using transformers from branch (hybrid-mamba)

Signed-off-by: Jefferson Fialho <[email protected]>

Dockerfile.ubi

@@ -213,9 +213,8 @@ USER root
 RUN --mount=type=cache,target=/root/.cache/pip \
     --mount=type=bind,from=build,src=/workspace/dist,target=/workspace/dist \
     uv pip install $(echo /workspace/dist/*.whl)'[tensorizer]' && \
-    uv pip install vllm-tgis-adapter==0.5.3 
-#    uv pip install \
-#        "git+https://github.com/opendatahub-io/vllm-tgis-adapter@ibm-20241106-adapter"
+    uv pip install \
+        "git+https://github.com/opendatahub-io/vllm-tgis-adapter@ibm-20241106-adapter"
 
 RUN --mount=type=bind,from=build,src=/workspace/dist,target=/workspace/dist \
     echo "Local dir and dist:" && pwd && ls -l /workspace/dist

requirements-common.txt

@@ -4,7 +4,8 @@ numpy < 2.0.0
 requests >= 2.26.0
 tqdm
 py-cpuinfo
-transformers >= 4.45.2  # Required for Llama 3.2 and Qwen2-VL.
+#transformers >= 4.45.2  # Required for Llama 3.2 and Qwen2-VL.
+transformers @ git+https://github.com/fabianlim/transformers.git@hybrid-mamba
 tokenizers >= 0.19.1  # Required for Llama 3.
 protobuf # Required by LlamaTokenizer.
 fastapi >= 0.107.0, < 0.113.0; python_version < '3.9'

requirements-test.txt

@@ -550,7 +550,8 @@ tqdm==4.66.6
     #   transformers
 tqdm-multiprocess==0.0.11
     # via lm-eval
-transformers==4.45.2
+    # transformers==4.45.2
+transformers @ git+https://github.com/fabianlim/transformers.git@hybrid-mamba
     # via
     #   lm-eval
     #   peft