Upload folder using huggingface_hub

README.md

@@ -8,9 +8,6 @@ tags:
 - merge
 
 ---
-# Models in the ChickaQ family
-- **ChickaQ (0.6B)**
-- **ChickaQ-Large (1.8B)**
 # mergedmodel
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
@@ -18,12 +15,12 @@ This is a merge of pre-trained language models created using [mergekit](https://
 ## Merge Details
 ### Merge Method
 
-This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [vilm/Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1) as a base.
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) as a base.
 
 ### Models Merged
 
 The following models were included in the merge:
-* [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat)
+* [vilm/Quyen-SE-v0.1](https://huggingface.co/vilm/Quyen-SE-v0.1)
 
 ### Configuration
 
@@ -31,16 +28,15 @@ The following YAML configuration was used to produce this model:
 
 ```yaml
 models:
-  - model: vilm/Quyen-SE-v0.1
-    # no parameters necessary for base model
   - model: Qwen/Qwen1.5-0.5B-Chat
+    # no parameters necessary for base model
+  - model: vilm/Quyen-SE-v0.1
     parameters:
-      density: 0.5
-      weight: 0.5
-merge_method: ties
-base_model: vilm/Quyen-SE-v0.1
+      density: 1
+      weight: 1
+merge_method: dare_ties
+base_model: Qwen/Qwen1.5-0.5B-Chat
 parameters:
   normalize: true
 dtype: float16
-
 ```

config.json

@@ -1,9 +1,10 @@
 {
-  "_name_or_path": "vilm/Quyen-SE-v0.1",
+  "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
+  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "hidden_act": "silu",
   "hidden_size": 1024,
@@ -17,11 +18,11 @@
   "num_key_value_heads": 16,
   "rms_norm_eps": 1e-06,
   "rope_theta": 1000000.0,
-  "sliding_window": 4096,
-  "tie_word_embeddings": false,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
   "torch_dtype": "float16",
   "transformers_version": "4.38.2",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

mergekit_config.yml

@@ -1,12 +1,12 @@
 models:
-  - model: vilm/Quyen-SE-v0.1
-    # no parameters necessary for base model
   - model: Qwen/Qwen1.5-0.5B-Chat
+    # no parameters necessary for base model
+  - model: vilm/Quyen-SE-v0.1
     parameters:
-      density: 0.5
-      weight: 0.5
-merge_method: ties
-base_model: vilm/Quyen-SE-v0.1
+      density: 1
+      weight: 1
+merge_method: dare_ties
+base_model: Qwen/Qwen1.5-0.5B-Chat
 parameters:
   normalize: true
-dtype: float16
+dtype: float16

model-00001-of-00001.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eece92273f353f4b9563464043b2653ab2ef2f7222ee6cff0a3165c1aefbc95a
+oid sha256:0de001be263c6e862f27a4645edb9276c1c9731173448d92a48bb26697c96877
 size 1239173056

special_tokens_map.json

@@ -3,13 +3,6 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "eos_token": {
     "content": "<|im_end|>",
     "lstrip": false,

tokenizer_config.json

@@ -30,8 +30,8 @@
     "<|im_start|>",
     "<|im_end|>"
   ],
-  "bos_token": "<|im_end|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",