Instructions to use ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m")
model = AutoModelForCausalLM.from_pretrained("ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m

SGLang

How to use ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m with Docker Model Runner:
```
docker model run hf.co/ishaanranjan/slm-agent-search-hit-ranker-smollm2-135m
```

slm-agent-search-hit-ranker-smollm2-135m / README.md

ishaanranjan

Upload reproduced search_hit_ranker smollm2-135m specialist

fb40d92 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

3.09 kB

metadata

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_hit_ranker
model-index:
  - name: Code Search-Hit Ranker (SmolLM2 135M)
    results:
      - task:
          type: text-generation
          name: Code Search-Hit Ranker
        dataset:
          name: Held-out HTTPX and Jinja2 oracle benchmark
          type: custom
        metrics:
          - type: accuracy
            value: 0.16
            name: Success after one schema-feedback retry
          - type: accuracy
            value: 1
            name: First-pass schema validity

Code Search-Hit Ranker (SmolLM2 135M)

This is a full-parameter supervised fine-tune of HuggingFaceTB/SmolLM2-135M-Instruct for one narrow, schema-bound developer-agent subroutine:

Pick the definition site among real grep hits for a symbol.

The model is one cell from the Parameter Floors for Developer-Agent Subroutines 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	16.0%
First-pass success	16.0%
First-pass schema validity	100.0%
Base instruct success after retry	0.0% for the base instruct model
Rules-only success	99.3%

Experiment verdict for this subroutine: rules suffice.

Training

Training examples: 1576
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: 1.027056
Reproduction hardware: one NVIDIA A100 80GB PCIe
Source revision: d0fd7bf

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.