Autotrain compatible Base model:bigcode/starcoder2-... Base model:quantized:bigcode/s... Code Conversational Gguf Instruct Q2 Quantized Region:us Starcoder2
StarCoder2 15B Instruct V0.1 GGUF 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)
StarCoder2 15B Instruct V0.1 GGUF Parameters and Internals
| LLM Name | StarCoder2 15B Instruct V0.1 GGUF |
| Repository 🤗 | https://huggingface.co/second-state/StarCoder2-15B-Instruct-v0.1-GGUF |
| Model Name | StarCoder2-15B-Instruct-v0.1 |
| Model Creator | bigcode |
| Base Model(s) | |
| Model Size | 15b |
| Required VRAM | 6.2 GB |
| Updated | 2024-11-05 |
| Maintainer | second-state |
| Model Type | starcoder2 |
| Instruction-Based | Yes |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf|q2|q4_k|q5_k |
| Model Architecture | Starcoder2ForCausalLM |
| License | bigcode-openrail-m |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.39.0.dev0 |
| Vocabulary Size | 49152 |
| Torch Data Type | bfloat16 |
Best Alternatives to StarCoder2 15B Instruct V0.1 GGUF
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...rCoder2 15B Instruct V0.1 GGUF | 16K / 6.2 GB | 356 | 0 |
| Starcoder2 15B Instruct GPTQ | 16K / 9.2 GB | 259949 | 2 |
| Starcoder2 15B Instruct V0.1 | 16K / 31.9 GB | 3102 | 94 |
| Dolphincoder Starcoder2 15B | 16K / 31.9 GB | 234 | 69 |
| Starcoder2 15B Instruct V0.1 | 16K / 53.4 GB | 9 | 0 |
| Starcoder2 15B Instruct | 16K / 31.9 GB | 23 | 6 |
Note: green Score (e.g. "73.2") means that the model is better than second-state/StarCoder2-15B-Instruct-v0.1-GGUF .
Rank the StarCoder2 15B Instruct V0.1 GGUF 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? 37547 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803