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

Pic 7B Mistral Full V0.2 by TokenBender

 »  All LLMs  »  TokenBender  »  Pic 7B Mistral Full V0.2   URL Share it on

  18   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7... Dataset:codefuse-ai/evol-instr... Dataset:huggingfaceh4/no robot...   Dataset:intel/orca dpo pairs   Dataset:open-orca/slimorca Dataset:rizerphe/glaive-functi...   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/TokenBender/pic_7B_mistral_Full_v0.2 

Pic 7B Mistral Full V0.2 Benchmarks

ARC: 65.36 vs 96.7 (so35)-32.4%
HellaSwag: 84.03 vs 95.3 (gpt4)-11.8%
MMLU: 64.51 vs 88.3 (so35)-26.9%
TruthfulQA: 59.2 vs 59 (gpt4)0.3%
WinoGrande: 79.48 vs 87.5 (gpt4)-9.2%
GSM8K: 59.74 vs 96.4 (so35)-38%
LLME Score: 0.15729
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pic 7B Mistral Full V0.2 (TokenBender/pic_7B_mistral_Full_v0.2)

Pic 7B Mistral Full V0.2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
Should be useful in generic capacity. Demonstrates a little bit of everything. Basic tests in roleplay, json/function-calling, and coding.
Additional Notes 
Empathy, coder, and instruction/json/function adherence are key aspects of this model.
Training Details 
Data Sources:
Open-Orca/SlimOrca, HuggingFaceH4/no_robots, Intel/orca_dpo_pairs, rizerphe/glaive-function-calling-v2-zephyr, codefuse-ai/Evol-instruction-66k
Methodology:
SFT + DPO
Input Output 
Input Format:
ChatML (recommended), Alpaca (take care of EOT token)
LLM NamePic 7B Mistral Full V0.2
Repository 🤗https://huggingface.co/TokenBender/pic_7B_mistral_Full_v0.2 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM15 GB
Updated2025-03-20
MaintainerTokenBender
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   4.6 GB: 3-of-4   0.5 GB: 4-of-4
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Pic 7B Mistral Full V0.2

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB245915
SpydazWeb AI HumanAI RP512K / 14.4 GB131
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB50
...1 Summarize 64K LoRANET Merged128K / 14.4 GB140
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB8012011602
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37395
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB37413
Note: green Score (e.g. "73.2") means that the model is better than TokenBender/pic_7B_mistral_Full_v0.2.

Rank the Pic 7B Mistral Full V0.2 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? 45351 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