| { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "NousResearch/Yarn-Llama-2-13b-64k", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "NousResearch/Yarn-Llama-2-13b-64k--configuration_llama.LlamaConfig", |
| "AutoModelForCausalLM": "NousResearch/Yarn-Llama-2-13b-64k--modeling_llama_together_yarn.LlamaForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 13824, |
| "max_position_embeddings": 65536, |
| "model_type": "llama", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 40, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "_load_in_4bit": true, |
| "_load_in_8bit": false, |
| "bnb_4bit_compute_dtype": "bfloat16", |
| "bnb_4bit_quant_storage": "bfloat16", |
| "bnb_4bit_quant_type": "nf4", |
| "bnb_4bit_use_double_quant": true, |
| "llm_int8_enable_fp32_cpu_offload": false, |
| "llm_int8_has_fp16_weight": false, |
| "llm_int8_skip_modules": null, |
| "llm_int8_threshold": 6.0, |
| "load_in_4bit": true, |
| "load_in_8bit": false, |
| "quant_method": "bitsandbytes" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 16.0, |
| "finetuned": true, |
| "original_max_position_embeddings": 4096, |
| "type": "yarn" |
| }, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.46.0", |
| "use_cache": false, |
| "use_flash_attention": false, |
| "vocab_size": 32000 |
| } |
|
|
