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

Tora Code 7B V1.0 AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Tora Code 7B V1.0 AWQ   URL Share it on

  20   
  Arxiv:2309.17452   4-bit   Autotrain compatible   Awq Base model:llm-agents/tora-cod... Base model:quantized:llm-agent...   Code   Dataset:competition math   Dataset:gsm8k   En   Llama   Math   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/tora-code-7B-v1.0-AWQ 

Tora Code 7B V1.0 AWQ Benchmarks

LLME Score: 0.14507
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tora Code 7B V1.0 AWQ (TheBloke/tora-code-7B-v1.0-AWQ)

Tora Code 7B V1.0 AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Research, Commercial applications
Applications:
Mathematical problem solving
Primary Use Cases:
To solve challenging mathematical reasoning problems by interacting with tools, such as computation libraries and symbolic solvers.
Additional Notes 
The model integrates natural language reasoning with the use of external tools, enhancing both analytical and computational effectiveness.
Supported Languages 
en (English)
Training Details 
Data Sources:
ToRA-Corpus 16k, including tool-integrated reasoning trajectories of MATH and GSM8k from GPT-4
Methodology:
The models are trained using imitation learning (i.e., SFT) and then use output space shaping to enhance tool-integrated reasoning behaviors.
Model Architecture:
Llama
Input Output 
Input Format:
<|user|> {prompt} <|assistant|>
Output Format:
text
LLM NameTora Code 7B V1.0 AWQ
Repository 🤗https://huggingface.co/TheBloke/tora-code-7B-v1.0-AWQ 
Model NameToRA Code 7B v1.0
Model CreatorLLM-Agents
Base Model(s)  llm-agents/tora-code-7b-v1.0   llm-agents/tora-code-7b-v1.0
Model Size7b
Required VRAM3.9 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.34.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16

Best Alternatives to Tora Code 7B V1.0 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB101
Yarn Llama 2 7B 64K AWQ64K / 3.9 GB180
Calm2 7B Chat AWQ32K / 4.4 GB612
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB222
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB160
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB23590
Pandalyst 7B V1.2 AWQ16K / 3.9 GB231
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB221
CodeLlama 7B Instruct AWQ16K / 3.9 GB1764
Pandalyst 7B V1.1 AWQ16K / 3.9 GB321
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/tora-code-7B-v1.0-AWQ.

Rank the Tora Code 7B V1.0 AWQ 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? 40066 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 v20241217
  Support LLM Explorer