llama_with_eeve_new_03_150m
Model Info
llama μν€ν μ²μ eeve ν ν¬λμ΄μ λ₯Ό μ¬μ©ν΄ λλ€ κ°μ€μΉμμ μμν΄ μ¬μ νμ΅λ λͺ¨λΈμ λλ€
λ€μ μμ€ν ν둬ννΈκ° μ£Όμ΄μ§ μνλ‘ νμ΅νμμ΅λλ€(λͺ¨λΈ μ¬μ© μ ν둬ννΈλ₯Ό ν¬ν¨ν΄μΌ ν©λλ€).
'''### System:\nλΉμ μ λΉλλμ μ΄κ±°λ, μ±μ μ΄κ±°λ, λΆλ²μ μ΄κ±°λ λλ μ¬ν ν΅λ μ μΌλ‘ νμ©λμ§ μλ λ°μΈμ νμ§ μμ΅λλ€. μ¬μ©μμ μ¦κ²κ² λννλ©°, μ¬μ©μμ μλ΅μ κ°λ₯ν μ ννκ³ μΉμ νκ² μλ΅ν¨μΌλ‘μ¨ μ΅λν λμμ£Όλ €κ³ λ Έλ ₯ν©λλ€.
\n\n### User:\n {question}'''
Evaluation results
llm as a judge λ°©μμΌλ‘ νκ°λ₯Ό μ§ννμ΅λλ€. μμΈν λ΄μ©μ " "λ₯Ό μ°Έκ³ ν΄μ£ΌμΈμ
Model | params | Fluency | Coherence | Accuracy | Completeness |
---|---|---|---|---|---|
kikikara/llama_with_eeve_new_03_150m(this) | 0.15B | 63.12% | 37.18% | 23.75% | 23.75% |
EleutherAI/polyglot-ko-1.3b | 1.3B | 51.25% | 40.31% | 34.68% | 32.5% |
EleutherAI/polyglot-ko-5.8b | 5.8B | 54.37% | 40.62% | 41.25% | 35% |
How to use
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
tokenizer = AutoTokenizer.from_pretrained("kikikara/llama_with_eeve_new_03_150m")
model = AutoModelForCausalLM.from_pretrained("kikikara/llama_with_eeve_new_03_150m")
question = "λλ λꡬμΌ?"
prompt = f"### System:\nλΉμ μ λΉλλμ μ΄κ±°λ, μ±μ μ΄κ±°λ, λΆλ²μ μ΄κ±°λ λλ μ¬ν ν΅λ
μ μΌλ‘ νμ©λμ§ μλ λ°μΈμ νμ§ μμ΅λλ€.\nμ¬μ©μμ μ¦κ²κ² λννλ©°, μ¬μ©μμ μλ΅μ κ°λ₯ν μ ννκ³ μΉμ νκ² μλ΅ν¨μΌλ‘μ¨ μ΅λν λμμ£Όλ €κ³ λ
Έλ ₯ν©λλ€.\n\n\n### User:\n {question}"
pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=400, repetition_penalty=1.12)
result = pipe(prompt)
print(result[0]['generated_text'])```
- Downloads last month
- 211
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.