895/aegisconduct") model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gaston895/aegisconduct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gaston895/aegisconduct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gaston895/aegisconduct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Gaston895/aegisconduct
- SGLang
How to use Gaston895/aegisconduct with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Gaston895/aegisconduct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gaston895/aegisconduct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Gaston895/aegisconduct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gaston895/aegisconduct", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Unsloth Desktop
- Docker Model Runner
How to use Gaston895/aegisconduct with Docker Model Runner:
docker model run hf.co/Gaston895/aegisconduct
| license: apache-2.0 | |
| base_model: allura-forge/Llama-3.3-8B-Instruct | |
| datasets: | |
| - TeichAI/claude-4.5-opus-high-reasoning-250x | |
| language: | |
| - en | |
| tags: | |
| - thinking | |
| - reasoning | |
| - instruct | |
| - economics | |
| - finance | |
| - analysis | |
| - llama3.3 | |
| - unsloth | |
| - finetune | |
| - bfloat16 | |
| - 128k context | |
| pipeline_tag: text-generation | |
| library_name: transformers | |
| # AEGIS Conduct - Economic Analysis Model | |
| ## Model Overview | |
| This repository contains the Llama 3.3 8B Instruct model with thinking capabilities, fine-tuned for economic and financial analysis using Claude 4.5-Opus High Reasoning dataset. | |
| **Key Features:** | |
| - **Thinking Mode**: Automatic activation for complex reasoning | |
| - **Economic Focus**: Specialized for financial analysis and market insights | |
| - **128k Context**: Extended context window for comprehensive analysis | |
| - **Optimized**: Fine-tuned with Unsloth for efficient inference | |
| ## Model Details | |
| - **Base Model**: allura-forge/Llama-3.3-8B-Instruct | |
| - **Fine-tuning Dataset**: TeichAI/claude-4.5-opus-high-reasoning-250x | |
| - **Context Length**: 128k tokens | |
| - **Training Method**: Unsloth (3 epochs) | |
| - **Format**: SafeTensors | |
| - **Precision**: bfloat16 | |
| ## Repository Structure | |
| Configuration files are in the root directory, with model weights in the econ subdirectory: | |
| ``` | |
| βββ config.json # Model configuration | |
| βββ generation_config.json # Generation parameters | |
| βββ tokenizer_config.json # Tokenizer configuration | |
| βββ special_tokens_map.json # Special tokens mapping | |
| βββ tokenizer.json # Tokenizer vocabulary | |
| βββ model.safetensors.index.json # Model index | |
| βββ chat_template.jinja # Chat template | |
| βββ matrix-neo-reloaded-fight.gif # Visual asset | |
| βββ README.md # This file | |
| βββ econ/ | |
| βββ model-00001-of-00004.safetensors # Model weights (part 1) | |
| βββ model-00002-of-00004.safetensors # Model weights (part 2) | |
| βββ model-00003-of-00004.safetensors # Model weights (part 3) | |
| βββ model-00004-of-00004.safetensors # Model weights (part 4) | |
| ``` | |
| ## Usage | |
| ### Loading the Model | |
| ```python | |
| from transformers import AutoTokenizer, AutoModelForCausalLM | |
| # Method 1: Load with subfolder for model weights | |
| tokenizer = AutoTokenizer.from_pretrained("Gaston895/aegisconduct") | |
| model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct", subfolder="econ") | |
| # Method 2: If all files are at root (after full migration) | |
| # tokenizer = AutoTokenizer.from_pretrained("Gaston895/aegisconduct") | |
| # model = AutoModelForCausalLM.from_pretrained("Gaston895/aegisconduct") | |
| ``` | |
| ### Generate Response | |
| ```python | |
| # Generate response | |
| inputs = tokenizer("Analyze the economic impact of inflation on consumer spending:", return_tensors="pt") | |
| outputs = model.generate(**inputs, max_length=512, temperature=0.7) | |
| response = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| print(response) | |
| ``` | |
| ### Thinking Mode Activation | |
| The model automatically activates thinking mode for complex reasoning: | |
| ```python | |
| # These prompts will trigger thinking mode | |
| prompts = [ | |
| "Think deeply: Analyze the economic implications of rising interest rates", | |
| "Explain the financial impact of supply chain disruptions", | |
| "Think through: What are the long-term effects of quantitative easing?" | |
| ] | |
| ``` | |
| ### Recommended Settings | |
| - **Temperature**: 0.7 | |
| - **Repetition Penalty**: 1.05 | |
| - **Top-p**: 0.95 | |
| - **Min-p**: 0.05 | |
| - **Top-k**: 40 | |
| - **Context Window**: 4k minimum, 8k+ recommended | |
| ## Capabilities | |
| This model excels at: | |
| - **Economic Analysis**: Market trends, policy impacts, forecasting | |
| - **Financial Planning**: Investment strategies, risk assessment | |
| - **Data Interpretation**: Economic indicators, statistical analysis | |
| - **Policy Analysis**: Regulatory impacts, fiscal policy effects | |
| - **Global Economics**: International trade, currency analysis | |
| - **Research**: Academic-level economic reasoning and explanation | |
| ## Technical Notes | |
| - Configuration files are at root level for easy access | |
| - Model weights are in the `econ/` subdirectory | |
| - Use `subfolder="econ"` when loading model weights | |
| - Supports both instruct and thinking modes | |
| - No system prompt required (thinking tags self-generate) | |
| - Compatible with quantization (Q4KS, IQ3_M recommended minimum) | |
| ## License | |
| Apache 2.0 (inherited from base model) | |
| ## Credits | |
| - **Base Model**: [allura-forge/Llama-3.3-8B-Instruct](https://huggingface.co/allura-forge/Llama-3.3-8B-Instruct) | |
| - **Dataset**: [TeichAI/claude-4.5-opus-high-reasoning-250x](https://huggingface.co/datasets/TeichAI/claude-4.5-opus-high-reasoning-250x) | |
| - **Training Framework**: [Unsloth](https://github.com/unslothai/unsloth) | |