Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yunconglong/DARE_TIES_13B
+- yunconglong/13B_MATH_DPO
+base_model:
+- yunconglong/DARE_TIES_13B
+- yunconglong/13B_MATH_DPO
+---
+
+# Yunconglong-13B-slerp
+
+Yunconglong-13B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [yunconglong/DARE_TIES_13B](https://huggingface.co/yunconglong/DARE_TIES_13B)
+* [yunconglong/13B_MATH_DPO](https://huggingface.co/yunconglong/13B_MATH_DPO)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: yunconglong/DARE_TIES_13B
+        layer_range: [0, 32]
+      - model: yunconglong/13B_MATH_DPO
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/DARE_TIES_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "allknowingroger/Yunconglong-13B-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 +1,33 @@
+{
+  "_name_or_path": "yunconglong/DARE_TIES_13B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: yunconglong/DARE_TIES_13B
+        layer_range: [0, 32]
+      - model: yunconglong/13B_MATH_DPO
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: yunconglong/DARE_TIES_13B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b9cf38f27c1bc21a7ca65fd24191a46fbc181071e589c8f071785318001942
+size 994050792

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f599a2b94a1894e1a9fbfd2afd8f320df4a92be0666cbe071f229587680a0b8
+size 906004176

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa70aacd1e18b5ca28b6985726f62486c4e86e0443f67dd01d95110e2dfea8a
+size 989923840

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02d603f12ca8e4756b452d55874297dca5daa9b3f6c9ae1eaeb1962f5a867cd
+size 906004192

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139074ba47529d30d3bc528df0a2d3127fe0e16217203931eb919edf23e7d30c
+size 906004192

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dc279842ef2bf5f0181d40eec9727947e86c94d0da507eac338b38fd44db68
+size 906004192

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37abb7064860829b88c7ff230eec9c82fce197336e1298b9130fcdb115a941ad
+size 906004192

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1604f8a2e5bf1665a42775d9707f12abf498754581fe41dea48339dd70e7170f
+size 906004192

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea606a6db138ea25557e94d626af06968b7e04a20b09b349a007f2b55de2d2ef
+size 989923848

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d123400513b7f66de5f6a01e739f9d83431561e77b31fd1cea4677fe9f91037
+size 906004192

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2d78382d72572002a5e25cfea9be4482370bf3a984769a856a4d5cef1f02dd
+size 906004184

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89f57bdbacbfb8b3b9c8c5a2ac15e953b95aacaf92b40c3323085d89a59a59e
+size 906004176

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7496a7a6d5738ed76be2af9c9200069d590a42367e64f9eba6d6e270326497f8
+size 906004192

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2920713ac86c8697e18ad62f6fcc441aef167a7940a127e9a555c49a571263
+size 906004192

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:053244e565ae83d477bec9d6aa69a6002abf5e27d8fc03015d0ba38bfe6d2b14
+size 989923848

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b061164cdaaabe79e5aa74560d3d53d1417584aeef786ea4d79d7addc0227021
+size 906004192

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb71f4c8a222d9d68953ce715f1e64d54e5e43ee31151efa8d666eb4eade5950
+size 906004192

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00e670853283a98a97cf280855165e823167eb6f759a589a090a706385e22f4b
+size 906004192

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f1f1b664565639401212f47f5b2122ee104b94131bcfe25d4d1082ee9af2f9
+size 906004192

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ea568b43b758d6217d9e7f5759e3f6088d10d851e86d05f88c3324a6733f9a
+size 906004192

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba289fbc246ab5e37b0ba63f471d3cba6d13989542e1c8cadd9b9062e67a011
+size 989923832

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984fe0b51ad89aacc3d4f850f38be371e490eeb18d1dbbf36e3d33fadfbd4333
+size 906004192

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32aa148b6b0ef5286891871405bf0b9ac46118fc5131a73f19bcc41013066b11
+size 906004184

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30e2613158bcaa67053f55f744858c5167186d693470e5ff67bc6c5b34f4fc56
+size 906004176

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0019f4d19e7047e220b46f9a9a889cf03e1b345867b9721467e552f351ffe12b
+size 906004176

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60160a7699ee0b13dd66e8089b7c1d0488e47a9511dab99d994dc0fb9071b58f
+size 906004176

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40f12457567fe46800bd522e28ce5e2fbaf1aa209e1e08fcfc88ddddb7142d0
+size 989923824

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22f5a033592f95d69e09336d81572e34859c2c204a4f880f85e51e1455938d3
+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 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "max_length": null,
+  "model_max_length": 255,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}