LLM EXPLORER 60,645 MODELS INDEXED

Llama 3 8B Instruct Gradient 1048K Agent by AIGym

By AIGym · 51 downloads
HF Repo ↗ Copy URL

Llama 3 8B Instruct Gradient 1048K Agent is an open-source language model by AIGym. Features: 8b LLM, VRAM: 16.1GB, Context: 1024K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12.

  Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AIGym/Llama-3-8B-Instruct-Gradient-1048k-Agent 

Llama 3 8B Instruct Gradient 1048K Agent Parameters and Internals

Use Cases 
Areas:
Integration with crewai
Applications:
Chatbot, AI Agent
Primary Use Cases:
Chat-based applications
Limitations:
Usage outside crewai is out-of-scope
Considerations:
Recommended to self-host or use in the cloud
Additional Notes 
Automatically generated model card on Hugging Face
Training Details 
Data Sources:
m-a-p/CodeFeedback-Filtered-Instruction, RomanTeucher/awesome_topic_code_snippets, dair-ai/emotion, mzbac/function-calling-llama-3-format-v1.1, gretelai/synthetic_text_to_sql
Methodology:
Fine-tuned from Llama 3 high context length version
Context Length:
1048000
Input Output 
Input Format:
<|begin_of_text|><|start_header_id|>user<|end_header_id|> {prompt} <|eot_id|>
Accepted Modalities:
text
Output Format:
<|start_header_id|>assistant<|end_header_id|>
Performance Tips:
Host in the cloud or self-host for best results with crewai
LLM NameLlama 3 8B Instruct Gradient 1048K Agent
Repository 🤗https://huggingface.co/AIGym/Llama-3-8B-Instruct-Gradient-1048k-Agent 
Model Size8b
Required VRAM16.1 GB
Updated2024-12-12
MaintainerAIGym
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length1048576
Model Max Length1048576
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Quantized Models of the Llama 3 8B Instruct Gradient 1048K Agent

Model
Likes
Downloads
VRAM
...B Instruct Gradient 1048K 4bit2104 GB
...B Instruct Gradient 1048K 8bit1118 GB
...truct Gradient 1048K Bpw6 EXL2226 GB
...truct Gradient 1048K Bpw5 EXL2055 GB

Best Alternatives to Llama 3 8B Instruct Gradient 1048K Agent

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB1135125
UltraLong Thinking4192K / 16.1 GB23
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB12418
Cthulhu 8B V1.41048K / 16.1 GB1010
...raLong 1M Instruct Abliterated1048K / 32.1 GB49
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB70259
Zero Llama 3.1 8B Beta61048K / 16.1 GB71
Note: green Score (e.g. "73.2") means that the model is better than AIGym/Llama-3-8B-Instruct-Gradient-1048k-Agent.