Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model:
+- macadeliccc/SOLAR-2x10.7b-truthy-dpo
+- Alsebay/SunnyRain-2x10.7B
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [macadeliccc/SOLAR-2x10.7b-truthy-dpo](https://huggingface.co/macadeliccc/SOLAR-2x10.7b-truthy-dpo)
+* [Alsebay/SunnyRain-2x10.7B](https://huggingface.co/Alsebay/SunnyRain-2x10.7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: macadeliccc/SOLAR-2x10.7b-truthy-dpo
+  - model: Alsebay/SunnyRain-2x10.7B
+merge_method: slerp
+base_model: macadeliccc/SOLAR-2x10.7b-truthy-dpo
+dtype: bfloat16
+parameters:
+  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers
+
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "macadeliccc/SOLAR-2x10.7b-truthy-dpo",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "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": "4.44.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,8 @@
+models:
+  - model: macadeliccc/SOLAR-2x10.7b-truthy-dpo
+  - model: Alsebay/SunnyRain-2x10.7B
+merge_method: slerp
+base_model: macadeliccc/SOLAR-2x10.7b-truthy-dpo
+dtype: bfloat16
+parameters:
+  t: [0, 0.5, 1, 0.5, 0] # V shaped curve: Hermes for input & output, WizardMath in the middle layers

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018177aea3c1cbb1a61494bf32baac7d9b2041b78a9b81a65c4d0cf5c1dcb5ec
+size 4936868456

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ea6182af743ee715d0bce801bc0d5d186bca299fae1d245e65e99ab5e68b86
+size 4974684360

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f38e33e822241495bb11832aa53cca9a8bef933e0e6c9b776ede52783877da1
+size 4924319672

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da2fffb3cb602ad83b7e461ad52f3926dfad5c40a0085ab637b71c7122c7228
+size 4966262504

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4b7c2dc3efde5a92b40ae2fd138c5aac27770c3e9b6f279b6b3128159857fc3
+size 4966262520

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2df6c8fd237eb3c7e5f9ede011c672ae9cac95601b797434ec0cfa1a8190a773
+size 4932741520

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5e8436facebbd1c8be64b84c76aed3dcedd10f5a369cdd0617b5f754045b89
+size 4966262512

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11d44635031cfe7e1c9a74fdf3b0d6322e28e3b40ccafa392c7f67477d7d9b8
+size 3707944624

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 38375268352}, "weight_map": {"lm_head.weight": "model-00001-of-00008.safetensors", "model.embed_tokens.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00008.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00008.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00008.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00003-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00008.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00008.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00005-of-00008.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00008.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.40.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00008.safetensors", "model.layers.41.block_sparse_moe.gate.weight": "model-00006-of-00008.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.42.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.43.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.44.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.45.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.46.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00008.safetensors", "model.layers.47.block_sparse_moe.gate.weight": "model-00007-of-00008.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00008.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00008-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.norm.weight": "model-00008-of-00008.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 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "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": true
+}