Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+base_model:
+- LeroyDyer/Mixtral_AI_Cyber_MegaMind
+- LeroyDyer/Mixtral_AI_Cyber_MegaMind_2_0
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [LeroyDyer/Mixtral_AI_Cyber_MegaMind](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_MegaMind)
+* [LeroyDyer/Mixtral_AI_Cyber_MegaMind_2_0](https://huggingface.co/LeroyDyer/Mixtral_AI_Cyber_MegaMind_2_0)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+models:
+  - model: LeroyDyer/Mixtral_AI_Cyber_MegaMind
+    parameters:
+      weight: 0.512
+  - model: LeroyDyer/Mixtral_AI_Cyber_MegaMind_2_0
+    parameters:
+      weight: 0.512
+merge_method: linear
+dtype: float16
+
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "LeroyDyer/Mixtral_AI_Cyber_MegaMind",
+  "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": 3,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+models:
+  - model: LeroyDyer/Mixtral_AI_Cyber_MegaMind
+    parameters:
+      weight: 0.512
+  - model: LeroyDyer/Mixtral_AI_Cyber_MegaMind_2_0
+    parameters:
+      weight: 0.512
+merge_method: linear
+dtype: float16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68bef7ab9ecfc790537a286c7fa42742b8b92e934d59d6e94cec550dbb89de19
+size 5993759896

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7052beb3dc032f70bad775553441667e4fdb41e656328ff6e14fbf889dd17fea
+size 5972763432

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77ce9b3cf5ddd621f38654b7b2572031236507eb23bd50d3af045a27da40831
+size 5972763496

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d6b88eef0a0668c764e4e62de801d280f1376f7e98aeeed656c2ccb8e034d2
+size 5972763536

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9bfebd4fd0fe49a533827b6e76de1172a6f2720c4155dfe5e449a7768c9ee6
+size 5972763536

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af17130263249e0118dd122dda048fe347d3960578c2756b45ce574826c6f7e
+size 5972763536

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630a87b9764da9af85f95ef8ccb510e942531a5ba2842e4832dc4ddd61d665a8
+size 5972763536

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52453d1769dc568373da4193044c025a5cac2327a9bc5cd0bd139afa7d591dac
+size 5888893256

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b457664274e468a767188714149d2aa8ff2b2a88e1214fd5554390efbdcdf04a
+size 588222512

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 48307380224}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.norm.weight": "model-00001-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00009.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00009.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00009.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00009.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00009.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00009.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00009.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00009.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00008-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00009.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00009.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00009-of-00009.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00009-of-00009.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 +1,47 @@
+{
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "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
+}