mistral-7b-legal-ecuatoriano-v5-gguf

101
license:apache-2.0
by
demianros
Other
OTHER
7B params
New
101 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
16GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
7GB+ RAM

Training Data Analysis

🟑 Average (5.3/10)

Researched training datasets used by mistral-7b-legal-ecuatoriano-v5-gguf with quality assessment

Specialized For

general
science
code
multilingual
reasoning

Training Datasets (4)

common crawl
πŸ”΄ 2.5/10
general
science
Key Strengths
  • β€’Scale and Accessibility: At 9.5+ petabytes, Common Crawl provides unprecedented scale for training d...
  • β€’Diversity: The dataset captures billions of web pages across multiple domains and content types, ena...
  • β€’Comprehensive Coverage: Despite limitations, Common Crawl attempts to represent the broader web acro...
Considerations
  • β€’Biased Coverage: The crawling process prioritizes frequently linked domains, making content from dig...
  • β€’Large-Scale Problematic Content: Contains significant amounts of hate speech, pornography, violent c...
the pile
🟒 8/10
code
general
science
multilingual
Key Strengths
  • β€’Deliberate Diversity: Explicitly curated to include diverse content types (academia, code, Q&A, book...
  • β€’Documented Quality: Each component dataset is thoroughly documented with rationale for inclusion, en...
  • β€’Epoch Weighting: Component datasets receive different training epochs based on perceived quality, al...
wikipedia
🟑 5/10
science
multilingual
Key Strengths
  • β€’High-Quality Content: Wikipedia articles are subject to community review, fact-checking, and citatio...
  • β€’Multilingual Coverage: Available in 300+ languages, enabling training of models that understand and ...
  • β€’Structured Knowledge: Articles follow consistent formatting with clear sections, allowing models to ...
Considerations
  • β€’Language Inequality: Low-resource language editions have significantly lower quality, fewer articles...
  • β€’Biased Coverage: Reflects biases in contributor demographics; topics related to Western culture and ...
arxiv
🟑 5.5/10
science
reasoning
Key Strengths
  • β€’Scientific Authority: Peer-reviewed content from established repository
  • β€’Domain-Specific: Specialized vocabulary and concepts
  • β€’Mathematical Content: Includes complex equations and notation
Considerations
  • β€’Specialized: Primarily technical and mathematical content
  • β€’English-Heavy: Predominantly English-language papers

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

πŸš€ Usopythonllama.cpp
from llama_cpp import Llama

# Cargar modelo
model = Llama(
    model_path="mistral-legal-q4-k-m.gguf",
    n_ctx=4096,
    n_threads=8,
    verbose=False
)

# Prompt segΓΊn formato de entrenamiento
prompt = '''<s>[INST] Eres un Juez y Auditor JurΓ­dico Experto. Analiza la siguiente sentencia segΓΊn la metodologΓ­a de Manuel Atienza (7 puntos).

SENTENCIA:
[Texto de la sentencia aquΓ­]

GENERA el anΓ‘lisis siguiendo EXACTAMENTE este formato:
**1. NARRACIΓ“N DE HECHOS**
**2. PROBLEMA JURÍDICO**
**3. CUESTIONES Y SUBCUESTIONES**
**4. RESPUESTAS A LAS CUESTIONES**
**5. RATIO DECIDENDI Y OBITER DICTUM**
**6. SOLUCIΓ“N AL PROBLEMA**
**7. DECISIΓ“N**
[/INST]'''

# Generar anΓ‘lisis
output = model(prompt, max_tokens=2000, temperature=0.7)
print(output['choices'][0]['text'])
OpciΓ³n 3: IntegraciΓ³n en Sistemapythonllama.cpp
# Sistema completo con RAG
from llama_cpp import Llama
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings

# 1. Cargar modelo
llm = Llama(model_path="mistral-legal-q4-k-m.gguf", n_ctx=4096)

# 2. Cargar Γ­ndice RAG (corpus legal)
embeddings = HuggingFaceEmbeddings(model_name="intfloat/multilingual-e5-base")
vectorstore = FAISS.load_local("./indices/legal_corpus", embeddings)

# 3. Buscar contexto relevante
docs = vectorstore.similarity_search(query, k=5)
contexto = "\n".join([doc.page_content for doc in docs])

# 4. Generar anΓ‘lisis con contexto
prompt_con_rag = f'''[INST] ...

CONTEXTO LEGAL RELEVANTE:
{contexto}

SENTENCIA:
{texto_sentencia}
[/INST]'''

analisis = llm(prompt_con_rag, max_tokens=2000)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.