Arxiv:2311.13534 4-bit Autotrain compatible Base model:quantized:yhyu13/lm... Base model:yhyu13/lmcocktail-p... Custom code Gptq Phi-msft Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/LMCocktail-phi-2-v1-GPTQ
LMCocktail Phi 2 V1 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)
LMCocktail Phi 2 V1 GPTQ Parameters and Internals
| LLM Name | LMCocktail Phi 2 V1 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/LMCocktail-phi-2-v1-GPTQ |
| Model Name | LMCocktail Phi 2 v1 |
| Model Creator | Yu |
| Base Model(s) | |
| Model Size | 600.4m |
| Required VRAM | 1.8 GB |
| Updated | 2025-10-21 |
| Maintainer | TheBloke |
| Model Type | phi-msft |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | PhiForCausalLM |
| Model Max Length | 2048 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | CodeGenTokenizer |
| Vocabulary Size | 51200 |
| Torch Data Type | float16 |
| Activation Function | gelu_new |
Best Alternatives to LMCocktail Phi 2 V1 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi2 OSST GPTQ | 2K / 1.8 GB | 14 | 1 |
| Phi 2 GPTQ | 0K / 1.8 GB | 2441 | 30 |
| Phi 2 Orange GPTQ | 0K / 1.8 GB | 7 | 4 |
| Dolphin 2 6 Phi 2 GPTQ | 0K / 1.8 GB | 18 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/LMCocktail-phi-2-v1-GPTQ .
Rank the LMCocktail Phi 2 V1 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? 51563 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124