LLM Name | Batch1 Epochs4 Lr1e 05 Paged Adamw 32bit Cosine Length2048 Warmup 0.05 Max Grad1.0 Grad Accu32 |
Repository ๐ค | https://huggingface.co/caisarl76/batch1_epochs4_lr1e-05_paged_adamw_32bit_cosine_length2048_warmup_0.05_max_grad1.0_grad_accu32 |
Base Model(s) | |
Merged Model | Yes |
Model Size | 7b |
Required VRAM | 14.4 GB |
Updated | 2024-09-07 |
Maintainer | caisarl76 |
Model Type | llama |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 32bit |
Model Architecture | LlamaForCausalLM |
Context Length | 32768 |
Model Max Length | 32768 |
Transformers Version | 4.36.2 |
Tokenizer Class | LlamaTokenizer |
Padding Token | [PAD] |
Vocabulary Size | 32000 |
Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...p 0.05 Max Grad1.0 Grad Accu32 | 32K / 14.4 GB | 6 | 0 |
...ruct Solidity Bnb 4bit Smashed | 16K / 4.2 GB | 5 | 0 |
...B Instruct Hf Bnb 4bit Smashed | 16K / 4.2 GB | 16 | 0 |
CodelLama7B Inst DPO 7K Mlx | 16K / 4.2 GB | 8 | 2 |
...eLlama 7B Instruct Hf 4bit MLX | 16K / 4.2 GB | 3 | 1 |
...6.7B Instruct 3.0bpw H6 EXL2 2 | 16K / 2.8 GB | 14 | 1 |
...6.7B Instruct 8.0bpw H8 EXL2 2 | 16K / 6.8 GB | 11 | 2 |
...coder S CL 7B 3.0bpw H6 EXL2 2 | 16K / 2.8 GB | 14 | 1 |
...coder S CL 7B 4.0bpw H6 EXL2 2 | 16K / 3.6 GB | 14 | 1 |
...coder S CL 7B 5.0bpw H6 EXL2 2 | 16K / 4.4 GB | 14 | 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