Upload reproduced search_query_gen smollm2-135m specialist

README.md

@@ -0,0 +1,99 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+base_model_relation: finetune
+tags:
+- code
+- coding-agent
+- tool-use
+- function-calling
+- small-language-model
+- full-parameter-finetuning
+- supervised-fine-tuning
+- deterministic-verification
+- safetensors
+- subroutine:search_query_gen
+model-index:
+- name: Code Search-Query Generator (SmolLM2 135M)
+  results:
+  - task:
+      type: text-generation
+      name: Code Search-Query Generator
+    dataset:
+      name: Held-out HTTPX and Jinja2 oracle benchmark
+      type: custom
+    metrics:
+    - type: accuracy
+      value: 0.648
+      name: Success after one schema-feedback retry
+    - type: accuracy
+      value: 1.0
+      name: First-pass schema validity
+---
+
+# Code Search-Query Generator (SmolLM2 135M)
+
+This is a **full-parameter supervised fine-tune** of
+[`HuggingFaceTB/SmolLM2-135M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) for one narrow,
+schema-bound developer-agent subroutine:
+
+> Write an executable search regex from a plain-words request.
+
+The model is one cell from the
+[Parameter Floors for Developer-Agent Subroutines](https://github.com/IshaanAyaan/slm-agents)
+experiment. Labels are generated by deterministic oracles over real Python
+repositories; no teacher model or human judge labels the data.
+
+## Intended Use
+
+Use this checkpoint inside the repository's verified subroutine harness, which
+renders the task-specific prompt, parses strict JSON, permits one localized
+schema-feedback retry, applies deterministic guards, and falls back to rules
+where appropriate. This is not a general coding assistant or chat model.
+
+## Evaluation
+
+Evaluation uses up to 250 examples from HTTPX and Jinja2, both held out
+entirely from training. Decoding is greedy.
+
+| Metric | Result |
+|---|---:|
+| Success after one schema retry | 64.8% |
+| First-pass success | 64.8% |
+| First-pass schema validity | 100.0% |
+| Base instruct success after retry | 0.0% for the base instruct model |
+| Rules-only success | 23.7% |
+
+Experiment verdict for this subroutine: **unsolved (best 0.88 @ qwen2.5-0.5b)**.
+
+## Training
+
+- Training examples: 2000
+- Epochs: 3.0
+- Learning rate: 2e-05
+- Effective batch configuration: 32 per device x
+  1 gradient accumulation
+- Maximum sequence length: 2048
+- Seed: 0
+- Final training loss: 0.529164
+- Reproduction hardware: one NVIDIA A100 80GB PCIe
+- Source revision:
+  [`d0fd7bf`](https://github.com/IshaanAyaan/slm-agents/commit/d0fd7bff420c2f2f0446599ca2b169cc4f03b06a)
+
+The dataset was generated from pinned Flask, Click, and Rich repositories for
+training/validation. HTTPX and Jinja2 were reserved for testing.
+
+## Limitations
+
+The checkpoint is specialized to one closed JSON schema and should not be
+expected to retain broad instruction-following ability. The experiment mixes
+two base-model families across its size sweep. Some subroutines are better
+served by deterministic rules; consult the verdict above before deployment.
+
+## License
+
+Apache-2.0, following the base model. Experiment code is MIT licensed.

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c119dd074c478c8a75648dc39769abfbe75062330f0d3fe980bf89ec42dbf7f
+size 538090408

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,155 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_meta.json

@@ -0,0 +1,13 @@
+{
+  "base_model": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "train_path": "/root/slm-agents/slm_harness/results/subroutines/sft/search_query_gen/train.jsonl",
+  "n_train": 2000,
+  "epochs": 3.0,
+  "lr": 2e-05,
+  "batch_size": 32,
+  "grad_accum": 1,
+  "max_seq_len": 2048,
+  "seed": 0,
+  "train_seconds": 28.0,
+  "train_loss": 0.5291644927685853
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05364494c394f3f25d0f17bf31bc6add9f798217ae800f8000f73c155259416f
+size 5752