4-bit Autotrain compatible Conversational Endpoints compatible Gptq Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
VinaLlama2 14B GPTQ Int4 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)
VinaLlama2 14B GPTQ Int4 Parameters and Internals
| LLM Name | VinaLlama2 14B GPTQ Int4 |
| Repository 🤗 | https://huggingface.co/vilm/VinaLlama2-14B-GPTQ-Int4 |
| Model Size | 14b |
| Required VRAM | 9.7 GB |
| Updated | 2024-09-07 |
| Maintainer | vilm |
| Model Type | qwen2 |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 32768 |
| Model Max Length | 32768 |
| Transformers Version | 4.40.2 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | float16 |
| Errors | replace |
Best Alternatives to VinaLlama2 14B GPTQ Int4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Liberated Qwen1.5 14B 4bit | 32K / 9.7 GB | 9 | 1 |
| Qwen1.5 14B Chat GPTQ Int4 | 32K / 9.9 GB | 484 | 19 |
| Qwen1.5 14B Chat GPTQ Int8 | 32K / 16.5 GB | 71 | 11 |
| Qwen1.5 14B Chat 4bit | 32K / 9.1 GB | 11 | 1 |
| Qwen1.5 14B Chat 8bpw H8 EXL2 | 32K / 15 GB | 12 | 1 |
| Qwen1.5 14B Chat 5bpw EXL2 | 32K / 10.1 GB | 11 | 1 |
| Qwen1.5 14B Chat | 32K / 28.3 GB | 24090 | 108 |
| Qwen1.5 14B | 32K / 28.3 GB | 17488 | 36 |
| Qwen1.5 14B Chat AWQ | 32K / 9.7 GB | 18470 | 20 |
| Liberated Qwen1.5 14B | 32K / 28.4 GB | 7083 | 18 |
Note: green Score (e.g. "73.2") means that the model is better than vilm/VinaLlama2-14B-GPTQ-Int4 .
Rank the VinaLlama2 14B GPTQ Int4 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803