| { |
| "_name_or_path": "meta-llama/Llama-3.2-1B", |
| "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": { |
| "config_groups": { |
| "group_0": { |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 128, |
| "num_bits": 4, |
| "observer": "minmax", |
| "observer_kwargs": {}, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int" |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": 2.049489732929017, |
| "ignore": [ |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "transforms_config": { |
| "transform_groups": { |
| "u_transform_gate_up_proj": { |
| "global_transform": false, |
| "groups": [ |
| { |
| "call_args": {}, |
| "ignore": [], |
| "module_targets": [ |
| "weight" |
| ], |
| "targets": [ |
| "re:.*.mlp.gate_proj$", |
| "re:.*.mlp.up_proj$" |
| ] |
| } |
| ], |
| "transform_creation_args": { |
| "size": 8192 |
| }, |
| "transform_type": "random-hadamard" |
| }, |
| "u_transform_k_v_proj": { |
| "global_transform": false, |
| "groups": [ |
| { |
| "call_args": {}, |
| "ignore": [], |
| "module_targets": [ |
| "weight" |
| ], |
| "targets": [ |
| "re:.*.attn.k_proj$", |
| "re:.*.attn.v_proj$" |
| ] |
| } |
| ], |
| "transform_creation_args": { |
| "size": 512 |
| }, |
| "transform_type": "random-hadamard" |
| }, |
| "u_transform_q_o_down_proj": { |
| "global_transform": false, |
| "groups": [ |
| { |
| "call_args": {}, |
| "ignore": [], |
| "module_targets": [ |
| "weight" |
| ], |
| "targets": [ |
| "re:.*.attn.q_proj$", |
| "re:.*.attn.o_proj$", |
| "re:.*.mlp.down_proj$" |
| ] |
| } |
| ], |
| "transform_creation_args": { |
| "size": 2048 |
| }, |
| "transform_type": "random-hadamard" |
| }, |
| "v_transform_down_proj": { |
| "global_transform": false, |
| "groups": [ |
| { |
| "call_args": { |
| "first": false, |
| "transpose": true |
| }, |
| "ignore": [], |
| "module_targets": [ |
| "weight" |
| ], |
| "targets": [ |
| "re:.*.mlp.down_proj$" |
| ] |
| } |
| ], |
| "transform_creation_args": { |
| "size": 8192 |
| }, |
| "transform_type": "random-hadamard" |
| }, |
| "v_transform_linear": { |
| "global_transform": false, |
| "groups": [ |
| { |
| "call_args": { |
| "first": false, |
| "transpose": true |
| }, |
| "ignore": [ |
| "re:.*.mlp.down_proj$", |
| "lm_head" |
| ], |
| "module_targets": [ |
| "weight" |
| ], |
| "targets": [ |
| "Linear" |
| ] |
| } |
| ], |
| "transform_creation_args": { |
| "size": 2048 |
| }, |
| "transform_type": "random-hadamard" |
| } |
| } |
| } |
| }, |
| "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": "bfloat16", |
| "transformers_version": "4.49.0", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
