CodeLlama 7B Instruct Hf Dequantized is an open-source language model by predibase. Features: 7b LLM, VRAM: 13.5GB, Context: 16K, License: apache-2.0, Instruction-Based, Code Generating, LLM Explorer Score: 0.13.
Autotrain compatible Base model:codellama/codellama... Base model:finetune:codellama/... Codegen Conversational En Endpoints compatible Instruct Llama Region:us Safetensors Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/predibase/CodeLlama-7b-Instruct-hf-dequantized
CodeLlama 7B Instruct Hf Dequantized Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
CodeLlama 7B Instruct Hf Dequantized Parameters and Internals
| LLM Name | CodeLlama 7B Instruct Hf Dequantized |
| Repository 🤗 | https://huggingface.co/predibase/CodeLlama-7b-Instruct-hf-dequantized |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.5 GB |
| Updated | 2024-08-10 |
| Maintainer | predibase |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.39.3 |
| Tokenizer Class | CodeLlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32016 |
| Torch Data Type | bfloat16 |
Best Alternatives to CodeLlama 7B Instruct Hf Dequantized
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek Coder 6.7B Instruct | 16K / 13.5 GB | 215811 | 491 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 224984 | 255 |
| GetCode Slerp | 16K / 13.6 GB | 139 | 1 |
| Stack Codellama 7B Inst | 16K / 13.5 GB | 92 | 0 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 2794 | 59 |
| CodeV CL 7B | 16K / 13.5 GB | 13 | 1 |
| Glaive Coder 7B | 16K / 27 GB | 1015 | 55 |
| ...deLlama 7B Instruct Hf 8bits Q | 16K / 4.2 GB | 4 | 1 |
| Llama 2 7B Chat Finetune5 | 16K / 13.8 GB | 6 | 1 |
| CodeLLama SFT FILTERED | 16K / 13.5 GB | 6 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than predibase/CodeLlama-7b-Instruct-hf-dequantized .
Rank the CodeLlama 7B Instruct Hf Dequantized Capabilities
🆘 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! 🌟
What open-source LLMs or SLMs are you in search of? 53472 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a