| { |
| "_name_or_path": "/run/media/knut/HD/huggingface models/language models/LLMs/fine tuned/70b/orca_mini_v3_70b/", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 8192, |
| "initializer_range": 0.02, |
| "intermediate_size": 28672, |
| "max_position_embeddings": 4096, |
| "model_type": "llama", |
| "num_attention_heads": 64, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "quip_params": { |
| "codebook": "E8P12", |
| "codebook_version": 1, |
| "codesz": 8, |
| "fused": true, |
| "idx_dtype": "torch.int64", |
| "lora_rank": 0, |
| "model_version": 1, |
| "outlier_channel_split": false, |
| "packsz": 4, |
| "rescale_WH": false |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.34.0", |
| "use_cache": false, |
| "vocab_size": 32000 |
| } |
|
|
