| { | |
| "_name_or_path": "fxmarty/small-llama-testing", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 256, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 128, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 4, | |
| "pad_token_id": -1, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "activation_scheme": "static", | |
| "export": { | |
| "kv_cache_group": [], | |
| "min_kv_scale": 1.0, | |
| "pack_method": "reorder", | |
| "weight_format": "real_quantized", | |
| "weight_merge_groups": null | |
| }, | |
| "ignored_layers": [ | |
| "lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "fp8" | |
| }, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.1", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |