Arxiv:2104.09864 4-bit Autotrain compatible Base model:quantized:stability... Base model:stabilityai/stablec... Codegen Gpt neox Gptq Instruct Quantized Region:us Safetensors
Stablecode Instruct Alpha 3B GPTQ 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)
Stablecode Instruct Alpha 3B GPTQ Parameters and Internals
| LLM Name | Stablecode Instruct Alpha 3B GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/stablecode-instruct-alpha-3b-GPTQ |
| Model Name | Stablecode Instruct Alpha 3B |
| Model Creator | StabilityAI |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 1.8 GB |
| Updated | 2024-09-19 |
| Maintainer | TheBloke |
| Model Type | gpt_neox |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Generates Code | Yes |
| Model Architecture | GPTNeoXForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.30.2 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to Stablecode Instruct Alpha 3B GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...blecode Instruct Alpha 3B GPTQ | 4K / 1.8 GB | 8 | 1 |
| Stablecode Instruct Alpha 3B | 4K / 6.1 GB | 21 | 304 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/stablecode-instruct-alpha-3b-GPTQ .
Rank the Stablecode Instruct Alpha 3B 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? 36073 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803