Made cleaner formating for model card

README.md

@@ -1,24 +1,13 @@
 # Ginie — Smart Contract LLM
 
-The first AI model purpose-built to generate, compile, audit, and deploy smart contracts across institutional and public blockchains. Plain English in. Production-ready contract out. On-chain in under 90 seconds.
-
 [![Website](https://img.shields.io/badge/Website-ginie.xyz-blue)](https://ginie.xyz)
 [![npm](https://img.shields.io/badge/npm-30k%2B_weekly_downloads-red)](https://npmjs.com/package/ginie-sdk)
 [![License](https://img.shields.io/badge/License-MIT-green)](https://opensource.org/licenses/MIT)
 [![Demo](https://img.shields.io/badge/Demo-Live-brightgreen)](https://huggingface.co/spaces/GinieAI/Ginie-Demo)
-[![Canton](https://img.shields.io/badge/Canton_Network-Supported-purple)](https://canton.network)
-
----
-
-## What is Ginie?
-
-Ginie is the developer layer for the next generation of on-chain applications. The friction keeping developers off-chain is not the blockchain itself — it is the specialised languages, compiler toolchains, and security requirements that sit between an idea and a deployed contract. Ginie removes all of that.
 
-Write a description. Get a contract that compiles, passes security checks, and deploys — across Solidity (Ethereum, Avalanche, Camp Network), Daml (Canton Network), and Rust (Vara Network).
+Generate, compile, and deploy smart contracts from plain English. Built for Solidity, Daml (Canton Network), and Rust (Vara Network).
 
-Canton Network alone processes $6 trillion in tokenised assets, backed by Goldman Sachs, JPMorgan, and DTCC. Every institution building on it needs smart contracts. Ginie writes them.
-
----
+-----
 
 ## Quickstart
 
@@ -30,16 +19,16 @@ tokenizer = AutoTokenizer.from_pretrained("GinieAI/Solidity-LLM")
 model = AutoModelForCausalLM.from_pretrained(
     "GinieAI/Solidity-LLM",
     torch_dtype=torch.bfloat16,
-    device_map="cuda"
+    device_map="auto"
 )
 
 prompt = """### Instruction:
-Write a Solidity ERC20 token contract with minting, burning, and owner controls.
+Write a Solidity ERC20 token with minting, burning, and owner controls.
 
 ### Response:
 """
 
-inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
 outputs = model.generate(
     **inputs,
     max_new_tokens=800,
@@ -49,48 +38,43 @@ outputs = model.generate(
 )
 
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
+**npm SDK**
 
-npm SDK — 30,000+ active weekly downloads
-
+```bash
 npm install ginie-sdk
+```
 
-
+```javascript
 import { Ginie } from 'ginie-sdk'
 
 const ginie = new Ginie({ apiKey: 'your-key' })
 
 const contract = await ginie.generate({
-  prompt: 'ERC20 token with vesting schedule for a startup',
+  prompt: 'ERC20 token with vesting schedule',
   chain: 'ethereum',
   audit: true
 })
+```
 
-console.log(contract.code)
-console.log(contract.securityScore)
-console.log(contract.compiled)
+-----
 
+## Model
 
-Model Details
-
-
-
-|Property      |Value                        |
-|--------------|-----------------------------|
-|Developer     |[Ginie AI](https://ginie.xyz)|
-|Model type    |Causal LM — Code Generation  |
-|Parameters    |2 Billion                    |
-|Architecture  |32 Transformer blocks        |
-|Context length|2048 tokens                  |
-|Precision     |bfloat16                     |
-|Tokenizer     |GPT-2                        |
-|Base model    |Chain-GPT/Solidity-LLM       |
-|License       |MIT                          |
-
-Performance
-Evaluated against GPT-4o mini and DeepSeek-Coder-7B on 100 Solidity contract generation prompts. Compilation success and security assessed via Slither static analysis. OpenZeppelin compliance assessed against standard library usage patterns.
+|Property      |Value                 |
+|--------------|----------------------|
+|Parameters    |2B                    |
+|Architecture  |32 Transformer blocks |
+|Context length|2048 tokens           |
+|Precision     |bfloat16              |
+|Tokenizer     |GPT-2                 |
+|Base model    |Chain-GPT/Solidity-LLM|
+|License       |MIT                   |
 
