Hugging Face's logo

kimhyeongjun
/
Hermes-3-Llama-3.1-8B-Korean-Finance-Advisor

Text Generation
Transformers
Safetensors
llama
llama-factory
full
unsloth
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files
kimhyeongjun commited on
Commit
535fd25
β€’
1 Parent(s): 361e233

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -24,13 +24,13 @@ This model is a fine-tuned version of [NousResearch/Hermes-3-Llama-3.1-8B](https
24
 
25
  Everything happened automatically without any user intervention.
26
 
27
- Based on finance PDF data collected directly from the web, we refined the raw data using the 'meta-llama/Meta-Llama-3.1-70B-Instruct-FP8' model.
28
  After generating synthetic data based on the cleaned data, we further evaluated the quality of the generated data using the 'meta-llama/Llama-Guard-3-8B' and 'RLHFlow/ArmoRM-Llama3-8B-v0.1' models.
29
  We then used 'Alibaba-NLP/gte-large-en-v1.5' to extract embeddings and applied Faiss to perform Jaccard distance-based nearest neighbor analysis to construct the final dataset of 21k, which is diverse and sophisticated.
30
 
31
  λͺ¨λ“  과정은 μ‚¬μš©μžμ˜ κ°œμž… 없이 μžλ™μœΌλ‘œ μ§„ν–‰λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
32
 
33
- μ›Ήμ—μ„œ 직접 μˆ˜μ§‘ν•œ 금육 κ΄€λ ¨ PDF 데이터λ₯Ό 기반으둜, 돈이 μ—†μ–΄μ„œ 'meta-llama/Meta-Llama-3.1-70B-Instruct-FP8' λͺ¨λΈμ„ ν™œμš©ν•˜μ—¬ Raw 데이터λ₯Ό μ •μ œν•˜μ˜€μŠ΅λ‹ˆλ‹€.
34
  μ •μ œλœ 데이터λ₯Ό λ°”νƒ•μœΌλ‘œ ν•©μ„± 데이터λ₯Ό μƒμ„±ν•œ ν›„, 'meta-llama/Llama-Guard-3-8B' 및 'RLHFlow/ArmoRM-Llama3-8B-v0.1' λͺ¨λΈμ„ 톡해 μƒμ„±λœ λ°μ΄ν„°μ˜ ν’ˆμ§ˆμ„ μ‹¬μΈ΅μ μœΌλ‘œ ν‰κ°€ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
35
  μ΄μ–΄μ„œ 'Alibaba-NLP/gte-large-en-v1.5'λ₯Ό μ‚¬μš©ν•˜μ—¬ μž„λ² λ”©μ„ μΆ”μΆœν•˜κ³ , Faissλ₯Ό μ μš©ν•˜μ—¬ μžμΉ΄λ“œ 거리 기반의 κ·Όμ ‘ 이웃 뢄석을 μˆ˜ν–‰ν•¨μœΌλ‘œμ¨ λ‹€μ–‘ν•˜κ³  μ •κ΅ν•œ μ΅œμ’… 데이터셋 21k을 직접 κ΅¬μ„±ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
36
 
 
24
 
25
  Everything happened automatically without any user intervention.
26
 
27
+ Based on finance PDF data collected directly from the web, we refined the raw data using the 'neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8' model.
28
  After generating synthetic data based on the cleaned data, we further evaluated the quality of the generated data using the 'meta-llama/Llama-Guard-3-8B' and 'RLHFlow/ArmoRM-Llama3-8B-v0.1' models.
29
  We then used 'Alibaba-NLP/gte-large-en-v1.5' to extract embeddings and applied Faiss to perform Jaccard distance-based nearest neighbor analysis to construct the final dataset of 21k, which is diverse and sophisticated.
30
 
31
  λͺ¨λ“  과정은 μ‚¬μš©μžμ˜ κ°œμž… 없이 μžλ™μœΌλ‘œ μ§„ν–‰λ˜μ—ˆμŠ΅λ‹ˆλ‹€.
32
 
33
+ μ›Ήμ—μ„œ 직접 μˆ˜μ§‘ν•œ 금육 κ΄€λ ¨ PDF 데이터λ₯Ό 기반으둜, 돈이 μ—†μ–΄μ„œ 'neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8' λͺ¨λΈμ„ ν™œμš©ν•˜μ—¬ Raw 데이터λ₯Ό μ •μ œν•˜μ˜€μŠ΅λ‹ˆλ‹€.
34
  μ •μ œλœ 데이터λ₯Ό λ°”νƒ•μœΌλ‘œ ν•©μ„± 데이터λ₯Ό μƒμ„±ν•œ ν›„, 'meta-llama/Llama-Guard-3-8B' 및 'RLHFlow/ArmoRM-Llama3-8B-v0.1' λͺ¨λΈμ„ 톡해 μƒμ„±λœ λ°μ΄ν„°μ˜ ν’ˆμ§ˆμ„ μ‹¬μΈ΅μ μœΌλ‘œ ν‰κ°€ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
35
  μ΄μ–΄μ„œ 'Alibaba-NLP/gte-large-en-v1.5'λ₯Ό μ‚¬μš©ν•˜μ—¬ μž„λ² λ”©μ„ μΆ”μΆœν•˜κ³ , Faissλ₯Ό μ μš©ν•˜μ—¬ μžμΉ΄λ“œ 거리 기반의 κ·Όμ ‘ 이웃 뢄석을 μˆ˜ν–‰ν•¨μœΌλ‘œμ¨ λ‹€μ–‘ν•˜κ³  μ •κ΅ν•œ μ΅œμ’… 데이터셋 21k을 직접 κ΅¬μ„±ν•˜μ˜€μŠ΅λ‹ˆλ‹€.
36