Llama 3 Instruct Bellman 8B Swedish by neph1

 ยป  All LLMs  ยป  neph1  ยป  Llama 3 Instruct Bellman 8B Swedish   URL Share it on

  4-bit   Autotrain compatible   Bitsandbytes   Conversational Dataset:neph1/bellman-7b-finet... Dataset:neph1/codefeedback-swe...   Endpoints compatible   Gguf   Instruct   Llama   Lora   Pytorch   Region:us   Safetensors   Sv   Unsloth

Llama 3 Instruct Bellman 8B Swedish 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 Instruct Bellman 8B Swedish Parameters and Internals

Model Type 
Instruct
Additional Notes 
Previously struggled with generating stories but has improved.
Supported Languages 
Swedish (Proficient)
Training Details 
Data Sources:
Swedish Wikipedia, neph1/bellman-7b-finetune, neph1/codefeedback-swedish
Methodology:
Prompt Question Answering Finetuning
LLM NameLlama 3 Instruct Bellman 8B Swedish
Repository ๐Ÿค—https://huggingface.co/neph1/llama-3-instruct-bellman-8b-swedish 
Model Size8b
Required VRAM0 GB
Updated2024-11-21
Maintainerneph1
Instruction-BasedYes
Model Files  0.7 GB   0.3 GB   0.0 GB   0.0 GB
Supported Languagessv
Model ArchitectureAutoModelForCausalLM
Licensellama3
Model Max Length8192
Is Biasednone
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|q_proj|up_proj|down_proj|k_proj|o_proj|gate_proj
LoRA Alpha128
LoRA Dropout0.1
R Param64
Llama 3 Instruct Bellman 8B Swedish (neph1/llama-3-instruct-bellman-8b-swedish)

Best Alternatives to Llama 3 Instruct Bellman 8B Swedish

Best Alternatives
Context / RAM
Downloads
Likes
Codelica0K / 16.1 GB1110
...Instruct Persian Finetuned Sft0K / 0 GB1975
ModeliCo 8B0K / 16.1 GB182
Meta Llama 3.1 8B Instruct OAS0K / 16.1 GB2871
... Meta Llama 3 8B Instruct Lora0K / 0.7 GB173
Llama 3 8B Instruct Spider0K / 16.1 GB370
...3 Project Management Assistant0K / 0.2 GB201
...ama 3 8B Instruct Bnb Telcom 30K / 0.2 GB120
Llama300K / 16.1 GB120
Llama260K / 16.1 GB90
Note: green Score (e.g. "73.2") means that the model is better than neph1/llama-3-instruct-bellman-8b-swedish.

Rank the Llama 3 Instruct Bellman 8B Swedish 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? 38199 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110