LLM Name | Codellama High Quality Sft Postgres |
Repository ๐ค | https://huggingface.co/MrezaPRZ/codellama_high_quality_sft_postgres |
Model Size | 7b |
Required VRAM | 13.5 GB |
Updated | 2025-02-22 |
Maintainer | MrezaPRZ |
Model Type | llama |
Model Files | |
Generates Code | Yes |
Model Architecture | LlamaForCausalLM |
Context Length | 16384 |
Model Max Length | 16384 |
Transformers Version | 4.41.1 |
Tokenizer Class | CodeLlamaTokenizer |
Padding Token | </s> |
Vocabulary Size | 32016 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Deepseek Coder 6.7B Instruct | 16K / 13.5 GB | 46744 | 377 |
CodeLlama 7B Hf | 16K / 13.5 GB | 70039 | 347 |
CodeLlama 7B Hf | 16K / 13.5 GB | 24844 | 84 |
CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 43565 | 224 |
CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 30156 | 40 |
GetCode Slerp | 16K / 13.6 GB | 1753 | 1 |
MathCoder2 CodeLlama 7B | 16K / 13.5 GB | 14 | 5 |
Wizardllama 7B | 16K / 13.5 GB | 32 | 0 |
CodeLlama 7B Python Hf | 16K / 13.5 GB | 6503 | 138 |
CodeLlama 7B Hf | 16K / 13.5 GB | 12206 | 3 |
๐ 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! ๐