[Model] Add Phi3.5-mini #555
Merged
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
CharlieFRuan
added a commit
that referenced
this pull request
Aug 23, 2024
### Change - #555 ### TVMjs - Updated to current head: apache/tvm@1518008 - Main change is apache/tvm#17251 - This is needed for WASMs compiled after apache/tvm#17257 is merged (e.g. Phi-3.5). TVM global functions that returns bool need this PR to run correctly (e.g. `AcceptToken()` in BNFGrammar) in runtime. - However, these are backward compatible to WASMs compiled prior to this PR. Tested with Phi-3 (old WASM) running grammar.
jingyi-zhao-01
pushed a commit
to jingyi-zhao-01/web-llm
that referenced
this pull request
Dec 8, 2024
This PR adds the newly release Phi3.5-mini, adding the following `model_id`s to our prebuilt model list: - `Phi-3.5-mini-instruct-q4f16_1-MLC` (4k KVCache) - `Phi-3.5-mini-instruct-q4f32_1-MLC` (4k KVCache) - `Phi-3.5-mini-instruct-q4f16_1-MLC-1k` (1k KVCache) - `Phi-3.5-mini-instruct-q4f16_1-MLC-1k` (1k KVCache) See mlc-ai/binary-mlc-llm-libs#136 for on which commits of TVM and MLC-LLM this is compiled with. Note that Phi-3.5-mini comes with support up to 128K context (unlike Phi-3-mini which only has 4k) thanks to rope scaling which MLC-LLM supports, which you can take advantage of in WebLLM by increasing `ModelRecord.overrides.context_window_size` or specifying it in `ChatOptions` when loading a model, as long as there is enough VRAM.
jingyi-zhao-01
pushed a commit
to jingyi-zhao-01/web-llm
that referenced
this pull request
Dec 8, 2024
### Change - mlc-ai#555 ### TVMjs - Updated to current head: apache/tvm@1518008 - Main change is apache/tvm#17251 - This is needed for WASMs compiled after apache/tvm#17257 is merged (e.g. Phi-3.5). TVM global functions that returns bool need this PR to run correctly (e.g. `AcceptToken()` in BNFGrammar) in runtime. - However, these are backward compatible to WASMs compiled prior to this PR. Tested with Phi-3 (old WASM) running grammar.
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.
This PR adds the newly release Phi3.5-mini, adding the following
model_ids to our prebuilt model list:Phi-3.5-mini-instruct-q4f16_1-MLC(4k KVCache)Phi-3.5-mini-instruct-q4f32_1-MLC(4k KVCache)Phi-3.5-mini-instruct-q4f16_1-MLC-1k(1k KVCache)Phi-3.5-mini-instruct-q4f16_1-MLC-1k(1k KVCache)See mlc-ai/binary-mlc-llm-libs#136 for on which commits of TVM and MLC-LLM this is compiled with.
Note that Phi-3.5-mini comes with support up to 128K context (unlike Phi-3-mini which only has 4k) thanks to rope scaling which MLC-LLM supports, which you can take advantage of in WebLLM by increasing
ModelRecord.overrides.context_window_sizeor specifying it inChatOptionswhen loading a model, as long as there is enough VRAM.