LLM EXPLORER 60,783 MODELS INDEXED

Llama 2 70B Chat Hf by meta-llama

By meta-llama · 6028 downloads
HF Repo ↗ Copy URL

Llama 2 70B Chat Hf is an open-source language model by meta-llama. Features: 70b LLM, VRAM: 138GB, Context: 4K, License: llama2, LLM Explorer Score: 0.31, ELO: 1108, Arc: 64.6, HellaSwag: 85.9, MMLU: 63.9, GSM8K: 26.7.

  Arxiv:2307.09288   Conversational   En   Endpoints compatible   Facebook   Llama   Llama2   Meta   Pytorch   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/meta-llama/Llama-2-70b-chat-hf 

Llama 2 70B Chat Hf Benchmarks

LMSys ELO 1108 vs 1272 (so35) -12.9%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 2 70B Chat Hf Parameters and Internals

Model Type 
Pretrained, Fine-tuned generative text models
Use Cases 
Areas:
Commercial, Research
Primary Use Cases:
Assistant-like chat, Natural language generation tasks
Limitations:
English only, Subject to Acceptable Use Policy, Potential for bias and inaccurate responses
Considerations:
Perform application-specific safety testing
Additional Notes 
Llama 2 70B uses Grouped-Query Attention (GQA) for improved inference scalability
Supported Languages 
English (Optimized for dialogue use cases)
Training Details 
Data Sources:
Publicly available online data
Data Volume:
2 trillion tokens
Methodology:
Supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:
4096
Hardware Used:
A100-80GB GPUs
Model Architecture:
Auto-regressive language model with an optimized transformer architecture
Safety Evaluation 
Ethical Considerations:
Testing conducted mainly in English; potential for biased or objectionable responses; safety testing recommended before deployment
Responsible Ai Considerations 
Mitigation Strategies:
Safety testing and tuning before deployment
Input Output 
Input Format:
Text
Accepted Modalities:
Text
Output Format:
Text
LLM NameLlama 2 70B Chat Hf
Repository 🤗https://huggingface.co/meta-llama/Llama-2-70b-chat-hf 
Model Size70b
Required VRAM138 GB
Updated2026-07-06
Maintainermeta-llama
Model Typellama
Model Files  9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15   9.8 GB: 1-of-15   9.8 GB: 2-of-15   10.0 GB: 3-of-15   9.8 GB: 4-of-15   9.8 GB: 5-of-15   9.8 GB: 6-of-15   10.0 GB: 7-of-15   9.8 GB: 8-of-15   9.8 GB: 9-of-15   9.8 GB: 10-of-15   10.0 GB: 11-of-15   9.8 GB: 12-of-15   9.8 GB: 13-of-15   9.5 GB: 14-of-15   0.5 GB: 15-of-15
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Llama 2 70B Chat Hf

Model
Likes
Downloads
VRAM
Llama 2 70B Chat GGUF122361929 GB
WizardLM 70B V1.0 GPTQ1836 GB
Llama2 70B Chat 4bit AWQ1236 GB
Llama 2 70B Chat AWQ2446036 GB
Llama 2 70B Chat GPTQ25940835 GB
Llama 2 70B Chat GGML1611028 GB
Llama 2 70B Chat 4bit Japanese573 GB

Best Alternatives to Llama 2 70B Chat Hf

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB76844
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB22122
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB2423
...a 3 70B Instruct Gradient 262K256K / 141.9 GB2056
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB103
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB50
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB213
Yi 70B 200K RPMerge Franken195K / 142.4 GB121