4-bit 4bit Autotrain compatible Bitsandbytes Bnb En Endpoints compatible Llama Quantized Region:us Safetensors Sharded Tensorflow Unsloth Yi
Yi 34B Bnb 4bit Parameters and Internals
| LLM Name | Yi 34B Bnb 4bit |
| Repository | Open on 🤗 |
| Model Size | 34b |
| Required VRAM | 19.1 GB |
| Updated | 2024-07-27 |
| Maintainer | unsloth |
| Model Type | llama |
| Model Files | |
| Supported Languages | en |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Torch Data Type | bfloat16 |
Best Alternatives to Yi 34B Bnb 4bit
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Yi 34B 200K RPMerge | 0.2 | 195K / 68.9 GB | 335 | 54 |
| ...34B 200K Aezakmi Raw 1902 EXL2 | 0.2 | 195K / 20.7 GB | 7 | 1 |
| Yi 34B 200K MAR2024 EXL2 4bpw | 0.2 | 195K / 18 GB | 8 | 1 |
| Yi 34B 200K RPMerge EXL2 40bpw | 0.2 | 195K / 18.1 GB | 45 | 20 |
| ...mi Raw Toxic 2702 4.65bpw EXL2 | 0.2 | 195K / 20.8 GB | 8 | 2 |
| ...B 200K RPMerge 4.65bpw H6 EXL2 | 0.2 | 195K / 10.5 GB | 9 | 1 |
| Opus V1 34B 5.0bpw H6 EXL2 | 0.2 | 195K / 22.3 GB | 7 | 2 |
| Opus V1 34B 4.0bpw H6 EXL2 | 0.2 | 195K / 18 GB | 10 | 1 |
| Opus V1 34B 8.0bpw H8 EXL2 | 0.2 | 195K / 34.8 GB | 5 | 1 |
| 34B Beta 5.0bpw H6 EXL2 | 0.2 | 195K / 22.3 GB | 7 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/yi-34b-bnb-4bit .
Rank the Yi 34B Bnb 4bit 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? 34447 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501