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

Llama3 70B Chinese Chat AWQ 32K by bujido

 »  All LLMs  »  bujido  »  Llama3 70B Chinese Chat AWQ 32K   URL Share it on

  30   
  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Llama3 70B Chinese Chat AWQ 32K Benchmarks

ARC: 70.39 vs 96.7 (so35)-27.2%
HellaSwag: 85.81 vs 95.3 (gpt4)-10%
MMLU: 79.74 vs 88.3 (so35)-9.7%
TruthfulQA: 61.1 vs 59 (gpt4)3.6%
WinoGrande: 83.74 vs 87.5 (gpt4)-4.3%
GSM8K: 83.24 vs 96.4 (so35)-13.7%
LLME Score: 0.22776
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama3 70B Chinese Chat AWQ 32K Parameters and Internals

LLM NameLlama3 70B Chinese Chat AWQ 32K
Repository 🤗https://huggingface.co/bujido/Llama3-70B-Chinese-Chat-AWQ-32k 
Base Model(s)  Llama3 70B Chinese Chat   shenzhi-wang/Llama3-70B-Chinese-Chat
Model Size70b
Required VRAM39.9 GB
Updated2024-09-07
Maintainerbujido
Model Typellama
Model Files  5.0 GB: 1-of-9   4.9 GB: 2-of-9   4.9 GB: 3-of-9   4.9 GB: 4-of-9   4.9 GB: 5-of-9   4.9 GB: 6-of-9   4.9 GB: 7-of-9   3.4 GB: 8-of-9   2.1 GB: 9-of-9
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|eot_id|>
Vocabulary Size128256
Torch Data Typefloat16
Llama3 70B Chinese Chat AWQ 32K (bujido/Llama3-70B-Chinese-Chat-AWQ-32k)

Best Alternatives to Llama3 70B Chinese Chat AWQ 32K

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB41
...70B Instruct Gradient 262K AWQ256K / 39.9 GB60
MultiVerse 70B AWQ32K / 41.3 GB662
Opus V1.2 70B AWQ32K / 36.7 GB211
QuartetAnemoi 70B T0.0001 AWQ31K / 36.7 GB241
Senku 70B AWQ 4bit GEMM31K / 36.7 GB151
Kiqu 70B AWQ31K / 36.7 GB281
CodeLlama 70B Hf AWQ16K / 36.6 GB194
Llama 3 70B Instruct AWQ8K / 39.9 GB12387066
...Sft M1 D5 Abliterated AWQ 4bit8K / 39.9 GB12141
Note: green Score (e.g. "73.2") means that the model is better than bujido/Llama3-70B-Chinese-Chat-AWQ-32k.

Rank the Llama3 70B Chinese Chat AWQ 32K 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? 35693 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 v2024072803
  Support LLM Explorer