| { | |
| "_name_or_path": "philschmid/llama-2-7b-instruction-generator", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 32, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": "model.layers", | |
| "damp_percent": 0.1, | |
| "dataset": "wikitext2", | |
| "desc_act": false, | |
| "disable_exllama": false, | |
| "group_size": 128, | |
| "model_seqlen": 4096, | |
| "module_name_preceding_first_block": [ | |
| "model.embed_tokens" | |
| ], | |
| "pad_token_id": null, | |
| "quant_method": "gptq", | |
| "sym": true, | |
| "true_sequential": true, | |
| "use_cuda_fp16": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.32.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } |