4-bit Autotrain compatible Base model:01-ai/yi-34b-200k Base model:quantized:01-ai/yi-... Custom code Gptq Quantized Region:us Safetensors Yi
Yi 34B 200K 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)
Yi 34B 200K GPTQ Parameters and Internals
| LLM Name | Yi 34B 200K GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Yi-34B-200K-GPTQ |
| Model Name | Yi 34B 200K |
| Model Creator | 01-ai |
| Base Model(s) | |
| Model Size | 34b |
| Required VRAM | 18.6 GB |
| Updated | 2024-10-18 |
| Maintainer | TheBloke |
| Model Type | yi |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Model Architecture | YiForCausalLM |
| License | other |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | YiTokenizer |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Yi 34B 200K GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Yi 34B GPTQ | 4K / 18.7 GB | 25 | 33 |
| ...lpaca Rpv3 Scipy 4bpw Hb6 EXL2 | 195K / 18.7 GB | 18 | 2 |
| ...200K Alpaca Rpv3 4bpw Hb6 EXL2 | 195K / 18.7 GB | 14 | 2 |
| Yi 34B 200K 4.65bpw H6 EXL2 | 195K / 20.8 GB | 3 | 6 |
| Yi 34B 200K 4.0bpw H6 EXL2 | 195K / 18.1 GB | 2 | 4 |
| Yi 34B 200K 8.0bpw H8 EXL2 | 195K / 34.8 GB | 6 | 3 |
| Yi 34B 200K 5.0bpw H6 EXL2 | 195K / 22.3 GB | 1 | 1 |
| Deepsex 34B 4bpw H8 EXL2 | 4K / 18.1 GB | 42 | 4 |
| Deepsex 34B 4bpw H6 EXL2 | 4K / 18.1 GB | 2 | 3 |
| Yi 34B 5.0bpw H6 EXL2 | 4K / 22.2 GB | 8 | 3 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yi-34B-200K-GPTQ .
Rank the Yi 34B 200K 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803