Upload 15 files

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "llama",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "rope_scaling": null,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca5ef5b53af021104a366d6b22c6913a784a76c1f85bd05e534a4682272a6b76
+size 1992887642

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b9f030d7939e4ebc3e9de7bad8b0cce722ed9b14076373d7106776a06d7c258
+size 1952617706

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116b544cd332194024a61f68be5649b8af2be307733604548a21d7e07c136dd9
+size 1864501312

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6402a9b5071b72f46a00659d34a7db75395dbdfcb5f6000c6ee68d5112d97918
+size 1996629330

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:287d168e24b14a06066898c9fa5fc0aad33cd395963a1727d76f3bc6675f4fa0
+size 1945238264

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5807b23d22da5453ac01d531b78c303630d0816a700262604edd0be7e6d772f8
+size 1923240592

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0023c6aaf5598817f44f497b7633aba5abf60f32de80724639cd7344b83b44c
+size 1963518098

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29813a3c2c1447c717e08216eddb7fa9678244d6bf964a3b45a59bc2a6334a0b
+size 1592926894

pytorch_model.bin.index.json

@@ -0,0 +1,374 @@
+{
+  "metadata": {
+    "total_size": 15231433728
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00005-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00006-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00007-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00008-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}