+-----
 
+## Performance
 
 |Metric                 |Ginie v1|GPT-4o mini|DeepSeek-Coder-7B|
 |-----------------------|--------|-----------|-----------------|
@@ -99,55 +83,37 @@ Evaluated against GPT-4o mini and DeepSeek-Coder-7B on 100 Solidity contract gen
 |Gas efficiency         |**72%** |65%        |63%              |
 |Security score         |**58%** |54%        |51%              |
 
-Ginie achieves the highest compilation rate despite being the smallest model in the comparison — a direct result of domain specialisation over general-purpose scale.
-
-What Ginie generates today
-	∙	ERC20, ERC721, ERC1155 token contracts
-	∙	DeFi protocols — staking, liquidity pools, yield farming
-	∙	DAO and governance contracts
-	∙	Multisig wallets and escrow agreements
-	∙	NFT marketplaces
-	∙	Automated compliance and audit loops
-Chains supported
-
+Evaluated on 100 prompts. Security via Slither static analysis.
 
+-----
 
-|Chain         |Language|Status    |
-|--------------|--------|----------|
-|Ethereum      |Solidity|Live      |
-|Avalanche     |Solidity|Live      |
-|Camp Network  |Solidity|Live      |
-|Canton Network|Daml    |v3 roadmap|
-|Vara Network  |Rust    |v3 roadmap|
+## Chains
 
-Not suitable for
-	∙	Production deployment without expert review
-	∙	Formal legal contract auditing
-	∙	Non-code generation tasks
+|Chain                            |Language|Status|
+|---------------------------------|--------|------|
+|Ethereum, Avalanche, Camp Network|Solidity|Live  |
+|Canton Network                   |Daml    |v3    |
+|Vara Network                     |Rust    |v3    |
 
-Roadmap
+-----
 
+## Roadmap
 
+|Version|Ships                                  |
+|-------|---------------------------------------|
+|v1.0   |Solidity — 2B params                   |
+|v2.0   |DISL + Zellic corpus — 7,800+ examples |
+|v3.0   |Daml + Rust support                    |
+|v4.0   |Weekly retraining flywheel on user data|
 
-|Version   |What ships                                               |
-|----------|---------------------------------------------------------|
-|v1.0 (now)|Solidity generation — 2B params, 83% compile rate        |
-|v2.0      |Expanded corpus — DISL + Zellic, 7,800+ training examples|
-|v3.0      |Daml and Rust support — Canton Network and Vara Network  |
-|v4.0      |Data flywheel — weekly retraining on real user prompts   |
+-----
 
-The v4 flywheel is the permanent moat. Every contract a user successfully generates becomes a training example for the next version. The model improves weekly from real usage — a data distribution no statically trained competitor can replicate.
+## Attribution
 
-Training
-Ginie v1 is fine-tuned from Chain-GPT/Solidity-LLM using LoRA on a curated Solidity instruction dataset. Training focused on instruction-following quality, OpenZeppelin pattern adherence, and compilable output over raw token prediction.
-Security validation uses Slither static analysis. Compilation validation uses solc. Both are integrated into the generation pipeline — not just evaluation.
+Fine-tuned from [Chain-GPT/Solidity-LLM](https://huggingface.co/Chain-GPT/Solidity-LLM), itself based on [Salesforce/codegen-2B-multi](https://huggingface.co/Salesforce/codegen-2B-multi). MIT License.
 
-License and Attribution
-Released under the MIT License.
-Built on Chain-GPT/Solidity-LLM by ChainGPT, which is fine-tuned from Salesforce/codegen-2B-multi. Full credit to the original authors. Ginie extends this work for the institutional blockchain ecosystem.
+-----
 
-About Ginie AI
-Ginie AI is building the developer layer for institutional blockchain. Backed by the Canton Foundation and supported by the Canton Network ecosystem — the institutional blockchain processing $6 trillion in tokenised assets with Goldman Sachs, JPMorgan, and DTCC.
-ginie.xyz · npm SDK · Live demo
+[ginie.xyz](https://ginie.xyz) · Canton Network processes $6T in tokenised assets backed by Goldman Sachs, JPMorgan, and DTCC.
 
-Smart contracts generated by Ginie should be reviewed by a qualified developer before production deployment. Security scores are indicative and do not constitute a formal audit.
+> Generated contracts require expert review before production deployment.