Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+tags:
+- moe
+- merge
+- mergekit
+- lazymergekit
+- cognitivecomputations/dolphin-2_6-phi-2
+- lxuechen/phi-2-dpo
+- Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
+- mrm8488/phi-2-coder
+---
+
+# phixtral-4x2.8
+
+phixtral-2x2.8 is a Mixure of Experts (MoE) made with the following models using a custom version of mergekit:
+* [cognitivecomputations/dolphin-2_6-phi-2](https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2)
+* [lxuechen/phi-2-dpo](https://huggingface.co/lxuechen/phi-2-dpo)
+* [Yhyu13/phi-2-sft-dpo-gpt4_en-ep1](https://huggingface.co/Yhyu13/phi-2-sft-dpo-gpt4_en-ep1)
+* [mrm8488/phi-2-coder](https://huggingface.co/mrm8488/phi-2-coder)
+
+## 🧩 Configuration
+
+```yaml
+base_model: cognitivecomputations/dolphin-2_6-phi-2
+gate_mode: cheap_embed
+experts:
+  - source_model: cognitivecomputations/dolphin-2_6-phi-2
+    positive_prompts: [""]
+  - source_model: lxuechen/phi-2-dpo
+    positive_prompts: [""]
+  - source_model: Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
+    positive_prompts: [""]
+  - source_model: mrm8488/phi-2-coder
+    positive_prompts: [""]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mlabonne/phixtral-4x2.8"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

added_tokens.json

@@ -0,0 +1,42 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257,
+  "<|im_end|>": 50295,
+  "<|im_start|>": 50296
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "cognitivecomputations/dolphin-2_6-phi-2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_pdrop": 0.0,
+  "auto_map": {
+    "AutoConfig": "cognitivecomputations/dolphin-2_6-phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "cognitivecomputations/dolphin-2_6-phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "flash_attn": false,
+  "flash_rotary": false,
+  "fused_dense": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "img_processor": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "n_embd": 2560,
+  "n_head": 32,
+  "n_head_kv": null,
+  "n_inner": null,
+  "n_layer": 32,
+  "n_positions": 2048,
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "resid_pdrop": 0.1,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "rotary_dim": 32,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": false,
+  "vocab_size": 51200
+}

mergekit_moe_config.yml

@@ -0,0 +1,11 @@
+base_model: cognitivecomputations/dolphin-2_6-phi-2
+gate_mode: cheap_embed
+experts:
+  - source_model: cognitivecomputations/dolphin-2_6-phi-2
+    positive_prompts: [""]
+  - source_model: lxuechen/phi-2-dpo
+    positive_prompts: [""]
+  - source_model: Yhyu13/phi-2-sft-dpo-gpt4_en-ep1
+    positive_prompts: [""]
+  - source_model: mrm8488/phi-2-coder
+    positive_prompts: [""]

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89f2a8822555a57254b2dd9aa5f41b6d4eb4f5cd421e93423cccf0153ebcf109
+size 9965916552

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0022776c348793df7b4ec4fd72450496967ef5841f900a60f9a32e133b017e
+size 5662983792

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"transformer.embd.wte.weight": "model-00001-of-00002.safetensors", "lm_head.linear.bias": "model-00001-of-00002.safetensors", "lm_head.linear.weight": "model-00001-of-00002.safetensors", "lm_head.ln.bias": "model-00001-of-00002.safetensors", "lm_head.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.0.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.1.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.2.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.3.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.4.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.5.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.6.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.7.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.8.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.9.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.10.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.11.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.12.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.13.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.14.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.15.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.16.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.17.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.18.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.19.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.20.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.21.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.22.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.23.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.24.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.25.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.26.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.27.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.28.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.29.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.30.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.31.ln.bias": "model-00001-of-00002.safetensors", "transformer.h.0.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.1.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.2.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.3.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.4.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.5.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.6.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.7.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.8.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.9.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.10.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.11.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.12.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.13.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.14.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.15.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.16.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.17.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.18.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.19.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.20.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.21.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.22.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.23.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.24.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.25.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.26.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.27.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.28.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.29.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.30.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.31.ln.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.31.mixer.out_proj.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.31.mixer.out_proj.weight": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.31.mixer.Wqkv.bias": "model-00001-of-00002.safetensors", "transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.30.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.31.mixer.Wqkv.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.2.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.3.w1.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.2.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.3.w2.bias": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.18.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.19.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.20.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.21.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.22.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.23.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.24.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.25.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.26.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.27.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.28.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.29.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.30.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.31.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors", "transformer.h.0.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.1.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.2.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.3.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.4.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.5.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.6.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.7.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.8.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.9.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.10.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.11.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.12.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.13.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.14.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.22.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.23.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.24.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.25.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.26.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.27.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.28.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.29.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.30.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "transformer.h.31.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,341 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50296": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}