Model 007 13B V2 by pankajmathur

 ยป  All LLMs  ยป  pankajmathur  ยป  Model 007 13B V2   URL Share it on

  Arxiv:2306.02707   Autotrain compatible Dataset:databricks/databricks-...   Dataset:ehartford/dolphin Dataset:garage-baind/open-plat...   Dataset:psmathur/alpaca orca   Dataset:psmathur/dolly-v2 orca Dataset:psmathur/orca mini v1 ...   Dataset:psmathur/wizardlm orca   Dataset:tatsu-lab/alpaca Dataset:wizardlm/wizardlm evol...   En   Endpoints compatible   Fp16   Instruct   Llama   Model-index   Pytorch   Quantized   Region:us   Sharded

Model 007 13b V2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Model 007 13B V2 (pankajmathur/model_007_13b_v2)

Model 007 13B V2 Parameters and Internals

Model Type 
text generation
Additional Notes 
Model evaluates accurately with established benchmarks but can produce unexpected outputs. Approach results with caution due to potential bias and inaccuracies.
Supported Languages 
en (high)
Input Output 
Input Format:
The model expects prompts such as:\n### User: [Your question]\n### Assistant:\n
Accepted Modalities:
text
Output Format:
Text response relevant to the input prompt.
Performance Tips:
Ensure optimal GPU setup for large token generation and consider prompt structuring advice for best results.
LLM NameModel 007 13b V2
Repository ๐Ÿค—https://huggingface.co/pankajmathur/model_007_13b_v2 
Model Size13b
Required VRAM26 GB
Updated2025-02-18
Maintainerpankajmathur
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Model 007 13B V2

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B Instruct Fp1616K / 26 GB321828
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB1032
...13B Instruct Nf4 Fp16 Upscaled16K / 26 GB1320
...B Fast Instruct 4bit Quantized4K / 7.8 GB760
...igogne2 Enno 13B Sft Lora 4bit4K / 26 GB7860
Xwin LM 13B V0.2 EXL24K / 5.2 GB153
Mythalion 13B 2.30bpw H4 EXL24K / 4.1 GB123
...lion Kimiko V2.6.05bpw H8 EXL24K / 10.1 GB71
Law LLM 13B 4.0bpw H6 EXL22K / 6.8 GB51
Finance LLM 13B 6.0bpw H6 EXL22K / 10 GB41
Note: green Score (e.g. "73.2") means that the model is better than pankajmathur/model_007_13b_v2.

Rank the Model 007 13B V2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 43267 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227