push to hub

README.md

@@ -0,0 +1,44 @@
+---
+tags:
+- autotrain
+- text-generation-inference
+- text-generation
+library_name: transformers
+widget:
+  - messages:
+      - role: user
+        content: What is your favorite condiment?
+license: other
+---
+
+# Model Trained Using AutoTrain
+
+This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
+
+# Usage
+
+```python
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "PATH_TO_THIS_REPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForCausalLM.from_pretrained(
+    model_path,
+    device_map="auto",
+    torch_dtype='auto'
+).eval()
+
+# Prompt content: "hi"
+messages = [
+    {"role": "user", "content": "hi"}
+]
+
+input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
+output_ids = model.generate(input_ids.to('cuda'))
+response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
+
+# Model response: "Hello! How can I assist you today?"
+print(response)
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "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": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0",
+  "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": "4.39.0"
+}

model-00001-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6b403a0e9092089c15f46e37f0b529b9bb8a0170b6dddfcc52daad24fe62ae
+size 4892809584

model-00002-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41a5ef308fb4b4ecd2e20bd8cca72c4124084336f7cd6e33e2e92691ffe16fb
+size 4983004016

model-00003-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f564a58bc04f3330f460d989ddd2a681b2fd3596fd4df7a460cce6ab5df760
+size 4983004016

model-00004-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16adad63dc2d2329bc0c98f6339cec6571b43405970132fb0b32a9a518d67b7d
+size 4899035200

model-00005-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895281b9887e164d0c3a250214155399f99da570167623814788076eab60b564
+size 4983004016

model-00006-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5fde22952c7a3d936f46964909748415f2b83fca6b4c6a33e609375d7fbf92
+size 4983004016

model-00007-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48dd259085913ebc704a838e98eef8a53b25656884eceb1eede170b397d80d2
+size 4899035248

model-00008-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82827e1922ad1afff1de59d6d53260a2d9b90f3132a1f5d6f02b231468c3797e
+size 4983004072

model-00009-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6826b6779b1fbab8c000f337f6b478b829d47d1fa4515cdcb264097be2eafccf
+size 4983004072

model-00010-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1604c71a1e905f43bb09c847771b19676dabf6ffd13918dd0dc7945064355c8b
+size 4899035248

model-00011-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a94ff116dab38d8ccbba7dd8591116fb2882de35626d92f51ade0d2e57fcc3
+size 4983004072

model-00012-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3769251d1bfcc88bef4a955c816f206c77150a050f47ee00e2b70c036b91750c
+size 4983004072

model-00013-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78e7700d2e1b604581bfc7c6f68d6cb33faf966559ba1a83bf4bd64a546d020
+size 4983004072

model-00014-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b159edc348e5649fafaab852d1e1f96775ea073b47d05c9fd0260708d373fac8
+size 4899035248

model-00015-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76c6962a30744929fe7e3fa0e361b1f510fac4edeb0f25a9b3ea412bb5074a05
+size 4983004072

model-00016-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebc135af1e0c00216052d372da9cc4e157ea5f390e75c9492162f35a8c4f7ff3
+size 4983004072

model-00017-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84a984c02950b7f24a694f7dae36a78dc27ee4b44aeb6c998d9f0d4bb8a13c2
+size 4899035248

model-00018-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a679cce248567098ffdc79e93ff19e93189610acb0841465fb8df351699231
+size 4983004072

model-00019-of-00019.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b3e4b11e27dde463c8526c1524228d4f537eae1fc7d1f69d2f91f120b6ffae
+size 4221679088

model.safetensors.index.json

@@ -0,0 +1,1002 @@
+{
+  "metadata": {
+    "total_size": 93405585408
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00019-of-00019.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
+    "model.norm.weight": "model-00019-of-00019.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "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:e0dc5c1fb504f2713138e3e4922263dc75bad033d59e6f15a5bba66807033336
+size 6072

training_params.json

@@ -0,0 +1,47 @@
+{
+    "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "project_name": "autotrain-cei9g-ag3pe",
+    "data_path": "rishiraj/guanaco-style-metamath-40k",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 1024,
+    "model_max_length": 2048,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "evaluation_strategy": "epoch",
+    "save_total_limit": 1,
+    "save_strategy": "no",
+    "auto_find_batch_size": false,
+    "mixed_precision": "bf16",
+    "lr": 3e-05,
+    "epochs": 3,
+    "batch_size": 2,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 4,
+    "optimizer": "adamw_bnb_8bit",
+    "scheduler": "cosine",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "none",
+    "quantization": "int4",
+    "target_modules": "all-linear",
+    "merge_adapter": false,
+    "peft": false,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "prompt_text_column": "prompt",
+    "text_column": "text",
+    "rejected_text_column": "rejected_text",
+    "push_to_hub": true,
+    "repo_id": "abhishek/autotrain-cei9g-ag3pe",
+    "username": "abhishek"
+}