Upload folder using huggingface_hub

README.md

@@ -1,78 +0,0 @@
----
-license: llama3.2
-language:
-  - fr
-base_model: meta-llama/Llama-3.2-1B-Instruct
-tags:
-  - transformers.js
-  - onnx
-  - llama
-  - healthcare
-  - french
-  - quebec
-  - chatbot
-library_name: transformers
-pipeline_tag: text-generation
----
-
-# IntelliSoins Chatbot - Llama 3.2 1B Fine-tuned
-
-Modèle Llama 3.2-1B-Instruct fine-tuné avec LoRA pour le domaine de la santé au Québec.
-
-## Description
-
-Ce modèle a été fine-tuné par [IntelliSoins](https://www.intellisoins.ca) pour répondre aux questions sur:
-- Les services IntelliSoins
-- Les scribes IA médicaux
-- L'intelligence artificielle en santé au Québec
-- Les événements et conférences sur l'IA en santé
-
-## Utilisation avec Transformers.js
-
-```javascript
-import { pipeline } from '@huggingface/transformers';
-
-const generator = await pipeline(
-  'text-generation',
-  'IntelliSoins/intellisoins-chatbot',
-  { device: 'webgpu' }
-);
-
-const messages = [
-  { role: 'system', content: 'Tu es un assistant spécialisé en IA santé au Québec.' },
-  { role: 'user', content: 'Qu\'est-ce qu\'un scribe IA médical?' }
-];
-
-const result = await generator(messages, {
-  max_new_tokens: 256,
-  temperature: 0.7,
-});
-
-console.log(result[0].generated_text);
-```
-
-## Spécifications techniques
-
-- **Modèle de base**: meta-llama/Llama-3.2-1B-Instruct
-- **Méthode de fine-tuning**: LoRA (rank=8, alpha=20)
-- **Format**: ONNX quantifié INT8
-- **Taille**: ~1.2 GB
-- **Langue**: Français (Québec)
-
-## Entraînement
-
-Fine-tuné avec MLX sur Apple Silicon, puis converti en ONNX pour compatibilité navigateur.
-
-- **Framework**: MLX + PEFT
-- **Données**: Q&A sur IntelliSoins et l'IA en santé
-- **Époques**: 500 itérations
-- **Learning rate**: 1e-5
-
-## Licence
-
-Ce modèle est basé sur Llama 3.2 et est soumis à la [licence Llama 3.2](https://www.llama.com/llama3_2/license/).
-
-## Contact
-
-- Site web: [intellisoins.ca](https://www.intellisoins.ca)
-- Développé par Michael Ahern, Pharm.B.

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- if tools is not none and not tools_in_user_message %}
+    {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+{%- endif %}
+{{- system_message }}
+{{- "<|eot_id|>" }}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -32,8 +32,8 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.55.4",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

onnx/model_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffb42964d01c2fb00a72c5090d25dd8cd799dd8a3e48fed39895cf33ecf64d
-size 1237011221
+oid sha256:527b371a239da23afeeb2994f7d192874ff8e01391b0b7b85c26ee2adb719406
+size 1499811929