FinAI
Meridian.AI is a finance-specialized language model that continuously fine-tunes a Qwen2.5-0.5B backbone every hour on 25+ finance and math datasets, using Elastic Weight Consolidation (EWC) to prevent catastrophic...
Source du modèle
- Type
- Other
- Taille du fichier
- 942 MB
- Modèle de base
- Qwen/Qwen2.5-0.5B
- Version
- vmodel
- Mis à jour
- 21 oct. 2026
- Éditeur
- @meridianal
- Téléchargements
- 0
- Paramètres
- 5B
- Source
- Hugging Face
Description de la source
Meridian.AI — Continual-Learning Finance LLM
Meridian.AI is a finance-specialized language model that continuously fine-tunes a Qwen2.5-0.5B backbone every hour on 25+ finance and math datasets, using Elastic Weight Consolidation (EWC) to prevent catastrophic forgetting across training sessions. The entire pipeline runs unattended on free GitHub Actions infrastructure — no GPUs.
- Base model:
Qwen/Qwen2.5-0.5B(~494M params, Qwen2 architecture) - Continual learning: Elastic Weight Consolidation (diagonal Fisher)
- Training cadence: hourly GitHub Actions CI on CPU runners
- Source code & full docs: github.com/MeridianAlgo/FinAI
Usage
The deployed checkpoint is a standard Qwen2 model — trust_remote_code=True is not
required.
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "meridianal/FinAI"
tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder="checkpoint")
model = AutoModelForCausalLM.from_pretrained(
repo_id,
subfolder="checkpoint",
torch_dtype=torch.float32,
low_cpu_mem_usage=True,
)
model.eval()
prompt = """### Instruction:
Explain the difference between a bond's yield to maturity and its coupon rate.
### Response:
"""
inputs = tokenizer(prompt, return_tensors="pt")
with torch.no_grad():
output = model.generate(
**inputs,
max_new_tokens=200,
do_sample=True,
temperature=0.8,
top_p=0.92,
repetition_penalty=1.3,
no_repeat_ngram_size=3,
pad_token_id=tokenizer.pad_token_id,
eos_token_id=tokenizer.eos_token_id,
)
print(tokenizer.decode(output[0], skip_special_tokens=True))
Inputs are formatted with the ### Instruction: / ### Response: template used during training.
Model details
| Specification | Value |
|---|---|
| Base model | Qwen2.5-0.5B |
| Architecture | Qwen2ForCausalLM |
| Parameters | ~494M |
| Context window | 32,768 tokens (Qwen2.5 default) |
| Training dtype | bfloat16 |
| Continual learning | Elastic Weight Consolidation (EWC) |
Training data
A weighted streaming mix of 25+ finance and instruction datasets, including
gbharti/finance-alpaca, sujet-ai/Sujet-Finance-Instruct-177k,
nvidia/OpenMathInstruct-2, HuggingFaceFW/fineweb-edu, yahma/alpaca-cleaned, and the
FinanceMTEB suite. See the
repository README for the full
curriculum and weights.
Limitations & disclaimer
This is an experimental research project on continual learning for financial NLP. Outputs may contain factual errors and are intended for academic and research purposes only. Nothing generated by this model constitutes financial advice. Do not use outputs to make real financial decisions or execute trades.
Sources
1 source
Sources
1 sourceVérifié 21 oct.
Artefacts du modèle
1 artefact
Artefacts du modèle
1 artefactlegacy/v5.1.0/model.safetensors
safetensors · 942 MB · SHA-256 1c065dfd1a39…0bab · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- language: - en license: mit tags: - finance - continual-learning - qwen2 - causal-lm - ewc base_model: Qwen/Qwen2.5-0.5B datasets: - gbharti/finance-alpaca - sujet-ai/Sujet-Finance-Instruct-177k - nvidia/OpenMathInstruct-2 - HuggingFaceFW/fineweb-edu - yahma/alpaca-cleaned library_name: transformers pipeline_tag: text-generation --- # Meridian.AI — Continual-Learning Finance LLM Meridian.AI is a finance-specialized language model that continuously fine-tunes a **Qwen2.5-0.5B** backbone every hour on 25+ finance and math datasets, using **Elastic Weight Consolidation (EWC)** to prevent catastrophic forgetting across training sessions. The entire pipeline runs unattended on free GitHub Actions infrastructure — no GPUs. - **Base model:** [`Qwen/Qwen2.5-0.5B`](https://huggingface.co/Qwen/Qwen2.5-0.5B) (~494M params, Qwen2 architecture) - **Continual learning:** Elastic Weight Consolidation (diagonal Fisher) - **Training cadence:** hourly GitHub Actions CI on CPU runners - **Source code & full docs:** [github.com/MeridianAlgo/FinAI](https://github.com/MeridianAlgo/FinAI) ## Usage The deployed checkpoint is a **standard Qwen2 model** — `trust_remote_code=True` is **not** required. ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "meridianal/FinAI" tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder="checkpoint") model = AutoModelForCausalLM.from_pretrained( repo_id, subfolder="checkpoint", torch_dtype=torch.float32, low_cpu_mem_usage=True, ) model.eval() prompt = """### Instruction: Explain the difference between a bond's yield to maturity and its coupon rate. ### Response: """ inputs = tokenizer(prompt, return_tensors="pt") with torch.no_grad(): output = model.generate( **inputs, max_new_tokens=200, do_sample=True, temperature=0.8, top_p=0.92, repetition_penalty=1.3, no_repeat_ngram_size=3, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) print(tokenizer.decode(output[0], skip_special_tokens=True)) ``` Inputs are formatted with the `### Instruction: / ### Response:` template used during training. ## Model details | Specification | Value | |:---|:---| | Base model | Qwen2.5-0.5B | | Architecture | Qwen2ForCausalLM | | Parameters | ~494M | | Context window | 32,768 tokens (Qwen2.5 default) | | Training dtype | bfloat16 | | Continual learning | Elast...
Source context: 0 downloads · 5 likes · Pipeline text-generation · Library transformers · Repo meridianal/FinAI
Source context: 0 downloads · 4 likes · Pipeline text-generation · Library transformers · Repo meridianal/FinAI
