Upload folder using huggingface_hub

README.md

@@ -1,3 +1,51 @@
 ---
-license: cc-by-nc-nd-3.0
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
 ---
+# merged2
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /home/ubuntu/nvm/mathdpo
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: bfloat16
+merge_method: passthrough
+slices:
+- sources:
+  - layer_range: [0, 7]
+    model:
+      model:
+        path: /home/ubuntu/nvm/mathdpo
+- sources:
+  - layer_range: [9, 12]
+    model:
+      model:
+        path: /home/ubuntu/nvm/mathdpo
+- sources:
+  - layer_range: [14, 17]
+    model:
+      model:
+        path: /home/ubuntu/nvm/mathdpo
+- sources:
+  - layer_range: [19, 32]
+    model:
+      model:
+        path: /home/ubuntu/nvm/mathdpo
+```

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/home/ubuntu/nvm/mathdpo",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 8,
+  "num_local_experts": 2,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3966565c1793369266e86b9efcb39790ac0c3201fe0ac787dc67df9e6859af
+size 9892507920

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d549e5209d3c58396092afe96dc711d634fa25ce130870dee2e89c331145c357
+size 8952958096

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.embed_tokens.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": null,
+  "model_max_length": 255,
+  "pad_to_multiple_of": null,
+  "pad_token": "<s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}