Arxiv:2401.06118 Aqlm Autotrain compatible Code Conversational Custom code En Endpoints compatible Instruct Microsoft Phi3 Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Phi-3-mini-128k-instruct-AQLM-1x16
Phi 3 Mini 128K Instruct AQLM 1x16 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)
Phi 3 Mini 128K Instruct AQLM 1x16 Parameters and Internals
| Model Type |
| |
| Additional Notes |
| |
| Supported Languages |
|
| LLM Name | Phi 3 Mini 128K Instruct AQLM 1x16 |
| Repository 🤗 | https://huggingface.co/ISTA-DASLab/Phi-3-mini-128k-instruct-AQLM-1x16 |
| Model Size | 718.3m |
| Required VRAM | 1.4 GB |
| Updated | 2025-09-23 |
| Maintainer | ISTA-DASLab |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Phi3ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.40.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 32064 |
| Torch Data Type | float16 |
Best Alternatives to Phi 3 Mini 128K Instruct AQLM 1x16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... Instruct AQLM PV 2Bit 1x16 Hf | 4K / 1.4 GB | 656 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/Phi-3-mini-128k-instruct-AQLM-1x16 .
Rank the Phi 3 Mini 128K Instruct AQLM 1x16 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124