Krisseck commited on
Commit
6702dc3
1 Parent(s): 34de337

qwen 2 results

Browse files
Files changed (1) hide show
  1. IFEval.csv +1 -0
IFEval.csv CHANGED
@@ -1,6 +1,7 @@
1
  Model,Params (B),Repo,Quantization,Final Score,Strict Prompt Score,Strict Inst Score,Loose Prompt Score,Loose Inst Score,Link
2
  LLama 3 70B,70,perplexity/llama-3-sonar-large-32k-chat (Openrouter),FP16,0.8331,0.7671,0.8381,0.8373,0.8897,https://openrouter.ai/models/perplexity/llama-3-sonar-large-32k-chat
3
  LLama 3 70B,70,llama3-70b-8192 (Groq),FP16,0.8175,0.7431,0.8213,0.8244,0.8813,https://console.groq.com/docs/models
 
4
  Llama 3 8B,8,QuantFactory/NeuralDaredevil-8B-abliterated-GGUF,Q8_0,0.7884,0.7357,0.8058,0.7763,0.8357,https://huggingface.co/QuantFactory/NeuralDaredevil-8B-abliterated-GGUF
5
  Command R+,104,cohere/command-r-plus (Openrouter),FP16,0.7701,0.7190,0.7962,0.7450,0.8201,https://openrouter.ai/models/cohere/command-r-plus
6
  Llama 3 8B,8,failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF,Q8_0,0.7589,0.7001,0.7818,0.7394,0.8141,https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF
 
1
  Model,Params (B),Repo,Quantization,Final Score,Strict Prompt Score,Strict Inst Score,Loose Prompt Score,Loose Inst Score,Link
2
  LLama 3 70B,70,perplexity/llama-3-sonar-large-32k-chat (Openrouter),FP16,0.8331,0.7671,0.8381,0.8373,0.8897,https://openrouter.ai/models/perplexity/llama-3-sonar-large-32k-chat
3
  LLama 3 70B,70,llama3-70b-8192 (Groq),FP16,0.8175,0.7431,0.8213,0.8244,0.8813,https://console.groq.com/docs/models
4
+ Qwen 2 72B,72,qwen/qwen-2-72b-instruct (Openrouter),FP16,0.8056,0.7579,0.8357,0.7781,0.8513,https://openrouter.ai/models/qwen/qwen-2-72b-instruct
5
  Llama 3 8B,8,QuantFactory/NeuralDaredevil-8B-abliterated-GGUF,Q8_0,0.7884,0.7357,0.8058,0.7763,0.8357,https://huggingface.co/QuantFactory/NeuralDaredevil-8B-abliterated-GGUF
6
  Command R+,104,cohere/command-r-plus (Openrouter),FP16,0.7701,0.7190,0.7962,0.7450,0.8201,https://openrouter.ai/models/cohere/command-r-plus
7
  Llama 3 8B,8,failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF,Q8_0,0.7589,0.7001,0.7818,0.7394,0.8141,https://huggingface.co/failspy/Meta-Llama-3-8B-Instruct-abliterated-v3-GGUF