| { |
| "architectures": [ |
| "Lfm2MoeForCausalLM" |
| ], |
| "bos_token_id": 1, |
| "conv_L_cache": 3, |
| "conv_bias": false, |
| "dtype": "bfloat16", |
| "eos_token_id": 7, |
| "hidden_size": 2048, |
| "intermediate_size": 7168, |
| "layer_types": [ |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv", |
| "full_attention", |
| "conv", |
| "conv" |
| ], |
| "max_position_embeddings": 128000, |
| "model_type": "lfm2_moe", |
| "moe_intermediate_size": 1792, |
| "norm_eps": 1e-05, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_dense_layers": 2, |
| "num_experts": 32, |
| "num_experts_per_tok": 4, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 8, |
| "pad_token_id": 0, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 8, |
| "observer": "mse", |
| "observer_kwargs": {}, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int" |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.layers.0.conv.in_proj", |
| "model.layers.0.conv.out_proj", |
| "model.layers.0.feed_forward.w1", |
| "model.layers.0.feed_forward.w3", |
| "model.layers.0.feed_forward.w2", |
| "model.layers.1.conv.in_proj", |
| "model.layers.1.conv.out_proj", |
| "model.layers.1.feed_forward.w1", |
| "model.layers.1.feed_forward.w3", |
| "model.layers.1.feed_forward.w2", |
| "model.layers.2.self_attn.q_proj", |
| "model.layers.2.self_attn.k_proj", |
| "model.layers.2.self_attn.v_proj", |
| "model.layers.2.self_attn.out_proj", |
| "model.layers.2.feed_forward.gate", |
| "model.layers.3.conv.in_proj", |
| "model.layers.3.conv.out_proj", |
| "model.layers.3.feed_forward.gate", |
| "model.layers.4.conv.in_proj", |
| "model.layers.4.conv.out_proj", |
| "model.layers.4.feed_forward.gate", |
| "model.layers.5.conv.in_proj", |
| "model.layers.5.conv.out_proj", |
| "model.layers.5.feed_forward.gate", |
| "model.layers.6.self_attn.q_proj", |
| "model.layers.6.self_attn.k_proj", |
| "model.layers.6.self_attn.v_proj", |
| "model.layers.6.self_attn.out_proj", |
| "model.layers.6.feed_forward.gate", |
| "model.layers.7.conv.in_proj", |
| "model.layers.7.conv.out_proj", |
| "model.layers.7.feed_forward.gate", |
| "model.layers.8.conv.in_proj", |
| "model.layers.8.conv.out_proj", |
| "model.layers.8.feed_forward.gate", |
| "model.layers.9.conv.in_proj", |
| "model.layers.9.conv.out_proj", |
| "model.layers.9.feed_forward.gate", |
| "model.layers.10.self_attn.q_proj", |
| "model.layers.10.self_attn.k_proj", |
| "model.layers.10.self_attn.v_proj", |
| "model.layers.10.self_attn.out_proj", |
| "model.layers.10.feed_forward.gate", |
| "model.layers.11.conv.in_proj", |
| "model.layers.11.conv.out_proj", |
| "model.layers.11.feed_forward.gate", |
| "model.layers.12.conv.in_proj", |
| "model.layers.12.conv.out_proj", |
| "model.layers.12.feed_forward.gate", |
| "model.layers.13.conv.in_proj", |
| "model.layers.13.conv.out_proj", |
| "model.layers.13.feed_forward.gate", |
| "model.layers.14.self_attn.q_proj", |
| "model.layers.14.self_attn.k_proj", |
| "model.layers.14.self_attn.v_proj", |
| "model.layers.14.self_attn.out_proj", |
| "model.layers.14.feed_forward.gate", |
| "model.layers.15.conv.in_proj", |
| "model.layers.15.conv.out_proj", |
| "model.layers.15.feed_forward.gate", |
| "model.layers.16.conv.in_proj", |
| "model.layers.16.conv.out_proj", |
| "model.layers.16.feed_forward.gate", |
| "model.layers.17.conv.in_proj", |
| "model.layers.17.conv.out_proj", |
| "model.layers.17.feed_forward.gate", |
| "model.layers.18.self_attn.q_proj", |
| "model.layers.18.self_attn.k_proj", |
| "model.layers.18.self_attn.v_proj", |
| "model.layers.18.self_attn.out_proj", |
| "model.layers.18.feed_forward.gate", |
| "model.layers.19.conv.in_proj", |
| "model.layers.19.conv.out_proj", |
| "model.layers.19.feed_forward.gate", |
| "model.layers.20.conv.in_proj", |
| "model.layers.20.conv.out_proj", |
| "model.layers.20.feed_forward.gate", |
| "model.layers.21.self_attn.q_proj", |
| "model.layers.21.self_attn.k_proj", |
| "model.layers.21.self_attn.v_proj", |
| "model.layers.21.self_attn.out_proj", |
| "model.layers.21.feed_forward.gate", |
| "model.layers.22.conv.in_proj", |
| "model.layers.22.conv.out_proj", |
| "model.layers.22.feed_forward.gate", |
| "model.layers.23.conv.in_proj", |
| "model.layers.23.conv.out_proj", |
| "model.layers.23.feed_forward.gate", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.12.1.dev0" |
| }, |
| "rope_theta": 1000000.0, |
| "routed_scaling_factor": 1.0, |
| "tie_word_embeddings": false, |
| "transformers_version": "5.0.0.dev0", |
| "use_cache": true, |
| "use_expert_bias": true, |
| "vocab_size": 65536 |
| } |
