Luke Nitish Kumar issues

Results 6 issues of


                                            Luke Nitish Kumar

How to use LSTM middleware with a DQN agent

Is it possible to use an LSTM layer with a DQN agent? If so how can specify the sequnece length (number of transitions) to use?

Converter for Llama based Masked Diffusion Models (Based on Dream)

# ✨ Description This PR provides a converter for Diffusion models based on Llama (and Dream). It complements the mask-diffusion training PR #238 and needs to merge after. ## 🔍...

Concat prompt and completion cols for tokenizing

# ✨ Description Migrated from #248; this PR allows a dataset with prompt and completion specifically and in general any pair of text columns (eg: question and answer) to be...

Combine GPTHuggingfaceDatasetConfig input sources into `source_schema`

# ✨ Description This PR creates a common interface for all `GPTHuggingfaceDatasetConfig` input columns via the new `source_schema` variable. Beyond the variable `filed` we require additional keys to preprocess and...

[hybrid_dev] Cleanup modeling file for Apriel-H

# ✨ Description Review cleanup.

[Prototype] Masked Diffusion Training with Shift

# ✨ Description This PR adds functionality to train a mask diffusion model. It sets up initial diffusion loss based on Llada with a shift of 1. - Resolving https://github.com/ServiceNow/Fast-LLM/issues/208...