Upload folder using huggingface_hub

Llama-3.2-3B-COTv2.2-BF16.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f33810ea6aee3320f740f6ee9eafca837f1fb761643f4dffea0917beeab3879
-size 6433688640
+oid sha256:14f62673e18f033e54628c138aef5c7b58f57ad8411c1a51bd766a4b3009a856
+size 6433688608

Llama-3.2-3B-COTv2.2-F32.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf1e8ae4bc683b388d1a6f9b74bde514b401ab46179ccfddb436dd2b2d5e2cc
-size 12858838080
+oid sha256:9d6fb60eab52f0cd2d38241c8dd249825dbc950faf0c9bf2e959ab136089e8e2
+size 12858838048

Llama-3.2-3B-COTv2.2-Q4_K_M.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14fda3dd47211f5f8fcbf8cdc148e58cdd866cd7bc20df34e7dae5a217e878f9
-size 2019378240
+oid sha256:3e7751cd05a31fa44aaab3d3f65e6f8d331d276e597eb7a9f9bbf862c5e093b6
+size 2019378208

Llama-3.2-3B-COTv2.2-Q6_K.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f5c773b8a9404cfbade1cb369a70a5a7fbd5aa4af65782dea9bd9c8bd1bbd1
-size 2643854400
+oid sha256:7c0b9cd99bbfb18ee50481c5f622bb4bad3b13cef5eb49c0d6b17ccaa89e74f7
+size 2643854368

Llama-3.2-3B-COTv2.2-Q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2601bbcb54f09347afbd092b08fc0985a69d351635966e69d0c7e9752c8f6072
-size 3421899840
+oid sha256:7454e6280750b05c94c368942cd47369f8e77b8a1b96ed98dcb9e8146057e8f6
+size 3421899808

README.md

@@ -1,120 +1,51 @@
 ---
-license: apache-2.0
 base_model:
 - meta-llama/Llama-3.2-3B-Instruct
+- ericflo/Llama-3.2-3B-COTv2.1
+- ericflo/Llama-3.2-3B-MultiCOT
+- ericflo/Llama-3.2-3B-COTv2
 library_name: transformers
-datasets:
-- ericflo/Llama-3.2-3B-COT
----
-# Thought-Ranked Llama 3.2 3B v2.2
-
-## What's New in v2?
-
-The biggest improvement in v2 is how the model thinks through problems. Instead of just one level of thoughts, it can now explore up to 6 levels deep, building on its best ideas at each step. Think of it like having a conversation with yourself, where each new thought builds on your previous best insight.
-
-## How It Works
-
-Let's look at an example. When asked "What would happen if the moon disappeared?", the model might think:
-
-```
-<thoughts>
-<thought>First, I should consider the moon's main effects on Earth</thought>
-<thought>The moon controls our tides, so ocean patterns would change dramatically</thought>
-<thought>Without the moon's gravitational pull, Earth's rotation would become unstable</thought>
-<thought>This would lead to extreme climate changes and disrupted ecosystems</thought>
-<thought>The loss of moonlight would affect nocturnal animals and human culture</thought>
-<thought>Combining all these effects, we'd see a cascade of environmental changes</thought>
-</thoughts>
-
-The disappearance of the moon would have far-reaching consequences for Earth...
-[detailed answer follows]
-```
-
-### System Messages
-
-The model responds to different types of system prompts. Here are some examples:
-
-1. Basic prompt:
-```
-{"role": "system", "content": "You are a helpful assistant. Think before responding."}
-```
-
-2. Specific thought count:
-```
-{"role": "system", "content": "You are a helpful assistant. Think 3 thoughts before responding."}
-```
+tags:
+- mergekit
+- merge
 
-3. Standard helper:
-```
-{"role": "system", "content": "You are a helpful assistant."}
-```
-
-About 40% of training examples include system messages, and 75% of those specifically mention thinking. This helps the model learn when and how much to think through problems.
-
-## Technical Details
-
-- **Base Model**: Llama 3.2 3B
-- **Training Data**: 2,500 carefully selected examples, each with up to 6 levels of thought chains
-- **Thought Selection**: At each level, the model generates multiple possible thoughts and picks the best one using an external ranking system
-
-## What's It Good For?
-
-This model excels at tasks that benefit from careful thinking:
-
-✅ Breaking down complex problems
-✅ Step-by-step math solutions
-✅ Detailed analysis of situations
-✅ Explaining complicated concepts
-✅ Making well-reasoned decisions
-
-## Limitations
-
-- Can sometimes overthink simple problems
-- Limited by the capabilities of the base Llama 3.2 3B model
-- Not suitable for critical decisions without human oversight
-- May occasionally generate irrelevant thought chains
+---
+# Llama-3.2-3B-COTv2.2
 
