feat!: v2025-01-02, Thai reasoning traces, improved Thai and instruction following performance

README.md

@@ -18,6 +18,10 @@ datasets:
 
 Typhoon T1 3B (Research Preview) is built on top of [Typhoon 2 3B Instruct](https://huggingface.co/scb10x/llama3.2-typhoon2-3b-instruct). It has improved performance on challenging benchmarks like GPQA, MMLU Pro, and AI Mathematics Olympiad validation set.
 
+> [!NOTE]
+> 🚀
+> **2025-02-01 Update**: We have released a new version of Typhoon T1 3B (Research Preview) with the ability to 🇹🇭 *generate Thai reasoning traces*, improved *Thai performance in general*, and *enhanced instruction following*. This version has the a comparative level of English performance to `v2025-01-23`.
+
 ## Key Points
 
 - **Typhoon T1** is a new family of open reasoning models developed by SCB 10X
@@ -25,6 +29,7 @@ Typhoon T1 3B (Research Preview) is built on top of [Typhoon 2 3B Instruct](http
 - Typhoon T1 3B (Research Preview) offers a **fast**, **low-compute requirements** model, yet is **capable** in a variety of tasks by scaling test-time compute, enabling the model to think longer before giving a final answer. Typhoon T1 3B (Research Preview) is able to **_reason across domains_**, unlike many open reasoning models limited to mathematics and coding
 - We **open** our recipe for data pipeline and training this model without distilling from other reasoning models
 - We introduce **a new thinking paradigm** for reasoning models, structured thinking, where we add auxiliary tokens to help structure the thinking process of the model. This approach shows an increase in performance over a common variant of separating only thought and response parts based on our experiments
+- Typhoon T1 3B (Research Preview) `v2025-02-01` is the first reasoning model where we intentionally equipped the model with the ability to **generate Thai reasoning traces**, improving *transparency* and *interpretability* of the model.
 
 For more technical details, please visit our [technical blog](https://blog.opentyphoon.ai/introducing-typhoon-t1-a-family-of-open-reasoning-models-research-preview-22daacc88662).
 
@@ -36,20 +41,20 @@ For more technical details, please visit our [technical blog](https://blog.opent
 |-----------------------|-------------------|-------------------------|----------------|----------|
 | Typhoon 2 3B Instruct | 56.63             | 66                      | 27.01          | 0        |
 | Typhoon T1 3B (semi)  | 59.59             | 68.99                   | 25.89          | 0        |
-| **Typhoon T1 3B (Research Preview)**     | **62.40**         | **69.87**               | **31.7**       | **2.22** |
+| **Typhoon T1 3B (Research Preview)** v2025-01-23     | **62.40**         | **69.87**               | **31.7**       | **2.22** |
 
 ### MMLU Pro (↑), 5-shot
 
 | Model name            | Average   | Math      | Health    | Physics  | Business  | Biology   | Chemistry | Computer Science | Economics | Engineering | Philosophy | Other     | History   | Psychology | Law       |
 |-----------------------|-----------|-----------|-----------|----------|-----------|-----------|-----------|------------------|-----------|-------------|------------|-----------|-----------|------------|-----------|
 | Typhoon 2 3B Instruct | 26.7      | 26.8      | 33.62     | 23.4     | 25.35     | 43.38     | 19.88     | 28.29            | 35.43     | 18.37       | 28.06      | 27.92     | 25.72     | 37.84      | 13.17     |
-| **Typhoon T1 3B (Research Preview)**     | **30.65** | **30.57** | **36.19** | **27.1** | **31.69** | **50.77** | **22.17** | **31.22**        | **38.86** | **21.98**   | **30.66**  | **32.79** | **26.51** | **43.36**  | **17.26** |
+| **Typhoon T1 3B (Research Preview)** v2025-01-23     | **30.65** | **30.57** | **36.19** | **27.1** | **31.69** | **50.77** | **22.17** | **31.22**        | **38.86** | **21.98**   | **30.66**  | **32.79** | **26.51** | **43.36**  | **17.26** |
 
 ## Model description
 
 - **Model type**: A 3B instruct decoder-only model based on Llama architecture.
-- **Requirement**: transformers 4.46.1 or newer.
-- **Primary Language(s)**: English 🇬🇧 and Thai 🇹🇭 (based on Typhoon 2 3B Instruct. However, most of long thought training data are in English.)
+- **Requirement**: `transformers` 4.46.1 or newer.
+- **Primary Language(s)**: English 🇬🇧 and Thai 🇹🇭
 - **License**: [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE)
 
 
@@ -62,12 +67,15 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
 model_id = "scb10x/llama-3.2-typhoon-t1-3b-research-preview"
+revision = "main" # To use the previous version comment this line
+# revision = "v2025-01-23" # To use the previous version uncomment this line
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     torch_dtype=torch.bfloat16,
     device_map="auto",
+    revision=revision
 )
 
 messages = [
@@ -102,6 +110,9 @@ print(tokenizer.decode(response, skip_special_tokens=True))
 ```bash
 pip install vllm
 vllm serve scb10x/llama-3.2-typhoon-t1-3b-research-preview
+
+# To serve the previous version, add the revision parameter as shown below
+# vllm serve scb10x/llama-3.2-typhoon-t1-3b-research-preview --revision v2025-01-23
 # see more information at https://docs.vllm.ai/
 ```
 

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7555738e2bd218624e81a572c518b6d206a768b059fcf9a521d0001151ac6ca
+oid sha256:ff07f295caaeedc3964f764dfac7fe37adcc145888e4236ccdb4b74e5798d098
 size 4965799096

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1548b68539213c1ab359dc86af228dd85501d06f72d11b5fffeab43374bd3879
+oid sha256:1a012b37e95cafcde00213a6ffc094aea909e392539f8a09872d3aa2437ad973
 size 1459729952

special_tokens_map.json

@@ -1,4 +1,20 @@
 {
+  "additional_special_tokens": [
+    {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": {
     "content": "<|begin_of_text|>",
     "lstrip": false,

tokenizer_config.json

@@ -2049,6 +2049,10 @@
       "special": true
     }
   },
+  "additional_special_tokens": [
+    "<|eot_id|>",
+    "<|eom_id|>"
+  ],
   "bos_token": "<|begin_of_text|>",
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\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 + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{{- system_message }}\n{%- if tools is not none %}\n    {{- \"\\n\" }}\n    {{- \"You are given a question and a set of possible functions. Based on the question, you will need to make one or more function/tool calls to achieve the purpose.\" }}\n    {{- \"If none of the function can be used, point it out. If the given question lacks the parameters required by the function, also point it out.\" }}\n    {{- \"You should only return the function call in tools call sections.\" }}\n    {{- \"If you decide to invoke any of the function(s), you MUST put it in the format of [Function(arguments1={{params_name1: params_value1,params_name2: params_value2, ...}},  name1=function_name1), Function(arguments2={{params}},  name2=function_name2) , ...]\"}}\n    {{- \"You SHOULD NOT include any other text in the response.\\nHere is a list of functions in JSON format that you can invoke.\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- \"<|eot_id|>\" }}\n\n\n{%- for message in messages %}\n    {%- if not (message.role == 'tool') %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif message.role == \"tool\" %}\n        {{- \"<|start_header_id|>tool<|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 %}",
   "clean_up_tokenization_spaces": true,