Openchat 3.5 0106 AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Openchat 3.5 0106 AWQ   URL Share it on

  Arxiv:2303.08774   Arxiv:2309.11235   4-bit   Autotrain compatible   Awq Base model:openchat/openchat-3... Base model:quantized:openchat/...   C-rlft   Conversational   Mistral   Openchat   Quantized   Region:us   Safetensors

Openchat 3.5 0106 AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openchat 3.5 0106 AWQ (TheBloke/openchat-3.5-0106-AWQ)

Openchat 3.5 0106 AWQ Parameters and Internals

Model Type 
mistral, text-generation
Use Cases 
Areas:
research, commercial applications
Primary Use Cases:
Coding, Generalist, Mathematical Reasoning
Limitations:
Complex reasoning, Mathematical and arithmetic tasks, Programming and coding challenges, Hallucination of non-existent information
Additional Notes 
The model uses efficient low-bit quantization (AWQ) providing faster inference with Nvidia GPUs and supports high-throughput deployment. The release emphasizes advancements in open-source models through mixed-quality data.
Training Details 
Data Sources:
VMware Open Instruct
Methodology:
AWQ quantization, 4-bit quantization
Context Length:
8192
Hardware Used:
Massed Compute
Input Output 
Input Format:
"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
Accepted Modalities:
text
Output Format:
text
Release Notes 
Notes:
The model provides improvements in coding capabilities and is tailored for generalist and mathematical reasoning tasks.
LLM NameOpenchat 3.5 0106 AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/openchat-3.5-0106-AWQ 
Model NameOpenchat 3.5 0106
Model CreatorOpenChat
Base Model(s)  openchat/openchat-3.5-0106   openchat/openchat-3.5-0106
Model Size1.2b
Required VRAM4.2 GB
Updated2025-01-20
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Openchat 3.5 0106 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Feedback Wizard 4bit AWQ32K / 4.2 GB240
Quantized Kheopss AWQ 4bits V132K / 4.2 GB170
Ryze AWQ 4bit32K / 4.2 GB200
Dictalm2.0 Instruct AWQ32K / 4.2 GB6360
...lot Engine Step Json Short AWQ32K / 4.2 GB190
...V3 Plot Chat Roleplay Chat AWQ32K / 4.2 GB190
Dictalm2.0 AWQ32K / 4.2 GB3290
MistralLite AWQ32K / 4.2 GB223
SFR Embedding Mistral AWQ32K / 4.2 GB160
LemonadeRP 4.5.3 AWQ32K / 4.2 GB90
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/openchat-3.5-0106-AWQ.

Rank the Openchat 3.5 0106 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? 41636 in total.

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