TymofiiNasobko/Mamay-function-calling-no-thinking

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0
+library_name: transformers
+model_name: Mamay-function-calling-no-thinking
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for Mamay-function-calling-no-thinking
+
+This model is a fine-tuned version of [INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0](https://huggingface.co/INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="TymofiiNasobko/Mamay-function-calling-no-thinking", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.26.2
+- Transformers: 4.57.4
+- Pytorch: 2.9.0+cu126
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "INSAIT-Institute/MamayLM-Gemma-3-4B-IT-v1.0",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "fc2",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "fc1",
+    "o_proj",
+    "q_proj",
+    "out_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe142e44fb0c5f04f5fcfebd4e31e023d37f9242352f5fb3977351665dc2b4d4
+size 154117112

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,113 @@
+{{ bos_token }}
+{%- if tools -%}
+{%- set loop_messages = messages[1:] -%}
+	{{- '<start_of_turn>' + 'system' + '
+' -}}
+	{%- if messages[0]['role'] == "system" -%}
+        {%- if messages[0]['content'] is string -%}
+		    {{- messages[0]['content'] + '
+' + '
+' -}}
+        {%- else -%}
+            {{- messages[0]['content'][0]['text'] + '
+' + '
+' -}}
+        {%- endif -%}
+    {%- endif -%}
+	{{- "# Tools
+
+You may call one or more functions to assist with the user query.
+
+You are provided with function signatures within <tools></tools> XML tags:
+<tools>" -}}
+	{%- for tool in tools -%}
+		{{- "
+" -}}
+		{{- tool | tojson -}}
+	{%- endfor -%}
+    {{- '<end_of_turn>' + '
+' -}}
+{%- elif messages[0]['role'] == "system" -%}
+{%- set loop_messages = messages[1:] -%}
+	{{- '<start_of_turn>' + 'system' + '
+' -}}
+    {%- if messages[0]['content'] is string -%}
+        {{- messages[0]['content'] -}}
+    {%- else -%}
+        {{- messages[0]['content'][0]['text'] -}}
+    {%- endif -%}
+    {{- '<end_of_turn>
+' }}
+{%- else -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if message['role'] == 'assistant' or message['role'] == 'model' -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' }}
+    {%- if message['content'] is string -%}
+        {%- if role == "model" -%}
+{% generation %}
+{{- message['content'] | trim -}}
+{% if message['tool_calls'] %}
+    {% for tool_call in message['tool_calls'] %}
+        {% if tool_call['function'] is defined %}
+            {% set tool_call = tool_call['function'] %}
+        {% endif %}
+{{- "
+" -}}
+<tool_call>
+{"name": "{{ tool_call['name'] }}", "arguments": {{ tool_call['arguments'] | tojson }}}
+</tool_call>
+    {%- endfor -%}
+{%- endif -%}
+{% endgeneration %}
+        {%- else -%}
+            {{ message['content'] | trim }}
+        {%- endif -%}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {%- if role == "model" -%}
+{% generation %}
+{{- item['text'] | trim -}}
+{% if message['tool_calls'] %}
+    {% for tool_call in message['tool_calls'] %}
+        {% if tool_call['function'] is defined %}
+            {% set tool_call = tool_call['function'] %}
+        {% endif %}
+{{- "
+" -}}
+<tool_call>
+{"name": "{{ tool_call['name'] }}", "arguments": {{ tool_call['arguments'] | tojson }}}
+</tool_call>
+    {%- endfor -%}
+{%- endif -%}
+{% endgeneration %}
+                {%- else -%}
+                    {{ item['text'] | trim }}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+{%- if role == "model" -%}
+{% generation %}
+{{ '<end_of_turn>
+' }}{% endgeneration %}
+{%- else -%}
+{{ '<end_of_turn>
+' }}
+{%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<end_of_turn>",
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e951d7a26ab64624a9411db3f91fdab169318cdd66e3cbaaa5b2195bd87981f4
+size 6289