Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- allknowingroger/Multimerge-12B-MoE
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+base_model:
+- allknowingroger/Multimerge-12B-MoE
+- zhengr/MixTAO-7Bx2-MoE-v8.1
+---
+
+# MultiMash-12B-slerp
+
+MultiMash-12B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [allknowingroger/Multimerge-12B-MoE](https://huggingface.co/allknowingroger/Multimerge-12B-MoE)
+* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: allknowingroger/Multimerge-12B-MoE
+        layer_range: [0, 32]
+      - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: allknowingroger/Multimerge-12B-MoE
+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 = "allknowingroger/MultiMash-12B-slerp"
+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 +1,31 @@
+{
+  "_name_or_path": "allknowingroger/Multimerge-12B-MoE",
+  "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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: allknowingroger/Multimerge-12B-MoE
+        layer_range: [0, 32]
+      - model: zhengr/MixTAO-7Bx2-MoE-v8.1
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: allknowingroger/Multimerge-12B-MoE
+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-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33fc4b37acfbada841a8ffa8220b0b6508bf420dce84ee52373f00adfef0083
+size 994050792

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb74da227ce9eb48fa1d5d91b6ccc1fba0924f8d7fff2e533a6a7fb9a5c8285
+size 906004176

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc1f479d0e66e54b1ab324669dca1b8ae5b0af5d747fb4abdf6f38e34c584451
+size 989923840

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59be35bf66bc4db7175cdb06cd22408a8ae65b76fc9ab31b7c3a1dcad200be2
+size 906004192

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca853fbd8f43a55b705a41da8a32c09446f39facf62b9f0af93674bd7691ea59
+size 906004192

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed17fa1d26878890112ba963b0adb2dcdbccf6ab96d496f9d1cb809c62c0c790
+size 906004192

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf9ca4fe441af179309f7540f20f4e6c15f60e381d18e6a9c8523efd09f411e
+size 906004192

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7beef60e3a8ccb74dbd7e9bfd69131ed08b71f3e27eb2772d984fd7e955d8e0c
+size 906004192

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c3b2fc0e9b3e027312eb1fff889ff7b12021b41a3736b6ffe6048bfd77ac13
+size 989923848

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61702516b02d3610ff526048d7a97b28adcf4a9a53a821e69e1fede6e1c4422f
+size 906004192

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9505aa9a0c6ba4ef2e8cdf008ed7a08355fd05d529b6c9e7163b158c111212
+size 906004184

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87085805dec1aa212866d301b75ef003cfe52febb3517790009a69e5f82ca712
+size 906004176

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e2201800a364a148762803c5b900c7bbdf8f2f7f070b373360dbfbb750d989
+size 906004192

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c80860587dfa90852f955763101cc092a55e5d0cf6848cbe6555a9e533bd122
+size 906004192

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d5d572d8c7f379c1ac9ac6c127dc0e3cff704d0fd493f0002806562f00e795
+size 989923848

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addc265fbbe041cdc9c4f2208705870bf4705f25d3cc22e7ff81f0dc7746b361
+size 906004192

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a41927bd8b5cf64b5d32bda47f75bdc116f437af7c31146d2c17677b6153771
+size 906004192

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:754ebf2473fc3ce140e8738b1e8e20ab925885893136ea12e32a450732631dcd
+size 906004192

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7538a7776fef11e8d316dd3759829d970e59b72d1a8979e2fbe92da2f4c6537
+size 906004192

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f9e7d7e1834875e05a12a06d1af097a0e1275d78b252d122f82c6bfdd15b14
+size 906004192

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5dfddc32972b78a6b03a2ff430081fe1297c9baba17a3dc6d8351f0f6c6e0e
+size 989923832

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b06478ef85aba3499cfb9f8c5804a61bda67c94d25786877ab42adf02e07d9
+size 906004192

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d5e72c9adfd5e3bddec514a0b89b7c3bb09a5be67ba18d9dc59e9367f68fde
+size 906004184

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0be36b2f0bba390524471335d31f0ec24e2794905ad4bcd9cc7cef560b34adc
+size 906004176

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4e5f1d56da2d433ed31db73a89190f4f9611055da2a41433084824ea08e4bd
+size 906004176

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2dc51249fea56417ba61ee0874f0d25c83c007539d942eb0bce26e8f50191f
+size 906004176

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac19bf10c220db2b1b04e59505b89a5aeffadffddc3e0d96972495e0d9b4c3d
+size 989923824

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f27b073a52941ac1350c7a903f7cdfa4fde208099a744c10d51fef8e8649b
+size 788571816

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 25758277632}, "weight_map": {"lm_head.weight": "model-00001-of-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00028.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00002-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00028.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00028.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00003-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00028.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00028.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00005-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00028.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00028.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00007-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00028.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00008-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00028.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00028.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00028.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00010-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00028.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00011-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00028.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00028.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00013-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00028.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00014-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00028.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00028.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00015-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00028.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00016-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00028.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00017-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00028.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00018-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00028.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00019-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00020-of-00028.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00020-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00020-of-00028.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00021-of-00028.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00021-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00022-of-00028.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00022-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00022-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00023-of-00028.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00023-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00023-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00024-of-00028.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00024-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00025-of-00028.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00025-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00025-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00026-of-00028.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00026-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00026-of-00028.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00027-of-00028.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00027-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00028-of-00028.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00028-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 32768,
+  "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
+}