Upload 9 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+loss_plot.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,35 @@
+# 4x1.8B MoE Qwen Ckpt 50000
+
+This is a MoE model project constructed based on the Qwen 1.8B model. In this project, we concatenated 4 original models and trained them using special training methods.
+
+This model is a checkpoint model for the continue pretraining stage.
+
+![](loss_plot.png)
+
+# Evaluations
+
+|      Groups      |n-shot| Metric |Value |   |Stderr|
+|------------------|-----:|--------|-----:|---|-----:|
+|boolq             |     0|acc     |0.6508|±  |0.0083|
+|ceval-valid       |     0|acc     |0.5290|±  |0.1912|
+|                  |     0|acc_norm|0.5290|±  |0.1912|
+|cmmlu             |     0|acc     |0.5087|±  |0.1237|
+|                  |     0|acc_norm|0.5087|±  |0.1237|
+|mathqa            |     0|acc     |0.2647|±  |0.0081|
+|                  |     0|acc_norm|0.2693|±  |0.0081|
+|mmlu              |     0|acc     |0.4353|±  |0.0830|
+| - stem           |     0|acc     |0.3809|±  |0.0659|
+| - social_sciences|     0|acc     |0.4959|±  |0.0708|
+| - other          |     0|acc     |0.4844|±  |0.0744|
+| - humanities     |     0|acc     |0.3998|±  |0.0849|
+
+# Acknowledgements
+
++ [Qwen](https://github.com/QwenLM/Qwen)
++ [mistral.ai](https://mistral.ai)
+
+# License Agreement
+
+This project is open source under the Tongyi Qianwen Research License Agreement. You can view the complete license agreement in this link: [https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20RESEARCH%20LICENSE%20AGREEMENT].
+
+During the use of this project, please ensure that your usage behavior complies with the terms and conditions of the license agreement.

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/data03/moe_chatlaw/models/moe_chatlaw_pt_4/checkpoint-26000",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 8192,
+  "model_type": "mixtral",
+  "num_attention_heads": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "num_local_experts": 4,
+  "output_router_logits": true,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.2"
+}

model.safetensors.index.json

@@ -0,0 +1,466 @@
+{
+  "metadata": {
+    "total_size": 8543543296
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|endoftext|>"
+}

