Model Card on HF 🤗: https://huggingface.co/agi-designer/Aspera-SWE-Llama-7b-updated-4bit-awq
Aspera SWE Llama 7B Updated 4bit AWQ 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)
Aspera SWE Llama 7B Updated 4bit AWQ Parameters and Internals
| LLM Name | Aspera SWE Llama 7B Updated 4bit AWQ |
| Repository 🤗 | https://huggingface.co/agi-designer/Aspera-SWE-Llama-7b-updated-4bit-awq |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 3.9 GB |
| Updated | 2024-12-22 |
| Maintainer | agi-designer |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq|4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | </s> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Aspera SWE Llama 7B Updated 4bit AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Smaugv0.1 AWQ | 195K / 19.3 GB | 10 | 1 |
| Yarn Llama 2 7B 64K AWQ | 64K / 3.9 GB | 18 | 0 |
| Calm2 7B Chat AWQ | 32K / 4.4 GB | 61 | 2 |
| Llama 2 7B 32K Instruct AWQ | 32K / 3.9 GB | 22 | 2 |
| ...Llama 7B Python Hf W4 G128 AWQ | 16K / 3.9 GB | 2359 | 0 |
| Pandalyst 7B V1.2 AWQ | 16K / 3.9 GB | 23 | 1 |
| Tora Code 7B V1.0 AWQ | 16K / 3.9 GB | 20 | 0 |
| ...eechless Tora Code 7B V1.0 AWQ | 16K / 3.9 GB | 22 | 1 |
| CodeLlama 7B Instruct AWQ | 16K / 3.9 GB | 176 | 4 |
| Pandalyst 7B V1.1 AWQ | 16K / 3.9 GB | 32 | 1 |
Rank the Aspera SWE Llama 7B Updated 4bit AWQ 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217