Training in progress, step 100

.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: swiss-ai/Apertus-8B-Instruct-2509
+library_name: transformers
+model_name: apertus-8b-coding
+tags:
+- generated_from_trainer
+- hf_jobs
+- sft
+- trl
+licence: license
+---
+
+# Model Card for apertus-8b-coding
+
+This model is a fine-tuned version of [swiss-ai/Apertus-8B-Instruct-2509](https://huggingface.co/swiss-ai/Apertus-8B-Instruct-2509).
+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="Colby/apertus-8b-coding", 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: 1.4.0
+- Transformers: 5.8.0
+- Pytorch: 2.11.0
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,47 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "swiss-ai/Apertus-8B-Instruct-2509",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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 sha256:480e454a9e4359d40506048a2374c9089f0be48c84a72dcc40257150a087f546
+size 79743368

chat_template.jinja

@@ -0,0 +1,337 @@
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tools(tools) -%}
+    {%- for tool in tools %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- "\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;" }}
+        {%- else -%}
+            {{- "() => any;" }}
+        {%- endif -%}
+        {%- if not loop.last -%}
+            {{- "\n" }}
+        {%- endif -%}
+    {%- endfor %}
+{%- endmacro -%}
+
+{{ bos_token }}
+
+{%- set system_token = '<|system_start|>' -%}
+{%- set end_system_token = '<|system_end|>' -%}
+{%- set developer_token = '<|developer_start|>' -%}
+{%- set end_developer_token = '<|developer_end|>' -%}
+{%- set user_token = '<|user_start|>' -%}
+{%- set end_user_token = '<|user_end|>' -%}
+{%- set assistant_token = '<|assistant_start|>' -%}
+{%- set end_assistant_token = '<|assistant_end|>' -%}
+{%- set inner_token = '<|inner_prefix|>' -%}
+{%- set outer_token = '<|inner_suffix|>' -%}
+{%- set tool_calls_token = '<|tools_prefix|>' -%}
+{%- set end_tool_calls_token = '<|tools_suffix|>' -%}
+{%- set image_token = '<|image|>' -%}
+
+{%- set ns = namespace(in_assistant=false, in_tool=false, in_inner=false, waiting_for_tool_outputs=false, assistant_format=none) -%}
+
+{%- if messages and messages[0].role == 'system' -%}
+    {%- if "content" in messages[0] -%}
+        {%- if messages[0].content is string -%}
+            {{ system_token + messages[0].content + end_system_token }}
+        {%- elif messages[0].content is mapping and "text" in messages[0].content -%}
+            {{ system_token + messages[0].content.text + end_system_token }}
+        {%- else -%}
+            {{- raise_exception("Invalid system message") -}}
+        {%- endif -%}
+    {%- else -%}
+        {{- raise_exception("Invalid system message") -}}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {{ system_token + 'You are Apertus, a helpful assistant created by the SwissAI initiative.\nKnowledge cutoff: 2024-04\nCurrent date: ' + strftime_now('%Y-%m-%d') + end_system_token }}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{{ developer_token + 'Deliberation: ' }}
+{%- if enable_thinking is defined and enable_thinking -%}
+    {{ 'enabled\n' }}
+{%- else -%}
+    {{ 'disabled\n' }}
+{%- endif -%}
+{%- if tools is defined and tools -%}
+    {{ 'Tool Capabilities:\n' + render_tools(tools) }}
+{%- else -%}
+    {{ 'Tool Capabilities: disabled' }}
+{%- endif -%}
+{{ end_developer_token }}
+
+{%- for message in loop_messages -%}
+    {%- if message.role == 'user' -%}
+        {%- set ns.in_inner = false -%}
+        {%- if ns.in_tool -%}
+            {{ ']' }}
+            {%- set ns.in_tool = false -%}
+        {%- endif -%}
+        {%- if ns.in_assistant -%}
+            {{ end_assistant_token }}
+            {%- set ns.in_assistant = false -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {{ user_token }}
+            {%- if message.content is string -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "parts" in message.content -%}
+                {%- set parts = message.content.parts -%}
+                {%- for part in parts -%}
+                    {%- if part.type == "text" -%}
+                        {{ part.text }}
+                    {%- elif part.type == "image" -%}
+                        {{ image_token }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid user part: " + part.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid user message: " + message.role) -}}
+            {%- endif -%}
+            {{ end_user_token }}
