feat: add support for phi4 and ministral 8b (#71)

* feat: add support for phi4

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* feat: add support for Ministral-8B

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: vatsalkshah

requirements.txt

@@ -1,6 +1,6 @@
 torch>=1.13.1
-huggingface-hub>=0.24.7,<0.25
-transformers>=4.43.0,<=4.45.0
+huggingface-hub==0.29.1
+transformers==4.49.0
 datasets>=2.14.3
 accelerate>=0.27.2
 loguru==0.7.0

src/core/constant.py

@@ -58,6 +58,7 @@
     "mistralai/Mistral-7B-Instruct-v0.1",
     "mistralai/Mistral-7B-Instruct-v0.2",
     "mistralai/Mistral-7B-Instruct-v0.3",
+    "mistralai/Ministral-8B-Instruct-2410",
     # mixtral
     "mistralai/Mixtral-8x7B-v0.1",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
@@ -97,6 +98,9 @@
     "microsoft/Phi-3.5-mini-instruct",
     "microsoft/Phi-3-mini-4k-instruct",
     "microsoft/Phi-3-medium-4k-instruct",
+    # phi4
+    "microsoft/Phi-4-mini-instruct",
+    "microsoft/phi-4",
     # deepseek
     "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
     "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",

src/core/hf_utils.py

@@ -1,5 +1,4 @@
 from huggingface_hub import HfApi
-from huggingface_hub.utils._errors import EntryNotFoundError
 from loguru import logger
 
 api = HfApi()
@@ -13,9 +12,12 @@ def download_lora_config(repo_id: str, revision: str) -> bool:
             local_dir="lora",
             revision=revision,
         )
-    except EntryNotFoundError:
-        logger.info("No adapter_config.json found in the repo, assuming full model")
-        return False
+    except Exception as e:
+        if "adapter_config.json" in str(e):
+            logger.info("No adapter_config.json found in the repo, assuming full model")
+            return False
+        else:
+            raise  # Re-raise the exception if it's not related to the missing file
     return True
 
 

src/core/template.py

@@ -170,3 +170,15 @@ def register_template(
     system=None,
     stop_word="<|end|>",
 )
+
+register_template(
+    template_name="phi4",
+    system_format=None,
+    user_format="<|user|>\n{content}<|end|>\n<|assistant|>",
+    assistant_format="{content}<|end|>\n",
+    tool_format="<|tool|>{content}<|/tool|>",
+    function_format="<|tool_call|>{content}<|/tool_call|>",
+    observation_format="<|tool|>\n{content}<|end|>\n<|assistant|>",
+    system=None,
+    stop_word="<|end|>",
+)