Phi3 Telecom by lakshyasoni

 ยป  All LLMs  ยป  lakshyasoni  ยป  Phi3 Telecom   URL Share it on

  4bit Base model:finetune:unsloth/ph... Base model:unsloth/phi-3-mini-...   Conversational   En   Endpoints compatible   Instruct   Lora   Mistral   Quantized   Region:us   Safetensors   Trl   Unsloth

Phi3 Telecom Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Phi3 Telecom (lakshyasoni/phi3_telecom)

Phi3 Telecom Parameters and Internals

Model Type 
text-generation
Additional Notes 
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NamePhi3 Telecom
Repository ๐Ÿค—https://huggingface.co/lakshyasoni/phi3_telecom 
Base Model(s)  ...hi 3 Mini 4K Instruct Bnb 4bit   unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Required VRAM0.1 GB
Updated2025-02-16
Maintainerlakshyasoni
Instruction-BasedYes
Model Files  0.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureAutoModel
Licenseapache-2.0
Model Max Length4096
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj|gate_proj|o_proj|up_proj|k_proj|down_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to Phi3 Telecom

Best Alternatives
Context / RAM
Downloads
Likes
Lora Model0K / 0.1 GB11890
Phi 3.1 EvolKit Lora0K / 0.1 GB01
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB35541612
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB7497301
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB10433138
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB108816
Spydaz Web AI 0K / 4.4 GB1583
...i 3 Mini 4K Instruct V0.3 GGUF0K / 1.4 GB2275
Autocomplete Model0K / 4.1 GB270
Phi 3 Mini 4K Instruct0K / 2.3 GB160
Note: green Score (e.g. "73.2") means that the model is better than lakshyasoni/phi3_telecom.

Rank the Phi3 Telecom 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? 43187 in total.

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