Upload folder using huggingface_hub

.ipynb_checkpoints/mergekit_config-checkpoint.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
+        layer_range: [0, 32]
+      - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

README.md

@@ -1,3 +1,63 @@
 ---
-license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+base_model:
+- yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+- zhengr/MixTAO-7Bx2-MoE-v8.1
 ---
+
+# Godrick_7Bx2_MoE_13B-v0.1
+
+Godrick_7Bx2_MoE_13B-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B](https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
+        layer_range: [0, 32]
+      - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "blueRab2it/Godrick_7Bx2_MoE_13B-v0.1"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+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"])
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B 
+        layer_range: [0, 32]
+      - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b5e84b7d3f67d78c5c5ba36bcfb28032f981423d0f72d946924155f810384d
+size 1906313128

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cc16a445d3eb26ab6326d162fdabed24635c0914290446e993978d1f1290de2
+size 1996490960

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fb84f193f002ff026fc2c104eb2c13f1c0fcda605483f3ad5e3b1cb62bebd22
+size 1996490968

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e26563242fcfdff1018cc25fecfcd9777fb0a9cf05806a900bd84222c4be3a
+size 1996490960

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d323ebfed39cefae0312147ed6d6c49d53e42ece1a48e4072a574cb0e50f2e
+size 1906321400

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2000bc549a33509e7adc7d1a4cb4a53fccdf6ac69d60674275516d695ea8aa18
+size 1996490960

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8158c6ba5a8aa0cae3f62df72cc8f4721375eb1a9311c07121c24847947c697
+size 1996490968

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ed8491331152ebb8b4000faf3359ffe7e837b70c7094e1f49abf032a552415
+size 1996490968

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f02d709a95baab3e00faecd0441958907d7d7e1cf29b9708ef1b434edc769e3
+size 1996490952

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b85970aa3b92e1035890d38244a0c4d5cc284feab0b9d86810e6e53334df1444
+size 1996490968

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ecf3887d00c5b5d4539bd55d39f70b5f06096bad34b7004c33d9fed44bfdd3a
+size 1996490968

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df6612bed69e979af99063bc2214f4edd329713d5d1f5821faeaf9b73b12633
+size 1292375104

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "lm_head.weight": "model-00005-of-00012.safetensors", "model.norm.weight": "model-00005-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 255,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}