Downloads Β· 30 days
20
23% of all-time downloads
bangill/maplestoryworlds-lua-api-finetune
maplestoryworlds-lua-api-finetune is a text generation model from bangill. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
This model is fine-tuned on MapleStory Worlds Lua API sample code. It is optimized for game script automation, code generation, and context-aware API usage.
Downloads Β· 30 days
20
23% of all-time downloads
All-time downloads
87
Public
Parameters
1.1B
2.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.3 GB Β· 100%
From the Hugging Face model README
This model is fine-tuned on MapleStory Worlds Lua API sample code. It is optimized for game script automation, code generation, and context-aware API usage.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('your-hf-id/model-name')
model = AutoModelForCausalLM.from_pretrained('your-hf-id/model-name')
inputs = tokenizer("local currentTargetEntity = self.Entity.AI", return_tensors='pt')
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs))
| Before | After | Change | |
|---|---|---|---|
| Perplexity | 46.14 | 5.34 | β8.6x |
| Eval loss | 3.83 | 1.68 | β |
| Speed(sec) | 1.30s | 1.28s | - |
Perplexity measures prediction difficulty for language models. Lower values mean more accurate predictions.
Base model: nuprl/MultiPL-T-StarCoderBase_1b
Hugging Face: nuprl/MultiPL-T-StarCoderBase_1b
name: bangill
mail: [email protected]
μ΄ λͺ¨λΈμ MapleStory Worlds Lua API μμ μ½λλ‘ νμΈνλλ νΉν LLMμ
λλ€.
κ²μ μ€ν¬λ¦½νΈ μλν, μ½λ μμ±, λ¬Έλ§₯ κΈ°λ° API νμ©μ μ΅μ νλμ΅λλ€.
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('your-hf-id/model-name')
model = AutoModelForCausalLM.from_pretrained('your-hf-id/model-name')
inputs = tokenizer("local currentTargetEntity = self.Entity.AI", return_tensors='pt')
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs))
| νμ΅ μ | νμ΅ ν | λ³νν | |
|---|---|---|---|
| Perplexity | 46.14 | 5.34 | β8.6λ°° |
| Eval loss | 3.83 | 1.68 | β |
| νκ°μλ | 1.30s | 1.28s | - |
Perplexity: μΈμ΄λͺ¨λΈμ μμΈ‘ λμ΄λλ₯Ό λνλ΄λ μ§νλ‘, κ°μ΄ μμμλ‘ μ λ΅μ κ°κΉμ΄ μμΈ‘μ λλ€.
κΈ°λ³Έ λͺ¨λΈ: nuprl/MultiPL-T-StarCoderBase_1b
νκΉ
νμ΄μ€: https://huggingface.co/nuprl/MultiPL-T-StarCoderBase_1b
μ΄λ¦: bangill
μ΄λ©μΌ: [email protected]