Mistral 7B Instruct V0.2 Fp8 by FriendliAI

 ยป  All LLMs  ยป  FriendliAI  ยป  Mistral 7B Instruct V0.2 Fp8   URL Share it on

  Arxiv:2310.06825   8-bit   Autotrain compatible Base model:mistralai/mistral-7...   Conversational   Instruct   License:apache-2.0   Mistral   Pretrained   Region:us   Safetensors

Rank the Mistral 7B Instruct V0.2 Fp8 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  
Mistral 7B Instruct V0.2 Fp8 (FriendliAI/Mistral-7B-Instruct-v0.2-fp8)

Quantized Models of the Mistral 7B Instruct V0.2 Fp8

...ral 7B Instruct V0.2 Onnx Fp160410 GB

Best Alternatives to Mistral 7B Instruct V0.2 Fp8

Best Alternatives
HF Rank
Mistral 7B Instruct V0.262.2332K / 14.4 GB29817401932
Bagel 7B V0.4 AWQ60.132K / 4.2 GB190
Bagel DPO 7B V0.4 AWQ60.132K / 4.2 GB150
Mistral 7B Instruct V0.2 Q454.632K /  GB340
Rubra 11B H 5.0bpw EXL254.632K / 1.7 GB101
...ecurity 7B V0.2 3.0bpw H6 EXL254.632K / 3 GB752
Panda 7B V0.1 3.0bpw H6 EXL254.632K / 3 GB150
....2 Neural Story 3.0bpw H6 EXL254.632K / 3 GB130
...ecurity 7B V0.2 4.0bpw H6 EXL254.632K / 3.9 GB230
Panda 7B V0.1 4.0bpw H6 EXL254.632K / 3.9 GB160
Note: green Score (e.g. "73.2") means that the model is better than FriendliAI/Mistral-7B-Instruct-v0.2-fp8.

Mistral 7B Instruct V0.2 Fp8 Parameters and Internals

LLM NameMistral 7B Instruct V0.2 Fp8
RepositoryOpen on ๐Ÿค— 
Model NameMistral-7B-Instruct-v0.2
Base Model(s)  Mistral 7B Instruct V0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM7.5 GB
Model Typemistral
Model Files  7.5 GB
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 35008 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024040901