Download README.md from huggingface-mic/DeepSeek-Coder-V2-Lite-Instruct-mic: direct link, hf CLI and curl.
- Browser
- Download file 8.63 kB
-
https://huggingface.co/huggingface-mic/DeepSeek-Coder-V2-Lite-Instruct-mic/resolve/main/README.md
- Command line
-
hf download hf://huggingface-mic/DeepSeek-Coder-V2-Lite-Instruct-mic/README.md
-
curl -L -o README.md https://huggingface.co/huggingface-mic/DeepSeek-Coder-V2-Lite-Instruct-mic/resolve/main/README.md
tags:
- mic
- test-artifact
base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
DeepSeek-Coder-V2-Lite-Instruct-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
DeepSeek-Coder-V2-Lite-Instruct-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
DeepSeek-Coder-V2-Lite-Instruct causal LM
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: DeepSeek-Coder-V2-Lite-Instruct-mic
A 13.2M-parameter fixture for the DeepSeek-Coder-V2-Lite-Instruct MIC, covering deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
465d8cbffd2f. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
DeepseekV2ForCausalLM, shrunk by the generic rule insweep.py(num_hidden_layers 2). - Processor files copied byte for byte from
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct:configuration_deepseek.py,generation_config.json,modeling_deepseek.py,tokenization_deepseek_fast.py,tokenizer.json,tokenizer_config.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:roll_batch, 1.11), 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
deepseek-ai/DeepSeek-Coder-V2-Lite-Instructloads 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 DeepSeek-Coder-V2-Lite-Instruct-mic.
Slim model
DeepSeek-Coder-V2-Lite-Instruct-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
DeepSeek-Coder-V2-Lite-Instruct-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
DeepSeek-Coder-V2-Lite-Instruct causal LM
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: DeepSeek-Coder-V2-Lite-Instruct-mic
A 13.2M-parameter fixture for the DeepSeek-Coder-V2-Lite-Instruct MIC, covering deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
465d8cbffd2f. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
DeepseekV2ForCausalLM, shrunk by the generic rule insweep.py(num_hidden_layers 2). - Processor files copied byte for byte from
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct:configuration_deepseek.py,generation_config.json,modeling_deepseek.py,tokenization_deepseek_fast.py,tokenizer.json,tokenizer_config.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:roll_batch, 1.11), 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
deepseek-ai/DeepSeek-Coder-V2-Lite-Instructloads 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 DeepSeek-Coder-V2-Lite-Instruct-mic.
Slim model
DeepSeek-Coder-V2-Lite-Instruct-mic
Slim model weights, executable usage and framework expectations in one repository.
Contract
DeepSeek-Coder-V2-Lite-Instruct causal LM
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: DeepSeek-Coder-V2-Lite-Instruct-mic
A 13.2M-parameter fixture for the DeepSeek-Coder-V2-Lite-Instruct MIC, covering deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
465d8cbffd2f. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
DeepseekV2ForCausalLM, shrunk by the generic rule insweep.py(num_hidden_layers 2). - Processor files copied byte for byte from
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct:configuration_deepseek.py,generation_config.json,modeling_deepseek.py,tokenization_deepseek_fast.py,tokenizer.json,tokenizer_config.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:roll_batch, 1.11), 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
deepseek-ai/DeepSeek-Coder-V2-Lite-Instructloads 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 DeepSeek-Coder-V2-Lite-Instruct-mic.