Autotrain compatible Codegen Conversational Dataset:ajibawa-2023/code-290k... Dataset:anon8231489123/sharegp... Dataset:camel-ai Dataset:chargoddard/commitpack... Dataset:cognitivecomputations/... Dataset:collectivecognition/ch... Dataset:coseal/codeultrafeedba... Dataset:cot-alpaca-gpt4 Dataset:cybernative/code vulne... Dataset:garage-baind/open-plat... Dataset:glaiveai/glaive-code-a... Dataset:glaiveai/glaive-functi... Dataset:gpteacher Dataset:iamturun/code instruct... Dataset:ise-uiuc/magicoder-evo... Dataset:jondurbin/airoboros-2.... Dataset:layoric/tiny-codes-alp... Dataset:lmsys/lmsys-chat-1m Dataset:meta-math/metamathqa Dataset:nickrosh/evol-instruct... Dataset:open-orca/slimorca Dataset:opengpt Dataset:replete-ai/code bagel Dataset:replete-ai/code bagel ... Dataset:replete-ai/openhermes-... Dataset:teknium/gpt4-llm-clean... Dataset:teknium/openhermes-2.5 Dataset:tiger-lab/mathinstruct Dataset:unnatural-instructions... Dataset:wizardlm/wizardlm evol... Dataset:wizardlm/wizardlm evol... Endpoints compatible Instruct Llama Model-index Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B
Replete Coder Llama3 8B Benchmarks
MMLU Pro: 3.67
GPQA: 1.45
MUSR: 7.51
BBH: 7.06
IFEval: 47.29 vs 88 (so35)-46.3%
MATH Lvl 5: 3.4
LLME Score: 0.26206
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)
Replete Coder Llama3 8B Parameters and Internals
| LLM Name | Replete Coder Llama3 8B |
| Repository 🤗 | https://huggingface.co/Replete-AI/Replete-Coder-Llama3-8B |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2024-10-06 |
| Maintainer | Replete-AI |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 8192 |
| Model Max Length | 8192 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| Vocabulary Size | 128256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Replete Coder Llama3 8B
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Athena Llama Coder 3 8B | 32K / 16.1 GB | 15 | 1 |
| ...plete Coder Instruct 8B Merged | 8K / 16.1 GB | 2573 | 1 |
| Rombos Replete Coder Llama3 8B | 8K / 16.1 GB | 3245 | 2 |
| ...plete Coder Instruct 8B Merged | 8K / 16.1 GB | 43 | 4 |
| Test Dataset Codellama 3 8B | 8K / 16.1 GB | 38 | 78 |
| Llama 3 8B Instruct Coder AWQ | 8K / 5.8 GB | 13 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than Replete-AI/Replete-Coder-Llama3-8B .
Rank the Replete Coder Llama3 8B 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? 40123 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217