commit bdc5f6767b609f5e455bb5df08fd951cbb4b0eba Author: ModelHub XC Date: Thu May 28 09:44:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: adept/persimmon-8b-chat Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4824359 --- /dev/null +++ b/README.md @@ -0,0 +1,17 @@ +--- +license: apache-2.0 +--- + +At Adept, we’re working towards an AI agent that can help people do anything they need to do on a computer. We’re not in the business of shipping isolated language models (LMs)—this was an early output of the model scaling program that will support our products. + +We trained it from scratch using a context size of 16K. Many LM use cases are context-bound; our model has 4 times the context size of LLaMA2 and 8 times that of GPT-3, MPT, etc. + +This is a chat finetuned version of the base model. The best prompt to use is: + +human: [some query] + +adept: + + + +See https://www.adept.ai/blog/persimmon-8b for more info \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a8bd615 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "architectures": [ + "PersimmonForCausalLM" + ], + "bos_token_id": 71013, + "eos_token_id": 71013, + "hidden_act": "relu2", + "hidden_dropout": 0.6, + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 16384, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 16384, + "model_type": "persimmon", + "num_attention_heads": 64, + "num_hidden_layers": 36, + "num_key_value_heads": 64, + "qk_layernorm": true, + "rope_scaling": null, + "rope_theta": 25000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.0.dev0", + "use_cache": true, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..9be2582 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 71013, + "eos_token_id": 71013, + "transformers_version": "4.34.0.dev0" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..19639c4 --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:195989b990d42fbf7843399f65ee3ce95ca7c3308cd7c5474b750bb7f48fb63f +size 9934290702 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..8e1c3dc --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f9ed5db4463a5c9c66c4ea01c21cc530b5478428f4cbb1fc07d07db58472e1 +size 8860267144 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..5a90551 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,587 @@ +{ + "metadata": { + "total_size": 18794350592 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00002-of-00002.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin", + "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.0.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.1.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.10.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.11.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.12.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.13.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.14.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.15.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.16.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.17.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.18.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.19.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.19.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.2.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.20.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.21.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.22.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.23.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.24.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.25.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.26.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.27.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.28.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.29.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.3.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.30.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.31.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.32.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.33.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.34.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.input_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.dense.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.dense.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.k_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.k_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.q_layernorm.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.q_layernorm.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.query_key_value.bias": "pytorch_model-00002-of-00002.bin", + "model.layers.35.self_attn.query_key_value.weight": "pytorch_model-00002-of-00002.bin", + "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.4.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.5.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.6.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.7.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.8.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.dense.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.dense.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.k_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_layernorm.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.q_layernorm.weight": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.query_key_value.bias": "pytorch_model-00001-of-00002.bin", + "model.layers.9.self_attn.query_key_value.weight": "pytorch_model-00001-of-00002.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ece7f95 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,16 @@ +{ + "bos_token": { + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..1f9e5bf --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407d001d18582959881b30ff39b660d4bd5ee50957d03f57daeeb3059e9db54c +size 6128796 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..584c380 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "|ENDOFTEXT|", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": null, + "legacy": null, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true +}