Alignment-handbook Autotrain compatible Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a... Codegen Conversational Dataset:self-generate/ds coder... Dpo Endpoints compatible Generated from trainer Instruct Llama Region:us Safetensors Sharded Tensorflow Trl
Model Card on HF 🤗: https://huggingface.co/yiran-wang3/ds_coder_adamw_iter1
Ds Coder Adamw Iter1 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)
Ds Coder Adamw Iter1 Parameters and Internals
| LLM Name | Ds Coder Adamw Iter1 |
| Repository 🤗 | https://huggingface.co/yiran-wang3/ds_coder_adamw_iter1 |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 13.9 GB |
| Updated | 2024-12-05 |
| Maintainer | yiran-wang3 |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.45.0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 102400 |
| Torch Data Type | bfloat16 |
Best Alternatives to Ds Coder Adamw Iter1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Deepseek Coder 6.7B Instruct | 16K / 13.5 GB | 16087 | 356 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 29685 | 219 |
| CodeLlama 7B Instruct Hf | 16K / 13.5 GB | 22219 | 29 |
| GetCode Slerp | 16K / 13.6 GB | 1049 | 1 |
| CodeV CL 7B | 16K / 13.5 GB | 571 | 1 |
| Cdlm 7 Ko Nl2sql V1.0 | 16K / 13.5 GB | 4800 | 4 |
| Stack Codellama 7B Inst | 16K / 13.5 GB | 75 | 0 |
| ...ama 7B Instruct Hf Dequantized | 16K / 13.5 GB | 197 | 0 |
| ...deLlama 7B Instruct Hf 8bits Q | 16K / 4.2 GB | 7 | 1 |
| Llama 2 7B Chat Finetune5 | 16K / 13.8 GB | 3 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than yiran-wang3/ds_coder_adamw_iter1 .
Rank the Ds Coder Adamw Iter1 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? 40303 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227