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

  8   
  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bujido/Llama3-70B-Chinese-Chat-AWQ-32k 

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: 0.1588
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 (bujido/Llama3-70B-Chinese-Chat-AWQ-32k)
🌟 Advertise your project 🚀

Llama3 70B Chinese Chat AWQ 32K Parameters and Internals

Model Type 
text generation, Chinese chat
Use Cases 
Areas:
Chinese dialogue tasks
Applications:
Chinese chat scenarios
Primary Use Cases:
Chinese dialogue generation
Considerations:
Experimental feature to handle longer contexts may affect performance.
Additional Notes 
Utilizes 4-bit AWQ quantization to maintain performance in resource-limited environments. Supports optional context extension to 32k tokens.
Supported Languages 
Chinese (proficient)
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
Updated2025-10-10
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

Best Alternatives to Llama3 70B Chinese Chat AWQ 32K

Best Alternatives
Context / RAM
Downloads
Likes
...0B Instruct Gradient 1048K AWQ1024K / 39.9 GB131
...70B Instruct Gradient 262K AWQ256K / 39.9 GB60
Llama 3.3 70B Instruct AWQ128K / 39.9 GB3935456
Llama 3.3 70B Instruct AWQ128K / 39.9 GB17963535
...lama 3.3 70B Instruct AWQ INT4128K / 39.9 GB4584025
... SauerkrautLM 70B Instruct AWQ128K / 39.9 GB475
MultiVerse 70B AWQ32K / 41.3 GB22
Opus V1.2 70B AWQ32K / 36.7 GB11
QuartetAnemoi 70B T0.0001 AWQ31K / 36.7 GB71
Senku 70B AWQ 4bit GEMM31K / 36.7 GB61
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? 51544 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 v20241124
  Support LLM Explorer