llama-vllm-mic
Slim model weights, executable usage and framework expectations in one repository.
- Contract manifest
- Transformers usage
- Transformers expectations
- Fixture provenance
- How the fixture was shrunk
Contract
SmolLM2-135M causal LM (vLLM-compatible fixture)
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: llama-vllm-mic
A 3.2M-parameter fixture for the llama-vllm MIC, covering HuggingFaceTB/SmolLM2-135M. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
ebd716dc45dd. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
LlamaForCausalLM, shrunk by the generic rule insweep.py(num_hidden_layers 2). - Processor files copied byte for byte from
HuggingFaceTB/SmolLM2-135M:generation_config.json,merges.txt,special_tokens_map.json,tokenizer.json,tokenizer_config.json,vocab.json. - Random weights (seed 17). They passed the input-sensitivity gate: every perturbation of the contract's inputs moved the logits by at least 0.001 (weakest:
input_ids:reverse, 2.11), so no training was needed. - Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
- Saved in bfloat16, the dtype
HuggingFaceTB/SmolLM2-135Mloads in by default. - Finite in float32, bfloat16, and float16 (forward, loss, gradients).
Built by build_fixtures.py; build.json records the pinned sources, gate results, and file hashes. This repository includes the slim weights, usage and framework expectations; rebuild the other files with python example/build_fixtures.py --fixture llama-vllm-mic.
- Downloads last month
- 43
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for huggingface-mic/llama-vllm-mic
Base model
HuggingFaceTB/SmolLM2-135M