Model Card on HF 🤗: https://huggingface.co/Narsil/starcoder-gptq-testing
Starcoder Gptq Testing 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)
Starcoder Gptq Testing Parameters and Internals
| LLM Name | Starcoder Gptq Testing |
| Repository 🤗 | https://huggingface.co/Narsil/starcoder-gptq-testing |
| Model Size | 2.7b |
| Required VRAM | 9.2 GB |
| Updated | 2025-05-21 |
| Maintainer | Narsil |
| Model Type | gpt_bigcode |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Generates Code | Yes |
| Model Architecture | GPTBigCodeForCausalLM |
| Transformers Version | 4.29.2 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
| Activation Function | gelu |
Best Alternatives to Starcoder Gptq Testing
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Sqlcoder2 GPTQ | 0K / 9.2 GB | 13 | 11 |
| Sqlcoder GPTQ | 0K / 9.2 GB | 26 | 9 |
| Octocoder GPTQ | 0K / 9.2 GB | 13 | 7 |
| Starcoder Gptq | 0K / 9.2 GB | 547 | 0 |
| Redmond Hermes Coder GPTQ | 0K / 9.2 GB | 8 | 10 |
Note: green Score (e.g. "73.2") means that the model is better than Narsil/starcoder-gptq-testing .
Rank the Starcoder Gptq Testing 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? 47499 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227