tokenization_qwen.py

@@ -0,0 +1,276 @@
+# Copyright (c) Alibaba Cloud.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Tokenization classes for QWen."""
+
+import base64
+import logging
+import os
+import unicodedata
+from typing import Collection, Dict, List, Set, Tuple, Union
+
+import tiktoken
+from transformers import PreTrainedTokenizer, AddedToken
+
+logger = logging.getLogger(__name__)
+
+
+VOCAB_FILES_NAMES = {"vocab_file": "qwen.tiktoken"}
+
+PAT_STR = r"""(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\r\n\p{L}\p{N}]?\p{L}+|\p{N}| ?[^\s\p{L}\p{N}]+[\r\n]*|\s*[\r\n]+|\s+(?!\S)|\s+"""
+ENDOFTEXT = "<|endoftext|>"
+IMSTART = "<|im_start|>"
+IMEND = "<|im_end|>"
+# as the default behavior is changed to allow special tokens in
+# regular texts, the surface forms of special tokens need to be
+# as different as possible to minimize the impact
+EXTRAS = tuple((f"<|extra_{i}|>" for i in range(205)))
+# changed to use actual index to avoid misconfiguration with vocabulary expansion
+SPECIAL_START_ID = 151643
+SPECIAL_TOKENS = tuple(
+    enumerate(
+        (
+            (
+                ENDOFTEXT,
+                IMSTART,
+                IMEND,
+            )
+            + EXTRAS
+        ),
+        start=SPECIAL_START_ID,
+    )
+)
+SPECIAL_TOKENS_SET = set(t for i, t in SPECIAL_TOKENS)
+
+
+def _load_tiktoken_bpe(tiktoken_bpe_file: str) -> Dict[bytes, int]:
+    with open(tiktoken_bpe_file, "rb") as f:
+        contents = f.read()
+    return {
+        base64.b64decode(token): int(rank)
+        for token, rank in (line.split() for line in contents.splitlines() if line)
+    }
+
+
+class QWenTokenizer(PreTrainedTokenizer):
+    """QWen tokenizer."""
+
+    vocab_files_names = VOCAB_FILES_NAMES
+
+    def __init__(
+        self,
+        vocab_file,
+        errors="replace",
+        extra_vocab_file=None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        # how to handle errors in decoding UTF-8 byte sequences
+        # use ignore if you are in streaming inference
+        self.errors = errors  
+
+        self.mergeable_ranks = _load_tiktoken_bpe(vocab_file)  # type: Dict[bytes, int]
+        self.special_tokens = {
+            token: index
+            for index, token in SPECIAL_TOKENS
+        }
+
+        # try load extra vocab from file
+        if extra_vocab_file is not None:
+            used_ids = set(self.mergeable_ranks.values()) | set(self.special_tokens.values())
+            extra_mergeable_ranks = _load_tiktoken_bpe(extra_vocab_file)
+            for token, index in extra_mergeable_ranks.items():
+                if token in self.mergeable_ranks:
+                    logger.info(f"extra token {token} exists, skipping")
+                    continue
+                if index in used_ids:
+                    logger.info(f'the index {index} for extra token {token} exists, skipping')
+                    continue
+                self.mergeable_ranks[token] = index
+            # the index may be sparse after this, but don't worry tiktoken.Encoding will handle this
+
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        assert (
+            len(self.mergeable_ranks) + len(self.special_tokens) == enc.n_vocab
+        ), f"{len(self.mergeable_ranks) + len(self.special_tokens)} != {enc.n_vocab} in encoding"
+
+        self.decoder = {
+            v: k for k, v in self.mergeable_ranks.items()
+        }  # type: dict[int, bytes|str]
+        self.decoder.update({v: k for k, v in self.special_tokens.items()})
+
+        self.tokenizer = enc  # type: tiktoken.Encoding
+
+        self.eod_id = self.tokenizer.eot_token
+        self.im_start_id = self.special_tokens[IMSTART]
+        self.im_end_id = self.special_tokens[IMEND]
+
+    def __getstate__(self):
+        # for pickle lovers
+        state = self.__dict__.copy()
+        del state["tokenizer"]
+        return state
+
+    def __setstate__(self, state):
+        # tokenizer is not python native; don't pass it; rebuild it
+        self.__dict__.update(state)
+        enc = tiktoken.Encoding(
+            "Qwen",
+            pat_str=PAT_STR,
+            mergeable_ranks=self.mergeable_ranks,
+            special_tokens=self.special_tokens,
+        )
+        self.tokenizer = enc
+
+    def __len__(self) -> int:
+        return self.tokenizer.n_vocab
+
+    def get_vocab(self) -> Dict[bytes, int]:
+        return self.mergeable_ranks
+
+    def convert_tokens_to_ids(
+        self, tokens: Union[bytes, str, List[Union[bytes, str]]]
+    ) -> List[int]:
+        ids = []
+        if isinstance(tokens, (str, bytes)):
+            if tokens in self.special_tokens:
+                return self.special_tokens[tokens]
+            else:
+                return self.mergeable_ranks.get(tokens)
+        for token in tokens:
+            if token in self.special_tokens:
+                ids.append(self.special_tokens[token])
