Training in progress, step 200

.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 +1,59 @@
+---
+base_model: igorktech/gemma-3n-e2b-it-language-pruned-v2
+library_name: transformers
+model_name: Custom
+tags:
+- generated_from_trainer
+- sft
+- trl
+- unsloth
+licence: license
+---
+
+# Model Card for Custom
+
+This model is a fine-tuned version of [igorktech/gemma-3n-e2b-it-language-pruned-v2](https://huggingface.co/igorktech/gemma-3n-e2b-it-language-pruned-v2).
+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="igorktech/Custom", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/igorktech01/huggingface/runs/qhc20kr6) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.21.0
+- Transformers: 4.55.0
+- Pytorch: 2.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## 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 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "igorktech/gemma-3n-e2b-it-language-pruned-v2",
+  "bias": "none",
+  "corda_config": null,
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2)))",
+  "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 sha256:20d46d7e9402d845ad7553f4f4ec7ee8f5e690282066eb4a0882ea9fdbc980e5
+size 236755440

chat_template.jinja

@@ -0,0 +1,125 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = '' -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{# Inject tools definitions here if available #}
+{%- if tools -%}
+  {#– Serialize all tools into one JSON blob, separated by newlines –#}
+  {%- set tools_json = tools | map('tojson') | join('
+') -%}
+  {#– Append the entire block to first_user_prefix in one go –#}
+  {%- set first_user_prefix = first_user_prefix
+       ~ "# Tools
+
+"
+       ~ "You may call one or more functions to assist with the user query.
+
+"
+       ~ "You are provided with function signatures within `<tools>` XML tags:
+"
+       ~ "<tools>
+"
+       ~ tools_json
+       ~ "
+</tools>
+
+"
+       ~ "For each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:
+"
+       ~ "<tool_call>
+"
+       ~ '{"name": <function-name>, "arguments": <args-json-object>}'
+       ~ "
+</tool_call>
+
+"
+  -%}
+{%- endif -%}
+
+{# Identify where to insert optional tool segments #}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=loop_messages|length - 1) -%}
+{%- for msg in loop_messages[::-1] -%}
+    {%- set idx = (loop_messages|length - 1) - loop.index0 -%}
+    {%- if ns.multi_step_tool and msg['role']=='user' and msg['content'] is string and not (msg['content'].startswith('<tool_response>') and msg['content'].endswith('</tool_response>')) -%}
+        {%- set ns.multi_step_tool = false -%}
+        {%- set ns.last_query_index = idx -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{# Render each message turn #}
+{%- for message in loop_messages -%}
+  {%- set role = "model" if message.role == 'assistant' else message.role -%}
+  {{ '<start_of_turn>' ~ role ~ "
+" ~ (first_user_prefix if loop.first else "") -}}
+  {%- if message.content is string -%}
+    {%- set content = message.content -%}
+  {%- elif message.content is iterable -%}
+    {%- set content = '' -%}
+    {%- for item in message.content -%}
+      {%- if item.type == 'text' -%}
+        {%- set content = content + item.text -%}
+      {%- elif item.type == 'image' -%}
+        {%- set content = content + '<image_soft_token>' -%}
+      {%- elif item.type == 'audio' -%}
+        {%- set content = content + '<audio_soft_token>' -%}
+      {%- endif -%}
+    {%- endfor -%}
+  {%- else -%}
+    {{ raise_exception("Invalid content type: " ~ message.role) }}
+  {%- endif -%}
+
+  {# Render by role #}
+  {%- if message.role == 'tool' -%}
+    {{ '<tool_response>
+' + content + '
+</tool_response>' }}
+  {%- elif message.role == 'assistant' -%}
+    {{ content }}
+    {# Append any tool_calls #}
+    {%- if message.tool_calls -%}
+      {%- for tool_call in message.tool_calls -%}
+        {%- if (loop.first and content) or (not loop.first) -%}
+            {{- '
+' }}
+        {%- endif -%}
+        {%- if tool_call.function -%}
+            {%- set tool_call = tool_call.function -%}
+        {%- endif -%}
+        {{- '<tool_call>
+{"name": "' }}
+        {{- tool_call.name }}
+        {{- '", "arguments": ' }}
+        {%- if tool_call.arguments is string -%}
+            {{- tool_call.arguments }}
+        {%- else -%}
+            {{- tool_call.arguments | tojson }}
+        {%- endif -%}
+        {{- '}
+</tool_call>' }}
+      {%- endfor -%}
+    {%- endif -%}
+  {%- else -%}
+    {{ content }}
+  {%- endif -%}
+  {{ '<end_of_turn>
+' }}
+
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {{ '<start_of_turn>model
+' }}
+{%- endif -%}

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "audio_token": "<audio_soft_token>",
+  "boa_token": "<start_of_audio>",
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoa_token": "<end_of_audio>",
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:b6c35ee648c07754b44cd9e371c75d4caa05c4504910b7ad29b1847ee9d8ba5d
+size 33442553

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a42fca01906dffcf28cbfe9dcf32e6e3cbff4c0efa29b2b10d991a854baba88b
+size 5752