Upload folder using huggingface_hub

README.md

@@ -1,10 +1,10 @@
 ---
 base_model:
-- bunnycore/Llama-3.2-3B-ProdigyPlusPlus
 - huihui-ai/Llama-3.2-3B-Instruct-abliterated
-- chuanli11/Llama-3.2-3B-Instruct-uncensored
 - meta-llama/Llama-3.2-3B-Instruct
+- chuanli11/Llama-3.2-3B-Instruct-uncensored
 - meta-llama/Llama-3.2-3B
+- bunnycore/Llama-3.2-3B-ProdigyPlusPlus
 library_name: transformers
 tags:
 - mergekit
@@ -18,14 +18,14 @@ 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 [chuanli11/Llama-3.2-3B-Instruct-uncensored](https://huggingface.co/chuanli11/Llama-3.2-3B-Instruct-uncensored) 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 [bunnycore/Llama-3.2-3B-ProdigyPlusPlus](https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlusPlus) as a base.
 
 ### Models Merged
 
 The following models were included in the merge:
-* [bunnycore/Llama-3.2-3B-ProdigyPlusPlus](https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlusPlus)
 * [huihui-ai/Llama-3.2-3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated)
 * [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
+* [chuanli11/Llama-3.2-3B-Instruct-uncensored](https://huggingface.co/chuanli11/Llama-3.2-3B-Instruct-uncensored)
 * [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)
 
 ### Configuration
@@ -34,72 +34,23 @@ The following YAML configuration was used to produce this model:
 
 ```yaml
 base_model:
-  model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-layer_range:
-- 0
-- 28
-merge_method: ties
+  model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
+dtype: float16
+merge_method: dare_ties
 merge_method_sequence:
 - dare_ties
 - ties
+models:
+- model: meta-llama/Llama-3.2-3B-Instruct
+- model: meta-llama/Llama-3.2-3B
+- model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
+- model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
+- model: chuanli11/Llama-3.2-3B-Instruct-uncensored
 parameters:
-  batch_size: 32
   density: 0.5
   int8_mask: true
-  layer_range:
-  - 0
-  - 28
-  model.embed_tokens.weight.t: 1.0
   normalize: false
-  t:
-  - filter: self_attn
-    value:
-    - 0
-    - 0.5
-    - 0.3
-    - 0.7
-    - 1
-  - filter: mlp
-    value:
-    - 1
-    - 0.5
-    - 0.7
-    - 0.3
-    - 0
-  - value: 0.5
   weight: 0.5
-slices:
-- sources:
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: meta-llama/Llama-3.2-3B-Instruct
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: meta-llama/Llama-3.2-3B
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
-    weight: 0.5
 tokenizer_source: union
 
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "chuanli11/Llama-3.2-3B-Instruct-uncensored",
+  "_name_or_path": "bunnycore/Llama-3.2-3B-ProdigyPlusPlus",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -33,7 +33,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 128256

mergekit_config.yml

@@ -1,68 +1,19 @@
 base_model:
-  model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-layer_range:
-- 0
-- 28
-merge_method: ties
+  model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
+dtype: float16
+merge_method: dare_ties
 merge_method_sequence:
 - dare_ties
 - ties
+models:
+- model: meta-llama/Llama-3.2-3B-Instruct
+- model: meta-llama/Llama-3.2-3B
+- model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
+- model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
+- model: chuanli11/Llama-3.2-3B-Instruct-uncensored
 parameters:
-  batch_size: 32
   density: 0.5
   int8_mask: true
-  layer_range:
-  - 0
-  - 28
-  model.embed_tokens.weight.t: 1.0
   normalize: false
-  t:
-  - filter: self_attn
-    value:
-    - 0
-    - 0.5
-    - 0.3
-    - 0.7
-    - 1
-  - filter: mlp
-    value:
-    - 1
-    - 0.5
-    - 0.7
-    - 0.3
-    - 0
-  - value: 0.5
   weight: 0.5
-slices:
-- sources:
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: meta-llama/Llama-3.2-3B-Instruct
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: meta-llama/Llama-3.2-3B
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: chuanli11/Llama-3.2-3B-Instruct-uncensored
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
-    weight: 0.5
-  - density: 0.5
-    layer_range:
-    - 0
-    - 28
-    model: bunnycore/Llama-3.2-3B-ProdigyPlusPlus
-    weight: 0.5
 tokenizer_source: union

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f7de1dd4d1c949758eb83255f3bfdbae8d108cef7c956d784822f2e53671f4
-size 4998794944
+oid sha256:866455a0ace665a9134bb7ee83c04d47aee612e8c565a07098d1517f22539580
+size 4998794808

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b20e109c5d1a0f6c42f1b2d003432b4687bc2cd0844225e13d2436e29af335
-size 2214739072
+oid sha256:b7de1213796b137872b5bee15617d3cb6d175b112f07d3c5c95bc4fc077dedf6
+size 2214738976

special_tokens_map.json

@@ -12,5 +12,12 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
   }
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
-size 17209920
+oid sha256:65ff5472d095ccd9332d9e723153d7bc7226cb6be9c1bffda738b5ba2e71bf26
+size 17210084

tokenizer_config.json

@@ -2053,10 +2053,15 @@
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
+  "max_length": null,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|eot_id|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }