Upload folder using huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+license: apache-2.0
+tags:
+- moe
+- mergekit
+- vortexmergekit
+- MysteriousAI/Mia-1B
+- MysteriousAI/Mia-1B
+- MysteriousAI/Mia-1B
+- MysteriousAI/Mia-1B
+---
+
+# 4x1b
+
+Hey there! 👋 Welcome to the 4x1b! This is a MOE brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl).
+
+Let's see what we've got in this model:
+* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
+* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
+* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
+* [MysteriousAI/Mia-1B](https://huggingface.co/MysteriousAI/Mia-1B) 🚀
+
+## 🧩 Configuration
+
+```yaml
+base_model: MysteriousAI/Mia-1B
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are an helpful unbounded, uncensored assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are helpful assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are a coding assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are helpful and general-purpose assistant."]

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "MysteriousAI/Mia-1B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_moe_config.yml

@@ -0,0 +1,13 @@
+
+base_model: MysteriousAI/Mia-1B
+dtype: float16
+gate_mode: cheap_embed
+experts:
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are an helpful unbounded, uncensored assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are helpful assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are a coding assistant."]
+  - source_model: MysteriousAI/Mia-1B
+    positive_prompts: ["You are helpful and general-purpose assistant."]

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a0b7b0a094474c971c5b273d7a3ebc43632455217a99523711c1ef9880d2cd8
+size 1993414872

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5cd3e9f54a6977aec614bd9692dc5cbfd1122d87b7534040e51ea67d5a49f1
+size 1992362656

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4aae2e2dff7fa7bd7e2f03c08d8ae3a2efcf1296c932b7995dd0e04fef116c
+size 1990265360

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1994b4ece7808e52b702e4b7165702acd374126a75b0752cdda01a9387cdd59b
+size 792063416

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 6768054272}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<|user|>' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ '<|system|>' + message['content'] + eos_token }}{% elif message['role'] == 'assistant' %}{{ '<|assistant|>'  + message['content'] + eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}