Training in progress, step 48

README.md

@@ -1,3 +1,58 @@
----
-license: apache-2.0
----
+---
+base_model: meta-llama/Llama-3.2-1B-Instruct
+library_name: transformers
+model_name: ZFusionAI_Hacker
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for ZFusionAI_Hacker
+
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct).
+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="GTKING/ZFusionAI_Hacker", 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/gamingking9025-muthayammal-college-of-engineering/huggingface/runs/ajpft44z) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.26.2
+- Transformers: 4.57.1
+- Pytorch: 2.8.0+cu126
+- Datasets: 4.4.1
+- Tokenizers: 0.22.1
+
+## 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 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

chat_template.jinja

@@ -1,73 +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 %}
 
-{# --- Extract system message if present --- #}
-{%- if messages and messages[0]['role'] == 'system' %}
-    {%- set system_message = messages[0]['content'] | trim %}
+{#- 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 block (minimal) --- #}
-{{- "<|start_header_id|>system<|end_header_id|>
-
-" }}
+{#- 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|>" }}
 
-{# --- Optional tool definitions (in user message) --- #}
-{%- if tools is defined and tools is not none %}
-    {%- set first_user = messages[0]['content'] | trim %}
-    {%- set messages = messages[1:] %}
-
-    {{- "<|start_header_id|>user<|end_header_id|>
-
-" }}
-    {{- "You have access to the following functions.
-" }}
-    {{- "Respond ONLY with a JSON function call.
-
-" }}
-
+{#- 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=2) }}
-        {{- "
-
-" }}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
     {%- endfor %}
-
-    {{- first_user }}
-    {{- "<|eot_id|>" }}
+    {{- first_user_message + "<|eot_id|>"}}
 {%- endif %}
 
-{# --- Remaining messages --- #}
 {%- for message in messages %}
-    {%- if message.role in ["user", "assistant"] %}
-        {{- "<|start_header_id|>" + message.role + "<|end_header_id|>
-
-" }}
-        {{- message.content | trim }}
-        {{- "<|eot_id|>" }}
-    {%- elif "tool_calls" in message %}
-        {%- set call = message.tool_calls[0].function %}
-        {{- "<|start_header_id|>assistant<|end_header_id|>
-
-" }}
-        {{- '{"name": "' + call.name + '", "parameters": ' + (call.arguments | tojson) + '}' }}
+    {%- 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" %}
-        {{- "<|start_header_id|>tool<|end_header_id|>
-
-" }}
-        {{- message.content }}
+    {%- 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 %}
-
-{# --- Generation prompt --- #}
 {%- if add_generation_prompt %}
-    {{- "<|start_header_id|>assistant<|end_header_id|>
-
-" }}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
 {%- endif %}

special_tokens_map.json

@@ -12,6 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": "<|eot_id|>"
+  }
 }

tokenizer_config.json

@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }