LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

NexusRaven 13B by Nexusflow

 »  All LLMs  »  Nexusflow  »  NexusRaven 13B   URL Share it on

  103   
  Arxiv:2308.12950   Autotrain compatible Base model:codellama/codellama... Base model:finetune:codellama/...   Codegen   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Nexusflow/NexusRaven-13B 

NexusRaven 13B Benchmarks

LLME Score: 0.14468
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
NexusRaven 13B (Nexusflow/NexusRaven-13B)

NexusRaven 13B Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
We highly recommend using a stop criteria of ["\nReflection:"]. The model was trained to first generate an answer and then reflect on its answer to either improve the answer or keep the answer the same. However, this "chain of thought" is often not helpful, and the final answer is seldom better than the initial call. Therefore, we strongly recommend using the Initial Call as the main call to execute., The model works best when it is connected with a retriever when there are a multitude of functions, as a large number of functions will saturate the context window of this model., The model can be prone to generate incorrect calls. Please ensure proper guardrails to capture errant behavior is in place.
Training Details 
Hardware Used:
multi-GPU
Input Output 
Performance Tips:
We highly recommend stopping the model generation at a stopping criteria of ["\nReflection:"], to avoid spending unnecessary tokens during inference.
LLM NameNexusRaven 13B
Repository 🤗https://huggingface.co/Nexusflow/NexusRaven-13B 
Base Model(s)  CodeLlama 13B Instruct Hf   codellama/CodeLlama-13b-Instruct-hf
Model Size13b
Required VRAM26 GB
Updated2025-02-05
MaintainerNexusflow
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3   0.0 GB
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.33.2
Tokenizer ClassCodeLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32024
Torch Data Typebfloat16

Quantized Models of the NexusRaven 13B

Model
Likes
Downloads
VRAM
NexusRaven 13B GGUF211545 GB
NexusRaven 13B GPTQ7277 GB
NexusRaven 13B AWQ4117 GB

Best Alternatives to NexusRaven 13B

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven V2 13B16K / 26 GB3904466
CodeLlama 13B Instruct Hf16K / 26 GB21714145
CodeLlama 13B MORepair16K / 26 GB262
CodeLlama 13B Instruct Hf16K / 26 GB120520
... Llama 2 13B Instruct Text2sql16K / 26 GB1295727
TableLLM 13B16K / 26 GB25526
Panda Coder 13B16K / 26 GB3613
Gen Sim16K / 0.3 GB1432
CodeLlama 13B Instruct Fp1616K / 26 GB243528
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB662
Note: green Score (e.g. "73.2") means that the model is better than Nexusflow/NexusRaven-13B.

Rank the NexusRaven 13B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 42565 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer