| { |
| "_name_or_path": "/slot/sandbox/j/_tmp/datam7lqkvi_", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "eos_token_id": 128001, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 16, |
| "num_key_value_heads": 8, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "in_group_size": 8, |
| "linear_weights_not_to_quantize": [ |
| "model.layers.0.input_layernorm.weight", |
| "model.layers.0.post_attention_layernorm.weight", |
| "model.layers.1.input_layernorm.weight", |
| "model.layers.1.post_attention_layernorm.weight", |
| "model.layers.2.input_layernorm.weight", |
| "model.layers.2.post_attention_layernorm.weight", |
| "model.layers.3.input_layernorm.weight", |
| "model.layers.3.post_attention_layernorm.weight", |
| "model.layers.4.input_layernorm.weight", |
| "model.layers.4.post_attention_layernorm.weight", |
| "model.layers.5.input_layernorm.weight", |
| "model.layers.5.post_attention_layernorm.weight", |
| "model.layers.6.input_layernorm.weight", |
| "model.layers.6.post_attention_layernorm.weight", |
| "model.layers.7.input_layernorm.weight", |
| "model.layers.7.post_attention_layernorm.weight", |
| "model.layers.8.input_layernorm.weight", |
| "model.layers.8.post_attention_layernorm.weight", |
| "model.layers.9.input_layernorm.weight", |
| "model.layers.9.post_attention_layernorm.weight", |
| "model.layers.10.input_layernorm.weight", |
| "model.layers.10.post_attention_layernorm.weight", |
| "model.layers.11.input_layernorm.weight", |
| "model.layers.11.post_attention_layernorm.weight", |
| "model.layers.12.input_layernorm.weight", |
| "model.layers.12.post_attention_layernorm.weight", |
| "model.layers.13.input_layernorm.weight", |
| "model.layers.13.post_attention_layernorm.weight", |
| "model.layers.14.input_layernorm.weight", |
| "model.layers.14.post_attention_layernorm.weight", |
| "model.layers.15.input_layernorm.weight", |
| "model.layers.15.post_attention_layernorm.weight", |
| "model.embed_tokens.weight", |
| "model.norm.weight", |
| "lm_head.weight" |
| ], |
| "nbits_per_codebook": 8, |
| "num_codebooks": 2, |
| "out_group_size": 1, |
| "quant_method": "aqlm" |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 32.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "llama3" |
| }, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": true, |
| "torch_dtype": "float16", |
| "transformers_version": "4.44.0.dev0", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