+            else:
+                ids.append(self.mergeable_ranks.get(token))
+        return ids
+
+    def _add_tokens(
+        self,
+        new_tokens: Union[List[str], List[AddedToken]],
+        special_tokens: bool = False,
+    ) -> int:
+        if not special_tokens and new_tokens:
+            raise ValueError("Adding regular tokens is not supported")
+        for token in new_tokens:
+            surface_form = token.content if isinstance(token, AddedToken) else token
+            if surface_form not in SPECIAL_TOKENS_SET:
+                raise ValueError("Adding unknown special tokens is not supported")
+        return 0
+
+    def save_vocabulary(self, save_directory: str, **kwargs) -> Tuple[str]:
+        """
+        Save only the vocabulary of the tokenizer (vocabulary).
+
+        Returns:
+            `Tuple(str)`: Paths to the files saved.
+        """
+        file_path = os.path.join(save_directory, "qwen.tiktoken")
+        with open(file_path, "w", encoding="utf8") as w:
+            for k, v in self.mergeable_ranks.items():
+                line = base64.b64encode(k).decode("utf8") + " " + str(v) + "\n"
+                w.write(line)
+        return (file_path,)
+
+    def tokenize(
+        self,
+        text: str,
+        allowed_special: Union[Set, str] = "all",
+        disallowed_special: Union[Collection, str] = (),
+        **kwargs,
+    ) -> List[Union[bytes, str]]:
+        """
+        Converts a string in a sequence of tokens.
+
+        Args:
+            text (`str`):
+                The sequence to be encoded.
+            allowed_special (`Literal["all"]` or `set`):
+                The surface forms of the tokens to be encoded as special tokens in regular texts.
+                Default to "all".
+            disallowed_special (`Literal["all"]` or `Collection`):
+                The surface forms of the tokens that should not be in regular texts and trigger errors.
+                Default to an empty tuple.
+
+            kwargs (additional keyword arguments, *optional*):
+                Will be passed to the underlying model specific encode method.
+
+        Returns:
+            `List[bytes|str]`: The list of tokens.
+        """
+        tokens = []
+        text = unicodedata.normalize("NFC", text)
+
+        # this implementation takes a detour: text -> token id -> token surface forms
+        for t in self.tokenizer.encode(
+            text, allowed_special=allowed_special, disallowed_special=disallowed_special
+        ):
+            tokens.append(self.decoder[t])
+        return tokens
+
+    def convert_tokens_to_string(self, tokens: List[Union[bytes, str]]) -> str:
+        """
+        Converts a sequence of tokens in a single string.
+        """
+        text = ""
+        temp = b""
+        for t in tokens:
+            if isinstance(t, str):
+                if temp:
+                    text += temp.decode("utf-8", errors=self.errors)
+                    temp = b""
+                text += t
+            elif isinstance(t, bytes):
+                temp += t
+            else:
+                raise TypeError("token should only be of type types or str")
+        if temp:
+            text += temp.decode("utf-8", errors=self.errors)
+        return text
+
+    @property
+    def vocab_size(self):
+        return self.tokenizer.n_vocab
+
+    def _convert_id_to_token(self, index: int) -> Union[bytes, str]:
+        """Converts an id to a token, special tokens included"""
+        if index in self.decoder:
+            return self.decoder[index]
+        raise ValueError("unknown ids")
+
+    def _convert_token_to_id(self, token: Union[bytes, str]) -> int:
+        """Converts a token to an id using the vocab, special tokens included"""
+        if token in self.special_tokens:
+            return self.special_tokens[token]
+        if token in self.mergeable_ranks:
+            return self.mergeable_ranks[token]
+        raise ValueError("unknown token")
+
+    def _tokenize(self, text: str, **kwargs):
+        """
+        Converts a string in a sequence of tokens (string), using the tokenizer. Split in words for word-based
+        vocabulary or sub-words for sub-word-based vocabularies (BPE/SentencePieces/WordPieces).
+
+        Do NOT take care of added tokens.
+        """
+        raise NotImplementedError
+
+    def _decode(
+        self,
+        token_ids: Union[int, List[int]],
+        skip_special_tokens: bool = False,
+        errors: str = None,
+        **kwargs,
+    ) -> str:
+        if isinstance(token_ids, int):
+            token_ids = [token_ids]
+        if skip_special_tokens:
+            token_ids = [i for i in token_ids if i < self.eod_id]
+        return self.tokenizer.decode(token_ids, errors=errors or self.errors)

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "QWenTokenizer",
+  "use_fast": false
+}