7B AWQ
Collection
These models are selected for their compatibility with small 12GB memory GPUs. • 203 items • Updated • 2
Text Generation
Transformers
Safetensors
mistral
quantized
4-bit precision
AWQ
chatml
Eval Results (legacy)
text-generation-inference
awq
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("solidrust/Falkor-7b-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Falkor-7b-AWQ")Quick Links
perlthoughts/Falkor-7b AWQ
- Model creator: perlthoughts
- Original model: Falkor-7b
Model summary
dragon-mistral-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Mistral-7B base model.
DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation.
- Downloads last month
- 2
Collection including solidrust/Falkor-7b-AWQ
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard68.260
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.840
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard63.980
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard63.080
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard80.350
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard60.500
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="solidrust/Falkor-7b-AWQ")