Add inference example notebooks for LFM2 models #50
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
alay2shah
commented
Feb 2, 2026
alay2shah
commented
- Transformers: text generation, streaming, vision
- vLLM: text generation, batching, vision
- llama.cpp: CLI and server API, vision
- MLX: text generation, streaming, vision (Apple Silicon note)
- Ollama: Python/curl API examples, vision
- Transformers: text generation, streaming, vision - vLLM: text generation, batching, vision - llama.cpp: CLI and server API, vision - MLX: text generation, streaming, vision (Apple Silicon note) - Ollama: Python/curl API examples, vision Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Use return_dict=True with apply_chat_template and access input_ids properly to avoid AttributeError on shape access. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use dtype="bfloat16" (not torch_dtype) - Use batch_decode as in docs - Keep tokenize=True as per docs Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
IMPORTANT: tie lm_head to input embeddings to fix missing weights issue in transformers v5. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Pin torch==2.9.0 to prevent errors - Use dtype instead of torch_dtype (deprecated) - Remove fallback note Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Use pip with --extra-index-url for CUDA support (--torch-backend is a uv flag, not pip) - Fix chat() API to use message format instead of raw strings Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
alay2shah
force-pushed
the
notebook-examples
branch
from
97bbed6 to
9a7c999
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.