Model Type |
| |||
Additional Notes |
| |||
Training Details |
| |||
Input Output |
|
LLM Name | Reflection Llama 3.1 70B Bnb 4bit |
Repository ๐ค | https://huggingface.co/unsloth/Reflection-Llama-3.1-70B-bnb-4bit |
Base Model(s) | |
Model Size | 70b |
Required VRAM | 39.7 GB |
Updated | 2024-12-22 |
Maintainer | unsloth |
Model Type | llama |
Model Files | |
Quantization Type | 4bit |
Model Architecture | LlamaForCausalLM |
License | llama3.1 |
Context Length | 131072 |
Model Max Length | 131072 |
Transformers Version | 4.44.2 |
Tokenizer Class | PreTrainedTokenizerFast |
Padding Token | <|finetune_right_pad_id|> |
Vocabulary Size | 128262 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...B Instruct Gradient 1048K 8bit | 1024K / 75 GB | 15 | 5 |
...B Instruct Gradient 1048K 4bit | 1024K / 39.7 GB | 19 | 3 |
...B Instruct Gradient 1048K 2bit | 1024K / 21.9 GB | 12 | 2 |
...0B Instruct Gradient 262K 4bit | 256K / 39.7 GB | 16 | 3 |
...0B Instruct Gradient 262K 8bit | 256K / 75 GB | 8 | 2 |
...0B Instruct Gradient 262K 2bit | 256K / 21.9 GB | 16 | 1 |
...t Gradient 262K 4.0bpw H6 EXL2 | 256K / 37.2 GB | 15 | 1 |
... Gradient 262K 2.25bpw H6 EXL2 | 256K / 22.2 GB | 8 | 0 |
...t Gradient 262K 2.4bpw H6 EXL2 | 256K / 23.5 GB | 12 | 0 |
...t Gradient 262K 3.5bpw H6 EXL2 | 256K / 32.9 GB | 6 | 0 |
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