From 173cc80103b3e618a694ffbe4b7678799d2bc5bd Mon Sep 17 00:00:00 2001 From: Jeff Green Date: Fri, 26 Dec 2025 06:06:55 +0000 Subject: [PATCH] Move eve-qwen3-8b-merged/config.json to root --- eve-qwen3-8b-merged/config.json | 58 --------------------------------- 1 file changed, 58 deletions(-) delete mode 100644 eve-qwen3-8b-merged/config.json diff --git a/eve-qwen3-8b-merged/config.json b/eve-qwen3-8b-merged/config.json deleted file mode 100644 index a6bb205..0000000 --- a/eve-qwen3-8b-merged/config.json +++ /dev/null @@ -1,58 +0,0 @@ -{ - "architectures": [ - "Qwen2ForCausalLM" - ], - "attention_dropout": 0.0, - "bos_token_id": 151643, - "dtype": "bfloat16", - "eos_token_id": 151645, - "hidden_act": "silu", - "hidden_size": 3584, - "initializer_range": 0.02, - "intermediate_size": 18944, - "layer_types": [ - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention", - "full_attention" - ], - "max_position_embeddings": 32768, - "max_window_layers": 28, - "model_type": "qwen2", - "num_attention_heads": 28, - "num_hidden_layers": 28, - "num_key_value_heads": 4, - "rms_norm_eps": 1e-06, - "rope_scaling": null, - "rope_theta": 1000000.0, - "sliding_window": null, - "tie_word_embeddings": false, - "transformers_version": "4.57.3", - "use_cache": true, - "use_sliding_window": false, - "vocab_size": 152064 -}