-## Example Usage
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
+## Merge Details
+### Merge Method
 
-model = AutoModelForCausalLM.from_pretrained("ericflo/Llama-3.2-3B-COT-v2.2")
-tokenizer = AutoTokenizer.from_pretrained("ericflo/Llama-3.2-3B-COT-v2.2")
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
 
-messages = [
-    {"role": "system", "content": "You are a helpful assistant. Think 3 thoughts before responding."},
-    {"role": "user", "content": "How would you teach a child to ride a bike?"}
-]
+### Models Merged
 
-input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
-output = model.generate(input_ids, temperature=1.0)
-response = tokenizer.decode(output[0])
-```
+The following models were included in the merge:
+* [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
+* [ericflo/Llama-3.2-3B-COTv2.1](https://huggingface.co/ericflo/Llama-3.2-3B-COTv2.1)
+* [ericflo/Llama-3.2-3B-MultiCOT](https://huggingface.co/ericflo/Llama-3.2-3B-MultiCOT)
+* [ericflo/Llama-3.2-3B-COTv2](https://huggingface.co/ericflo/Llama-3.2-3B-COTv2)
 
-Example output:
-```
-<thoughts>
-<thought>Safety should be the first priority - helmet and protective gear</thought>
-<thought>Starting with balance using training wheels can build confidence</thought>
-<thought>Breaking the process into small, manageable steps will help avoid overwhelm</thought>
-</thoughts>
+### Configuration
 
-Here's how I would teach a child to ride a bike...
-[detailed answer follows]
-```
+The following YAML configuration was used to produce this model:
 
-## Citation
+```yaml
+models:
+  - model: meta-llama/Llama-3.2-3B-Instruct
+    parameters:
+      weight: 0.4
+  - model: ericflo/Llama-3.2-3B-COTv2
+    parameters:
+      weight: 1.0
+  - model: ericflo/Llama-3.2-3B-COTv2.1
+    parameters:
+      weight: 0.4
+  - model: ericflo/Llama-3.2-3B-MultiCOT
+    parameters:
+      weight: 0.3
+merge_method: linear
+dtype: bfloat16
 
-```bibtex
-@misc{thought-ranked-llama-v2,
-  title={Thought-Ranked Llama 3.2 v2: Hierarchical Chain-of-Thought Generation},
-  author={[Eric Florenzano]},
-  year={2024},
-  howpublished={\url{https://huggingface.co/ericflo/Llama-3.2-3B-COT-v2}}
-}
 ```
-
-## Acknowledgments
-
-This model builds on the Llama 3.2 3B base model from Meta. Special thanks to the open-source AI community for their contributions to chain-of-thought prompting techniques.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ericflo/Llama-3.2-3B-MultiCOT",
+  "_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],

mergekit_config.yml

@@ -1,10 +1,10 @@
 models:
   - model: meta-llama/Llama-3.2-3B-Instruct
     parameters:
-      weight: 0.8
+      weight: 0.4
   - model: ericflo/Llama-3.2-3B-COTv2
     parameters:
-      weight: 0.8
+      weight: 1.0
   - model: ericflo/Llama-3.2-3B-COTv2.1
     parameters:
       weight: 0.4
@@ -12,4 +12,4 @@ models:
     parameters:
       weight: 0.3
 merge_method: linear
-dtype: bfloat16
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f078491908393f4a65b2a90de0ee42204062c634525a793e3ede365dee504b80
+oid sha256:4119e662a63df2f38d5d30442fae0efe2acd13affee46fd9aebdf77d02f6fa8a
 size 4990977384

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a109c1c8571647be64d304a73aac48836e9d92d87b691cc9e8807bfd014fb26
+oid sha256:99d363d12652ec3e6f2bf698d316cc26d7dd3418a4de26c6e55450e4aa972961
 size 1434551664

special_tokens_map.json

@@ -12,12 +12,5 @@
     "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:e9c4b74af81ca7d09faa23cc737405515f00d04de25d9ea1908153684b67d1c0
-size 17210020
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2053,15 +2053,10 @@
   "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": 16384,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|eot_id|>",
-  "stride": 0,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }