LLM Name | Epinnock Wizardcoder 1B Merged GPTQ |
Repository ๐ค | https://huggingface.co/s3nh/epinnock-wizardcoder-1b-merged-GPTQ |
Merged Model | Yes |
Model Size | 1b |
Required VRAM | 1 GB |
Updated | 2025-02-05 |
Maintainer | s3nh |
Model Type | gpt_bigcode |
Model Files | |
GPTQ Quantization | Yes |
Quantization Type | gptq|4bit |
Generates Code | Yes |
Model Architecture | GPTBigCodeForCausalLM |
Transformers Version | 4.31.0 |
Vocabulary Size | 49152 |
Torch Data Type | float16 |
Activation Function | gelu_pytorch_tanh |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Starcoderbase 1B GPTQ | 0K / 1 GB | 56 | 0 |
Starcoder 1B | 8K / GB | 8 | 1 |
Starcoder 1B Python | 0K / 2.3 GB | 7 | 0 |
CodeBarcenas 1B | 0K / 2.3 GB | 1330 | 0 |
...Personal Copilot T4 40GB Colab | 0K / 2.3 GB | 60 | 1 |
...nal Copilot A100 40GB Colab 1B | 0K / 2.3 GB | 10 | 1 |
Starcoderbase 1B Hf Python | 0K / 2.3 GB | 6 | 1 |
Codes 1B Spider | 0K / 4.5 GB | 63 | 0 |
Starcoderbase 1B | 0K / 4.5 GB | 102 | 0 |
Starcoderbase 1B Sft | 0K / 2.3 GB | 130 | 53 |
๐ 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! ๐