Model Type |
| ||
Use Cases |
| ||
Additional Notes | Some issues with model weights in terms of precision, to be fixed in the next version update. Repetition penalty should not be used. Re-alignment on synthetic datasets has changed distribution significantly from original datasets. |
LLM Name | 34B Beta 4.0bpw H6 EXL2 |
Repository ๐ค | https://huggingface.co/LoneStriker/34b-beta-4.0bpw-h6-exl2 |
Model Size | 34b |
Required VRAM | 18.1 GB |
Updated | 2024-11-13 |
Maintainer | LoneStriker |
Model Type | llama |
Model Files | |
Quantization Type | exl2 |
Model Architecture | LlamaForCausalLM |
License | gpl-3.0 |
Context Length | 200000 |
Model Max Length | 200000 |
Transformers Version | 4.37.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | <unk> |
Vocabulary Size | 64000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
Yi 34B 200K RPMerge | 195K / 68.9 GB | 409 | 60 |
...34B 200K Aezakmi Raw 1902 EXL2 | 195K / 20.7 GB | 15 | 1 |
Yi 34B 200K MAR2024 EXL2 4bpw | 195K / 18 GB | 7 | 1 |
...mi Raw Toxic 2702 4.65bpw EXL2 | 195K / 20.8 GB | 14 | 2 |
...B 200K RPMerge 4.65bpw H6 EXL2 | 195K / 10.5 GB | 8 | 1 |
Yi 34B 200K RPMerge EXL2 40bpw | 195K / 18.1 GB | 25 | 20 |
Opus V1 34B 5.0bpw H6 EXL2 | 195K / 22.3 GB | 3 | 2 |
Opus V1 34B 8.0bpw H8 EXL2 | 195K / 34.8 GB | 7 | 1 |
Opus V1 34B 4.0bpw H6 EXL2 | 195K / 18 GB | 3 | 1 |
34B Beta 5.0bpw H6 EXL2 | 195K / 22.3 GB | 5 | 1 |
๐ 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! ๐