Upload folder using huggingface_hub

README.md

@@ -0,0 +1,64 @@
+---
+base_model:
+- Qwen/Qwen2-7B
+- Qwen/Qwen2-7B
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- Qwen/Qwen2-7B
+---
+
+# qwen2-merged
+
+qwen2-merged is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+* [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B)
+
+## 🧩 Configuration
+
+```yaml
+base_model: Qwen/Qwen2-7B
+gate_mode: random
+architecture: qwen
+dtype: bfloat16
+experts:
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+
+shared_experts:
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+    residual_scale: 0.1
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Aoyinke/qwen2-merged"
+
+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 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "mixtral",
+  "num_attention_heads": 28,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_moe_config.yml

@@ -0,0 +1,17 @@
+
+base_model: Qwen/Qwen2-7B
+gate_mode: random
+architecture: qwen
+dtype: bfloat16
+experts:
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+
+shared_experts:
+  - source_model: Qwen/Qwen2-7B
+    positive_prompts: []
+    residual_scale: 0.1
+

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a92d2c4c4c3a8df72ec112774c2b7508d257b02b5cd4f367c0bcd670790f37bf
+size 1090002152

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3bbe829ee8f54329655a283d2b61663423af3715f37c2e92940fb6c3be8670
+size 1904943048

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5732bd1d41d2e8e5037697b28565d4aa34a4d2aaac4f7d19608463d7855ecd2
+size 1901070144

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4a330da4a65a233e3e2e17db620e3f03d1ffd18bc8d2c1bbc4d0c8e5f6d3e3
+size 1901070160

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2b7a88bdea526321a11c2e59b06f777b7a06a9a5fc8b866bb45073a1a7b72f
+size 1901070160

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2ed19028f386bb145b4eba1fd425603eba6ea2b6bb6397c5f649c47cd69a1f
+size 1901070152

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74fd487b7fdf25b50494f2077425043fb5f21bc42b36a83d10985c46fb25e880
+size 1901070144

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d993e7c1a6a60e6f9ae620a8d40e5ec30ac221064e4297706c48367c76b36f9b
+size 1901070160

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f7f7f7174f2418fc033c75d726ee62927d221148e1eefb1fbf2fd81548e5e9c
+size 1901070160

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace6182fe9554a21bf5450c2fd8440a1faaec2ec3bc3fc13adc0d57ead494061
+size 1901070152

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1958e5e9e2c248584e46108af1cf37c7ba9b3c3a68373cc7c69d5b7c983a4502
+size 1901070144

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfec39dafdb8070ba286a939385415a559c2c7298d72c3538edc2e87f6ce39b
+size 1901070160

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c0dc812bcad91ded26ec1cbaf03c324e515e34d6b0e03cac03944d2650f323
+size 1901070160

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85bf0e1b5fb13da0ee20dd63026685071e870f6d0dc414b3d1695f4e7b04e207
+size 1996703048

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9dd06813b34fa30b6ea0efe75f0d3c237458cfa97f54e4c7a6d20ca71eac91
+size 734411616

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.norm.weight": "model-00001-of-00015.safetensors", "lm_head.weight": "model-00002-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00015.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00015.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00015.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00015.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00015.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00015.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00015.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00015.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00015-of-00015.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,13 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": null,
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}