Arxiv:1911.02150 Arxiv:2205.14135 Arxiv:2207.14255 Arxiv:2305.06161 4-bit Autotrain compatible Code Codegen Dataset:bigcode/the-stack-dedu... Gpt bigcode Gptq Model-index Quantized Region:us Safetensors
Starcoder GPTQ Parameters and Internals
| LLM Name | Starcoder GPTQ |
| Repository | Open on 🤗 |
| Model Size | 2.6b |
| Required VRAM | 8.9 GB |
| Updated | 2024-07-26 |
| Maintainer | TheBloke |
| Model Type | gpt_bigcode |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Generates Code | Yes |
| Model Architecture | GPTBigCodeForCausalLM |
| License | bigcode-openrail-m |
| Transformers Version | 4.28.1 |
| Tokenizer Class | GPT2Tokenizer |
| Vocabulary Size | 49152 |
| Torch Data Type | float32 |
| Activation Function | gelu |
Best Alternatives to Starcoder GPTQ
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Starchat Beta GPTQ | 0.1 | 0K / 8.9 GB | 44 | 27 |
| Starcoderplus GPTQ | 0.1 | 0K / 8.9 GB | 27 | 25 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/starcoder-GPTQ .
Rank the Starcoder GPTQ 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501