Upload folder using huggingface_hub

README.md

@@ -0,0 +1,40 @@
+---
+base_model:
+- nilq/lua-mistral-1L-tiny
+- nilq/mistral-1L-tiny
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# outputs
+
+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:
+* [nilq/lua-mistral-1L-tiny](https://huggingface.co/nilq/lua-mistral-1L-tiny)
+* [nilq/mistral-1L-tiny](https://huggingface.co/nilq/mistral-1L-tiny)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: nilq/lua-mistral-1L-tiny
+  - model: nilq/mistral-1L-tiny
+merge_method: slerp
+base_model: nilq/mistral-1L-tiny
+parameters:
+  t:
+    - value: 0.5
+dtype: float16
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "nilq/mistral-1L-tiny",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 2048,
+  "model_type": "mistral",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: nilq/lua-mistral-1L-tiny
+  - model: nilq/mistral-1L-tiny
+merge_method: slerp
+base_model: nilq/mistral-1L-tiny
+parameters:
+  t:
+    - value: 0.5
+dtype: float16

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98ee9d6d99187b1930d308e54c471a6da9f8cc5dadf48d4a17ec7581431d13c
+size 70258952

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1 @@
+{}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}