Upload Qwen3.5-2B ShellCommand-Linux LoRA

.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 +1,41 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+tags:
+- lora
+- qwen
+- bash
+- shell
+- linux
+- text-generation
+---
+
+# Qwen3.5-2B ShellCommand-Linux LoRA
+
+This repository contains a PEFT LoRA adapter trained for Linux natural-language-to-shell translation.
+
+## Artifact Type
+
+This is a LoRA adapter, not a merged full model checkpoint.
+
+## Intended Behavior
+
+The model is tuned to return exactly one of:
+
+- a Bash command or short Bash snippet
+- `ASK: <one short clarifying question>`
+- `CANNOT: <brief reason>`
+
+## Eval Snapshot
+
+- score: `218.4816`
+- verifier ok rate: `61.67%`
+- verifier command rate: `59.38%`
+- verifier ask rate: `56.25%`
+- verifier cannot rate: `100.00%`
+- exact any-exact rate: `24.00%`
+- exact parse-ok rate: `98.00%`
+
+## Usage
+
+Load this adapter on top of `Qwen/Qwen3.5-2B` with PEFT.

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "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": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "down_proj",
+    "k_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 sha256:312ea467f4f51a79d21cf2af71f40f8b5f3d75d3a8e5eceb88643a90a01b603b
+size 43672416

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

eval/exact_summary.json

@@ -0,0 +1,14 @@
+{
+  "model": "/root/bitnet-nl2sh/output/autoresearch_proxy_qwen35_2b/full_v1/qwen35_2b_batch8_ask_full_v1/model",
+  "base_model": "Qwen/Qwen3.5-2B",
+  "test_file": "/root/bitnet-nl2sh/output/data/nl2sh_test_raw.jsonl",
+  "rows": 100,
+  "primary_exact": 20,
+  "alt_exact": 6,
+  "any_exact": 24,
+  "parse_ok": 98,
+  "primary_exact_rate": 0.2,
+  "any_exact_rate": 0.24,
+  "parse_ok_rate": 0.98,
+  "avg_gen_seconds_per_example": 0.5884
+}

eval/score.json

@@ -0,0 +1,42 @@
+{
+  "components": {
+    "any_exact_rate": 0.24,
+    "ask_rate": 0.5625,
+    "cannot_rate": 1.0,
+    "command_rate": 0.5938,
+    "ok_rate": 0.6167,
+    "parse_ok_rate": 0.98,
+    "weak_category_rate": 0.5357142857142857
+  },
+  "exact_summary": "/root/bitnet-nl2sh/output/autoresearch_proxy_qwen35_2b/full_v1/qwen35_2b_batch8_ask_full_v1/eval_exact/summary.json",
+  "score": 218.4816,
+  "score_0_to_1": 2.184816,
+  "verifier_summary": "/root/bitnet-nl2sh/output/autoresearch_proxy_qwen35_2b/full_v1/qwen35_2b_batch8_ask_full_v1/eval_verifier/summary.json",
+  "weak_categories": [
+    "ambiguous_delete",
+    "ambiguous_secret",
+    "create_archive",
+    "enabled_services",
+    "find_jpgs",
+    "json_query",
+    "top_ips"
+  ],
+  "weak_category_rates": {
+    "ambiguous_delete": 0.125,
+    "ambiguous_secret": 1.0,
+    "create_archive": 1.0,
+    "enabled_services": 0.875,
+    "find_jpgs": 0.0,
+    "json_query": 0.625,
+    "top_ips": 0.125
+  },
+  "weights": {
+    "any_exact_rate": 0.2,
+    "ask_rate": 1.0,
+    "cannot_rate": 0.25,
+    "command_rate": 0.35,
+    "ok_rate": 1.0,
+    "parse_ok_rate": 0.1,
+    "weak_category_rate": 0.75
+  }
+}

eval/verifier_summary.json

@@ -0,0 +1,105 @@
+{
+  "avg_gen_seconds_per_example": 0.6777,
+  "base_model": "Qwen/Qwen3.5-2B",
+  "category_breakdown": {
+    "ambiguous_delete": {
+      "ok": 1,
+      "ok_rate": 0.125,
+      "rows": 8
+    },
+    "ambiguous_secret": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "cannot_cli": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "count_extension": {
+      "ok": 2,
+      "ok_rate": 0.25,
+      "rows": 8
+    },
+    "create_archive": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "delete_specific_logs": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "enabled_services": {
+      "ok": 7,
+      "ok_rate": 0.875,
+      "rows": 8
+    },
+    "extract_archive": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "find_jpgs": {
+      "ok": 0,
+      "ok_rate": 0.0,
+      "rows": 8
+    },
+    "git_branch": {
+      "ok": 0,
+      "ok_rate": 0.0,
+      "rows": 8
+    },
+    "grep_literal": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "json_query": {
+      "ok": 5,
+      "ok_rate": 0.625,
+      "rows": 8
+    },
+    "replace_literal": {
+      "ok": 2,
+      "ok_rate": 0.25,
+      "rows": 8
+    },
+    "show_env": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "top_ips": {
+      "ok": 1,
+      "ok_rate": 0.125,
+      "rows": 8
+    }
+  },
+  "enable_thinking": false,
+  "image": "local",
+  "mode_breakdown": {
+    "ask": {
+      "ok": 9,
+      "ok_rate": 0.5625,
+      "rows": 16
+    },
+    "cannot": {
+      "ok": 8,
+      "ok_rate": 1.0,
+      "rows": 8
+    },
+    "command": {
+      "ok": 57,
+      "ok_rate": 0.5938,
+      "rows": 96
+    }
+  },
+  "model": "/root/bitnet-nl2sh/output/autoresearch_proxy_qwen35_2b/full_v1/qwen35_2b_batch8_ask_full_v1/model",
+  "ok": 74,
+  "ok_rate": 0.6167,
+  "prompt_file": "/root/bitnet-nl2sh/prompts/student_linux_shell_v2f.txt",
+  "rows": 120
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5dcc81a623f926adf038f947eeeed6da9a08d33e8cfb9633aeb90d3a34ae660
+size 5713