diff --git a/config.json b/config.json new file mode 100644 index 0000000..797231a --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 100000, + "eos_token_id": 100001, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.33.1", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/pytorch_model-00001-of-000002.bin b/pytorch_model-00001-of-000002.bin new file mode 100644 index 0000000..01f9746 --- /dev/null +++ b/pytorch_model-00001-of-000002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7942123dacfadc7bd7aeccdb19a521f69c326ab07e73376489e84c5abcbb3d75 +size 9492067331 diff --git a/pytorch_model-00002-of-000002.bin b/pytorch_model-00002-of-000002.bin new file mode 100644 index 0000000..74e190f --- /dev/null +++ b/pytorch_model-00002-of-000002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dec791d4d9bcd8ba8fec1fe71951041c9aa7316a043e6db47f40368724313855 +size 6333666262 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..02f256e --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 14483464192 + }, + "weight_map": { + "model.embed_tokens.weight": "pytorch_model-00001-of-000002.bin", + "model.norm.weight": "pytorch_model-00001-of-000002.bin", + "lm_head.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-000002.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-000002.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-000002.bin" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..d85ba6c --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "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..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..cb8e982 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,36 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "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 +}