Upload folder using huggingface_hub

README.md

@@ -0,0 +1,53 @@
+---
+base_model:
+- SillyTilly/mistralai_Mistral-Nemo-Base-2407
+- SillyTilly/mistralai_Mistral-Nemo-Instruct-2407
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [SillyTilly/mistralai_Mistral-Nemo-Base-2407](https://huggingface.co/SillyTilly/mistralai_Mistral-Nemo-Base-2407) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [SillyTilly/mistralai_Mistral-Nemo-Instruct-2407](https://huggingface.co/SillyTilly/mistralai_Mistral-Nemo-Instruct-2407)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+dtype: bfloat16
+merge_method: ties
+parameters:
+  normalize: true
+  int8_mask: true
+  lambda: 0.8
+slices:
+  - sources:
+    - model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+      layer_range: [0, -1]
+      parameters:
+        weight: 1.0
+        density: 0.6
+    - model: SillyTilly/mistralai_Mistral-Nemo-Instruct-2407
+      layer_range: [0, -1]
+      parameters:
+        weight: 0.7
+        density: 0.6
+tie_alpha: 0.3
+tie_norm: L2
+merge_verbose: true
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "SillyTilly/mistralai_Mistral-Nemo-Base-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": -1,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.1",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,22 @@
+base_model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+dtype: bfloat16
+merge_method: ties
+parameters:
+  normalize: true
+  int8_mask: true
+  lambda: 0.8
+slices:
+  - sources:
+    - model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
+      layer_range: [0, -1]
+      parameters:
+        weight: 1.0
+        density: 0.6
+    - model: SillyTilly/mistralai_Mistral-Nemo-Instruct-2407
+      layer_range: [0, -1]
+      parameters:
+        weight: 0.7
+        density: 0.6
+tie_alpha: 0.3
+tie_norm: L2
+merge_verbose: true

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9922c06872ffdb62d24543c3b7ffd3382fd6386fcf36fbfe785c41c5240288
+size 2684365128

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 2684364800}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}