four-two-labs/tinyllama-moe-base-orpo-mix

README.md

@@ -0,0 +1,75 @@
+---
+base_model: four-two-labs/tinyllama-moe-base
+tags:
+- trl
+- orpo
+- generated_from_trainer
+model-index:
+- name: orpo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# orpo
+
+This model is a fine-tuned version of [four-two-labs/tinyllama-moe-base](https://huggingface.co/four-two-labs/tinyllama-moe-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1757
+- Rewards/chosen: -0.1708
+- Rewards/rejected: -0.1682
+- Rewards/accuracies: 0.5003
+- Rewards/margins: -0.0027
+- Logps/rejected: -1.6818
+- Logps/chosen: -1.7085
+- Logits/rejected: -2.6114
+- Logits/chosen: -2.6139
+- Nll Loss: 1.0859
+- Log Odds Ratio: -0.8989
+- Log Odds Chosen: -0.1073
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | Nll Loss | Log Odds Ratio | Log Odds Chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|:--------:|:--------------:|:---------------:|
+| 1.1835        | 0.6001 | 2270 | 1.1764          | -0.1711        | -0.1684          | 0.4976             | -0.0027         | -1.6838        | -1.7106      | -2.6416         | -2.6430       | 1.0866   | -0.8991        | -0.1073         |
+| 1.1494        | 1.2002 | 4540 | 1.1757          | -0.1709        | -0.1682          | 0.5003             | -0.0026         | -1.6820        | -1.7085      | -2.5529         | -2.5573       | 1.0860   | -0.8988        | -0.1070         |
+| 1.233         | 1.8003 | 6810 | 1.1757          | -0.1709        | -0.1682          | 0.4993             | -0.0027         | -1.6819        | -1.7086      | -2.5859         | -2.5892       | 1.0859   | -0.8989        | -0.1073         |
+| 1.2344        | 2.4004 | 9080 | 1.1757          | -0.1708        | -0.1682          | 0.5003             | -0.0027         | -1.6818        | -1.7085      | -2.6114         | -2.6139       | 1.0859   | -0.8989        | -0.1073         |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32001,
+  "<|im_start|>": 32000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "four-two-labs/tinyllama-moe-base",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32000,
+  "eos_token_id": 32001,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 32001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32000,
+  "eos_token_id": 32001,
+  "pad_token_id": 32001,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d1e49fc8595b28820a6dcad057861620de1a2e554bd3c8e21c47f50a4f63d4
+size 4996921840

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26888def291633347235f4b63a0ac25f19ae384bbec01676014d3d0fa152e82c
+size 1771201464

model.safetensors.index.json

@@ -0,0 +1,428 @@
+{
+  "metadata": {
+    "total_size": 6768070656
+  },
+  "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-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-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.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 +1,28 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{{'<|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|>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|im_end|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9deea2ee937328ab947d871c3515816368518bdd7ee8273f2a5c45f8b19cd762
+size 5240