Llama 3 8B Instruct 64K AWQ by solidrust

 ยป  All LLMs  ยป  solidrust  ยป  Llama 3 8B Instruct 64K AWQ   URL Share it on

  Arxiv:2309.10400   4-bit   64k   Autotrain compatible   Awq   Axolotl Base model:maziyarpanahi/llama... Base model:quantized:maziyarpa...   Conversational   Dataset:intel/orca dpo pairs   Dpo   En   Endpoints compatible   Facebook   Finetuned   Instruct   Llama   Llama-3   Meta   Pose   Pytorch   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Llama 3 8B Instruct 64K AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B Instruct 64K AWQ (solidrust/Llama-3-8B-Instruct-64k-AWQ)

Llama 3 8B Instruct 64K AWQ Parameters and Internals

Model Type 
text generation
Additional Notes 
AWQ offers faster Transformers-based inference with equivalent or better quality compared to GPTQ settings.
Training Details 
Data Sources:
Intel/orca_dpo_pairs, RedPajama V1
Data Volume:
300M tokens
Methodology:
Continued pretraining with PoSE, rank stabilized LoRA of rank 256
Context Length:
64000
Model Architecture:
Rank stabilized LoRA with PoSE
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameLlama 3 8B Instruct 64K AWQ
Repository ๐Ÿค—https://huggingface.co/solidrust/Llama-3-8B-Instruct-64k-AWQ 
Model NameLlama-3-8B-Instruct-64k
Model CreatorMaziyarPanahi
Base Model(s)  Llama 3 8B Instruct 64K   MaziyarPanahi/Llama-3-8B-Instruct-64k
Model Size8b
Required VRAM5.8 GB
Updated2025-01-24
Maintainersolidrust
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 8B Instruct 64K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB230
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB71
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB124
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB70
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB250
Llama 3 8B Instruct AWQ8K / 5.8 GB1089622
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB11465
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB6388
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB180
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB170
Note: green Score (e.g. "73.2") means that the model is better than solidrust/Llama-3-8B-Instruct-64k-AWQ.

Rank the Llama 3 8B Instruct 64K AWQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227