Upload folder using huggingface_hub

README.md

@@ -0,0 +1,67 @@
+---
+license: apache-2.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- yanolja/EEVE-Korean-10.8B-v1.0
+- upstage/SOLAR-10.7B-v1.0
+base_model:
+- yanolja/EEVE-Korean-10.8B-v1.0
+- upstage/SOLAR-10.7B-v1.0
+---
+
+# TEST_MODEL
+
+TEST_MODEL is a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [yanolja/EEVE-Korean-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-10.8B-v1.0)
+* [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0)
+
+## 🧩 Configuration
+
+```yaml
+base_model: yanolja/EEVE-Korean-10.8B-v1.0
+dtype: float16
+experts:
+  - source_model: yanolja/EEVE-Korean-10.8B-v1.0
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: upstage/SOLAR-10.7B-v1.0
+    positive_prompts: ["You are helpful assistant."]
+merge_method: slerp
+gate_mode: cheap_embed
+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
+
+tokenizer_source: base
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jieunhan/TEST_MODEL"
+
+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"])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "yanolja/EEVE-Korean-10.8B-v1.0",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "vocab_size": 40960
+}

mergekit_moe_config.yml

@@ -0,0 +1,19 @@
+
+base_model: yanolja/EEVE-Korean-10.8B-v1.0
+dtype: float16
+experts:
+  - source_model: yanolja/EEVE-Korean-10.8B-v1.0
+    positive_prompts: ["You are an helpful general-pupose assistant."]
+  - source_model: upstage/SOLAR-10.7B-v1.0
+    positive_prompts: ["You are helpful assistant."]
+merge_method: slerp
+gate_mode: cheap_embed
+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
+
+tokenizer_source: base

model-00001-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a15480c5c285b1a7b4bd5882f361de7ae54b2473c6a8d3d45918b56df8ead66
+size 1963342736

model-00002-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c6f2dac78f4595ca808d4086f9691d13eba560b9602d8e14ed66428ec93b3bc
+size 1996490944

model-00003-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cc75c97be997b3a1a2af4021a171fd59ce76e21e336dc02f11479a14dfdea7
+size 1996490952

model-00004-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68517cd4eaf3c9500f9d6fc000f54ece91be44999ae47c46566ec61816a5fa6a
+size 1996490952

model-00005-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f266128ba7568b43514def22026886b327588b83f844143e49bb676381b91d0b
+size 1996490952

model-00006-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc9168c18dfd9e7e4a64796b50a00c2443fd5db0f0e0d5fdcd0abeb68bae319
+size 1996490952

model-00007-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c67dabae970a72bc364e8eb5d7511dac2d85923caca4b0697ea37389adc62f
+size 1996490936

model-00008-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f241c1ee10ae2a3a1690567a7cf6876715703150ee2f916fe885a1c941c781
+size 1996490944

model-00009-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d6055e6dd5043b1d1051d8de85535612324e5fb2997dd273c1140b8e268ce8
+size 1996490952

model-00010-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e746234c21aea1d2e64c2e302eb92cc5d2912ca9ec5d385a7c2a55ea32f8c7
+size 1996490952

model-00011-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cba6e1099fb203ad7a589d47cbeb5849ae551de6c1223528fd3b8eafe238f07
+size 1996490952

model-00012-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8c96e49be7f6ddd809ca7535edc6f0a2beeb6edf378ea8d75b5bcbd4071e29
+size 1996490944

model-00013-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e97690feb4c60aededc4cce3de8cc1f172e396f8e73c84d0ec63e9903a1dda4
+size 1996490936

model-00014-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c988553fd41028b91c30abc8ec76240f625311c58663e0d38ebb594354b33eb
+size 1996490952

model-00015-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e001b5e1c7c8efbde941b10947f159067e12a7d71d8a6771023cd17c6ec423f
+size 1996490952

model-00016-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6de59b7df9fb8dd5e68b353fed3c1942de43495215cacb60f4e3e56cc402a7
+size 1996490952

model-00017-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d330662f8a6754250d33eba84573dc937502002442cd9817ace5c4436445acaa
+size 1996490952

model-00018-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5002fe63c0a53efcbd05e50d25b9a5ecffeb3ddf938db2ca5f95a229323fe0
+size 1996893128

model-00019-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e24ea69e221d3abe7540583a5e3c6a220d1ae332e2a31cf72a13a3b76e0b544
+size 1979726688

model-00020-of-00020.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d545e946fcaca9eb0301446ff077dbe4d2c9078c3900b0ce21972e810881c3cf
+size 638328304

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00020.safetensors", "model.norm.weight": "model-00001-of-00020.safetensors", "lm_head.weight": "model-00001-of-00020.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00020.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00020.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00020.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00020.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00020.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00020.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00020.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00020.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00020.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00018-of-00020.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00019-of-00020.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00020.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00020.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00020-of-00020.safetensors"}}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,53 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|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": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}