初始化项目，由ModelHub XC社区提供模型

Model: vicgalle/Mixtral-7Bx2-truthy
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,326 @@
+---
+license: apache-2.0
+library_name: transformers
+datasets:
+- jondurbin/truthy-dpo-v0.1
+model-index:
+- name: Mixtral-7Bx2-truthy
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 72.18
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 87.88
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 65.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 74.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 80.66
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 67.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=vicgalle/Mixtral-7Bx2-truthy
+      name: Open LLM Leaderboard
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+```
+"results": {
+    "truthfulqa_mc": {
+      "mc1": 0.6107711138310894,
+      "mc1_stderr": 0.017068552680690338,
+      "mc2": 0.7527999957012117,
+      "mc2_stderr": 0.014045181780156504
+    }
+```
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_vicgalle__Mixtral-7Bx2-truthy)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |74.64|
+|AI2 Reasoning Challenge (25-Shot)|72.18|
+|HellaSwag (10-Shot)              |87.88|
+|MMLU (5-Shot)                    |65.20|
+|TruthfulQA (0-shot)              |74.68|
+|Winogrande (5-shot)              |80.66|
+|GSM8k (5-shot)                   |67.25|
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "cloudyu/Mixtral_7Bx2_MoE",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00853cc72426e68541b76cb3273c808eedac0391e56cb769944b45e5664bc1a
+size 4993525184

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c66229f5b0c809ea09f6e1f0f83a0f8507c86efcedc094f7a1c6a0f17b7873
+size 4932724792

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008d8a074c31253e52e3eca22aa7e522d99dda63c5f2e5d527eb0899a8231bcb
+size 4966262448

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b22da4594cdefdc481f948b0aff4a2990f44af960b10956f9c9f9db88b88ba5
+size 4966262448

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89a1c11edcf92948895395e0b6235996e157126fa9be15f2c29f17a8e312e641
+size 4932741456

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f97d1d773811cbf690cf011d1aea6559b314c484562730fd5cfb7c576654f8
+size 966812864

model.safetensors.index.json

@@ -0,0 +1,426 @@
+{
+  "metadata": {
+    "total_size": 25758277632
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}