+        {%- endif -%}
+    {%- elif message.role == 'assistant' -%}
+        {%- if not ns.in_assistant -%}
+            {{ assistant_token }}
+            {%- set ns.in_assistant = true -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {%- if message.content is string and (ns.assistant_format is none or ns.assistant_format == "string") -%}
+                {%- if ns.in_tool -%}
+                    {{ ']' }}
+                    {%- set ns.in_tool = false -%}
+                {%- endif -%}
+                {%- set ns.assistant_format = "string" -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "blocks" in message.content and (ns.assistant_format is none or ns.assistant_format == "mapping") -%}
+                {%- set ns.assistant_format = "mapping" -%}
+                {%- set blocks = message.content.blocks -%}
+                {%- for block in blocks -%}
+                    {%- if block.type == 'thoughts' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if not ns.in_inner -%}
+                            {%- set ns.in_inner = true -%}
+                            {{ inner_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- elif block.type == 'tool_calls' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ tool_calls_token + '[' }}
+                        {%- for tool_call in block.calls -%}
+                            {{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{ ']' + end_tool_calls_token }}
+                        {%- set ns.waiting_for_tool_outputs = true -%}
+                    {%- elif block.type == 'tool_outputs' -%}
+                        {%- if ns.in_tool -%}
+                            {{- raise_exception("Cannot have both tool outputs as separate messages and tool outputs as blocks") -}}
+                        {%- endif -%}
+                        {{ '[' }}
+                        {%- for tool_output in block.outputs -%}
+                            {{- tool_output.output }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{- ']' }}
+                        {%- set ns.waiting_for_tool_outputs = false -%}
+                    {%- elif block.type == 'response' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if (not loop.first and ns.in_inner) or (ns.in_assistant and ns.in_inner) -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid assistant block type: " + block.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid assistant content") -}}
+            {%- endif -%}
+        {%- else -%}
+            {{- raise_exception("Invalid assistant message") -}}
+        {%- endif -%}
+        {%- if "tool_calls" in message and message.tool_calls -%}
+            {{ tool_calls_token + '[' }}
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.type == 'function' -%}
+                    {%- set function = tool_call.function -%}
+                    {{- '{"' + function.name + '": ' + function.arguments + '}' }}
+                    {%- if not loop.last -%}
+                        {{- ", " }}
+                    {%- endif -%}
+                {%- else -%}
+                    {{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
+                {%- endif -%}
+            {%- endfor -%}
+            {{ ']' + end_tool_calls_token }}
+            {%- set ns.waiting_for_tool_outputs = true -%}
+        {%- endif -%}
+    {%- elif message.role == 'tool' -%}
+        {%- if not ns.in_assistant -%}
+            {{- raise_exception("Tool message outside of assistant") -}}
+        {%- endif -%}
+        {%- if not ns.in_tool -%}
+            {{ '[' }}
+            {%- set ns.in_tool = true -%}
+        {%- else -%}
+            {{ ", "}}
+        {%- endif -%}
+        {{ message.content }}
+        {%- set ns.waiting_for_tool_outputs = false -%}
+    {%- else -%}
+        {{- raise_exception("Invalid message role") -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if ns.in_tool -%}
+    {{ ']' }}
+{%- endif -%}
+{%- if ns.in_assistant and not (continue_assistant_message is defined and continue_assistant_message) and not ns.waiting_for_tool_outputs -%}
+    {{ end_assistant_token }}
+{%- endif -%}
+{%- if add_generation_prompt -%}
+    {{ assistant_token }}
+{%- endif -%}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010095abf1dc6f52d4867584e7b3f0d4eece854593ae310220ec7782dd1b0a66
+size 17078474

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|assistant_end|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f230a64cbc9ab0f91d8fdca49204b16492c3164617d23a4702ced85012cf8a4
+size 5713