Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+base_model:
+- Jiayi-Pan/Tiny-Vicuna-1B
+- yihanwang617/tinyllama-sft-vicuna-random-100k
+- QuixiAI/TinyDolphin-2.8.2-1.1b
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- NickyNicky/cognitivecomputations_TinyDolphin-2.8-1.1b
+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 [Linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Jiayi-Pan/Tiny-Vicuna-1B](https://huggingface.co/Jiayi-Pan/Tiny-Vicuna-1B)
+* [yihanwang617/tinyllama-sft-vicuna-random-100k](https://huggingface.co/yihanwang617/tinyllama-sft-vicuna-random-100k)
+* [QuixiAI/TinyDolphin-2.8.2-1.1b](https://huggingface.co/QuixiAI/TinyDolphin-2.8.2-1.1b)
+* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
+* [NickyNicky/cognitivecomputations_TinyDolphin-2.8-1.1b](https://huggingface.co/NickyNicky/cognitivecomputations_TinyDolphin-2.8-1.1b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Jiayi-Pan/Tiny-Vicuna-1B
+    parameters:
+      weight: 0.2
+  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    parameters:
+      weight: 0.2
+  - model: yihanwang617/tinyllama-sft-vicuna-random-100k
+    parameters:
+      weight: 0.2
+  - model: NickyNicky/cognitivecomputations_TinyDolphin-2.8-1.1b
+    parameters:
+      weight: 0.2
+  - model: QuixiAI/TinyDolphin-2.8.2-1.1b
+    parameters:
+      weight: 0.2
+merge_method: linear
+dtype: float32
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,18 @@
+models:
+  - model: Jiayi-Pan/Tiny-Vicuna-1B
+    parameters:
+      weight: 0.2
+  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    parameters:
+      weight: 0.2
+  - model: yihanwang617/tinyllama-sft-vicuna-random-100k
+    parameters:
+      weight: 0.2
+  - model: NickyNicky/cognitivecomputations_TinyDolphin-2.8-1.1b
+    parameters:
+      weight: 0.2
+  - model: QuixiAI/TinyDolphin-2.8.2-1.1b
+    parameters:
+      weight: 0.2
+merge_method: linear
+dtype: float32

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cafeeb941a1e5de4c2a9d45d8248dabe5ac865ae3c143225ac5327be74545a4
+size 4400216536

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": "<unk>",
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}