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

Llama 2 7B Guanaco 8bit Sharded by guardrail

 »  All LLMs  »  guardrail  »  Llama 2 7B Guanaco 8bit Sharded   URL Share it on

  6   

Llama 2 7B Guanaco 8bit Sharded is an open-source language model by guardrail. Features: 7b LLM, VRAM: 7.1GB, Context: 2K, License: apache-2.0, Quantized, HF Score: 50.6, LLM Explorer Score: 0.11, Arc: 53.8, HellaSwag: 78.7, MMLU: 46.7, TruthfulQA: 43.9, WinoGrande: 72.6, GSM8K: 7.8.

  8-bit   8bit Dataset:timdettmers/openassist...   Endpoints compatible   Llama   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/guardrail/llama-2-7b-guanaco-8bit-sharded 

Llama 2 7B Guanaco 8bit Sharded Benchmarks

ARC: 53.75 vs 96.7 (so35)-44.4%
HellaSwag: 78.69 vs 95.3 (gpt4)-17.4%
MMLU: 46.65 vs 88.3 (so35)-47.2%
TruthfulQA: 43.93 vs 59 (gpt4)-25.5%
WinoGrande: 72.61 vs 87.5 (gpt4)-17%
GSM8K: 7.81 vs 96.4 (so35)-91.9%
LLME Score: 0.11349
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Guanaco 8bit Sharded (guardrail/llama-2-7b-guanaco-8bit-sharded)
🌟 Advertise your project 🚀

Llama 2 7B Guanaco 8bit Sharded Parameters and Internals

Model Type 
text-generation
Additional Notes 
The model is sharded for use on a free Google Colab instance and can be easily imported using the `AutoModelForCausalLM` class from `transformers`.
Training Details 
Data Sources:
timdettmers/openassistant-guanaco
Methodology:
Fine-tuned in 4-bit precision using QLoRA
LLM NameLlama 2 7B Guanaco 8bit Sharded
Repository 🤗https://huggingface.co/guardrail/llama-2-7b-guanaco-8bit-sharded 
Base Model(s)  ... 2 7B Guanaco Instruct Sharded   guardrail/llama-2-7b-guanaco-instruct-sharded
Model Size7b
Required VRAM7.1 GB
Updated2026-04-03
Maintainerguardrail
Model Typellama
Model Files  1.0 GB: 1-of-8   1.0 GB: 2-of-8   1.0 GB: 3-of-8   1.0 GB: 4-of-8   1.0 GB: 5-of-8   1.0 GB: 6-of-8   0.8 GB: 7-of-8   0.3 GB: 8-of-8
Quantization Type8bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
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 Llama 2 7B Guanaco 8bit Sharded

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB24
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB43
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB41
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB31
Smaugv0.1 4.65bpw H6 EXL2195K / 20.8 GB31
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB31
DeepSeek Prover V2 7B 4bit64K / 3.9 GB284
Mistral 7B Openplatypus 1K32K / 29 GB18140
Mistral 7B OpenOrca 1K32K / 29 GB18113
...rnlm2 20B Llama 4.0bpw H6 EXL232K / 11 GB11
Note: green Score (e.g. "73.2") means that the model is better than guardrail/llama-2-7b-guanaco-8bit-sharded.

Rank the Llama 2 7B Guanaco 8bit Sharded 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer