feat(tooling): add script to auto update readme table of supported

models

Signed-off-by: Aaron <29749331+aarnphm@users.noreply.github.com>

src/openllm/_configuration.py

@@ -649,6 +649,9 @@ class LLMConfig:
         __openllm_hints__: dict[str, t.Any] = Field(None, init=False)
         """An internal cache of resolved types for this LLMConfig."""
 
+        __openllm_url__: str = Field(None, init=False)
+        """The resolved url for this LLMConfig."""
+
         GenerationConfig: type = type
         """Users can override this subclass of any given LLMConfig to provide GenerationConfig
         default value. For example:
@@ -678,6 +681,7 @@ class LLMConfig:
         default_timeout: int | None = None,
         trust_remote_code: bool = False,
         requires_gpu: bool = False,
+        url: str | None = None,
     ):
         if name_type == "dasherize":
             model_name = inflection.underscore(cls.__name__.replace("Config", ""))
@@ -694,6 +698,7 @@ class LLMConfig:
         cls.__openllm_model_name__ = model_name
         cls.__openllm_start_name__ = start_name
         cls.__openllm_env__ = openllm.utils.ModelEnv(model_name)
+        cls.__openllm_url__ = url or "(not set)"
 
         # NOTE: Since we want to enable a pydantic-like experience
         # this means we will have to hide the attr abstraction, and generate

src/openllm/models/chatglm/configuration_chatglm.py

@@ -22,6 +22,7 @@ class ChatGLMConfig(
     trust_remote_code=True,
     default_timeout=3600000,
     requires_gpu=True,
+    url="https://github.com/THUDM/ChatGLM-6B",
 ):
     """
     ChatGLM is an open bilingual language model based on

src/openllm/models/dolly_v2/configuration_dolly_v2.py

@@ -20,7 +20,12 @@ from __future__ import annotations
 import openllm
 
 
-class DollyV2Config(openllm.LLMConfig, default_timeout=3600000, trust_remote_code=True):
+class DollyV2Config(
+    openllm.LLMConfig,
+    default_timeout=3600000,
+    trust_remote_code=True,
+    url="https://github.com/databrickslabs/dolly",
+):
     """Databricks’ Dolly is an instruction-following large language model trained on the Databricks
     machine learning platform that is licensed for commercial use.
 

src/openllm/models/falcon/configuration_falcon.py

@@ -22,6 +22,7 @@ class FalconConfig(
     trust_remote_code=True,
     requires_gpu=True,
     default_timeout=3600000,
+    url="https://falconllm.tii.ae/",
 ):
     """Falcon-7B is a 7B parameters causal decoder-only model built by
     TII and trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb)

src/openllm/models/flan_t5/configuration_flan_t5.py

@@ -40,7 +40,7 @@ saved pretrained, or a fine-tune FLAN-T5, provide ``OPENLLM_FLAN_T5_PRETRAINED='
 DEFAULT_PROMPT_TEMPLATE = """Answer the following question:\nQuestion: {instruction}\nAnswer:"""
 
 
-class FlanT5Config(openllm.LLMConfig):
+class FlanT5Config(openllm.LLMConfig, url="https://huggingface.co/docs/transformers/model_doc/flan-t5"):
     """FLAN-T5 was released in the paper [Scaling Instruction-Finetuned Language Models](https://arxiv.org/pdf/2210.11416.pdf)
     - it is an enhanced version of T5 that has been finetuned in a mixture of tasks.
 

src/openllm/models/stablelm/configuration_stablelm.py

@@ -16,7 +16,7 @@ from __future__ import annotations
 import openllm
 
 
-class StableLMConfig(openllm.LLMConfig, name_type="lowercase"):
+class StableLMConfig(openllm.LLMConfig, name_type="lowercase", url="https://github.com/Stability-AI/StableLM"):
     """StableLM-Base-Alpha is a suite of 3B and 7B parameter decoder-only language models
     pre-trained on a diverse collection of English datasets with a sequence
     length of 4096 to push beyond the context window limitations of existing open-source language models.

src/openllm/models/starcoder/configuration_starcoder.py

@@ -16,7 +16,12 @@ from __future__ import annotations
 import openllm
 
 
-class StarCoderConfig(openllm.LLMConfig, name_type="lowercase", requires_gpu=True):
+class StarCoderConfig(
+    openllm.LLMConfig,
+    name_type="lowercase",
+    requires_gpu=True,
+    url="https://github.com/bigcode-project/starcoder",
+):
     """The StarCoder models are 15.5B parameter models trained on 80+ programming languages from
     [The Stack (v1.2)](https://huggingface.co/datasets/bigcode/the-stack), with opt-out requests excluded.