From 56f8ebc709f84087c8ab5d1f26478b6885673164 Mon Sep 17 00:00:00 2001 From: "Yao, Qing" Date: Wed, 23 Oct 2024 14:47:05 +0800 Subject: [PATCH 1/5] [Codegen] Replace codegen default Model to Qwen/Qwen2.5-Coder-7B-Instruct. Signed-off-by: Yao, Qing --- CodeGen/README.md | 6 +++--- CodeGen/docker_compose/intel/cpu/xeon/README.md | 2 +- CodeGen/docker_compose/intel/hpu/gaudi/README.md | 2 +- CodeGen/docker_compose/set_env.sh | 2 +- CodeGen/kubernetes/intel/README.md | 2 +- CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml | 2 +- CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml | 2 +- CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml | 2 +- CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml | 2 +- ProductivitySuite/docker_compose/intel/cpu/xeon/README.md | 2 +- ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh | 2 +- .../kubernetes/intel/cpu/xeon/manifest/codegen.yaml | 2 +- supported_examples.md | 2 +- 13 files changed, 15 insertions(+), 15 deletions(-) diff --git a/CodeGen/README.md b/CodeGen/README.md index 03288fb2d..03955ff00 100644 --- a/CodeGen/README.md +++ b/CodeGen/README.md @@ -87,10 +87,10 @@ By default, the LLM model is set to a default value as listed below: | Service | Model | | ------------ | ------------------------------------------------------------------------------- | -| LLM_MODEL_ID | [meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf) | +| LLM_MODEL_ID | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) | -[meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf) is a gated model that requires submitting an access request through Hugging Face. You can replace it with another model. -Change the `LLM_MODEL_ID` below for your needs, such as: [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat), [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) +[Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) may be a gated model that requires submitting an access request through Hugging Face. You can replace it with another model. +Change the `LLM_MODEL_ID` below for your needs, such as: [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) If you choose to use `meta-llama/CodeLlama-7b-hf` as LLM model, you will need to visit [here](https://huggingface.co/meta-llama/CodeLlama-7b-hf), click the `Expand to review and access` button to ask for model access. diff --git a/CodeGen/docker_compose/intel/cpu/xeon/README.md b/CodeGen/docker_compose/intel/cpu/xeon/README.md index 8bdde1f75..5332d719a 100644 --- a/CodeGen/docker_compose/intel/cpu/xeon/README.md +++ b/CodeGen/docker_compose/intel/cpu/xeon/README.md @@ -105,7 +105,7 @@ export your_no_proxy=${your_no_proxy},"External_Public_IP" export no_proxy=${your_no_proxy} export http_proxy=${your_http_proxy} export https_proxy=${your_http_proxy} -export LLM_MODEL_ID="meta-llama/CodeLlama-7b-hf" +export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" export TGI_LLM_ENDPOINT="http://${host_ip}:8028" export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} export MEGA_SERVICE_HOST_IP=${host_ip} diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/README.md b/CodeGen/docker_compose/intel/hpu/gaudi/README.md index 2a5040ea0..31cfad292 100644 --- a/CodeGen/docker_compose/intel/hpu/gaudi/README.md +++ b/CodeGen/docker_compose/intel/hpu/gaudi/README.md @@ -85,7 +85,7 @@ Since the `compose.yaml` will consume some environment variables, you need to se export no_proxy=${your_no_proxy} export http_proxy=${your_http_proxy} export https_proxy=${your_http_proxy} -export LLM_MODEL_ID="meta-llama/CodeLlama-7b-hf" +export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" export TGI_LLM_ENDPOINT="http://${host_ip}:8028" export HUGGINGFACEHUB_API_TOKEN=${your_hf_api_token} export MEGA_SERVICE_HOST_IP=${host_ip} diff --git a/CodeGen/docker_compose/set_env.sh b/CodeGen/docker_compose/set_env.sh index d66a120af..dba717b64 100644 --- a/CodeGen/docker_compose/set_env.sh +++ b/CodeGen/docker_compose/set_env.sh @@ -4,7 +4,7 @@ # SPDX-License-Identifier: Apache-2.0 -export LLM_MODEL_ID="meta-llama/CodeLlama-7b-hf" +export LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" export TGI_LLM_ENDPOINT="http://${host_ip}:8028" export MEGA_SERVICE_HOST_IP=${host_ip} export LLM_SERVICE_HOST_IP=${host_ip} diff --git a/CodeGen/kubernetes/intel/README.md b/CodeGen/kubernetes/intel/README.md index be18003b8..a4bb44681 100644 --- a/CodeGen/kubernetes/intel/README.md +++ b/CodeGen/kubernetes/intel/README.md @@ -14,7 +14,7 @@ ``` cd GenAIExamples/CodeGen/kubernetes/intel/cpu/xeon/manifests export HUGGINGFACEHUB_API_TOKEN="YourOwnToken" -export MODEL_ID="meta-llama/CodeLlama-7b-hf" +export MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct" sed -i "s/insert-your-huggingface-token-here/${HUGGINGFACEHUB_API_TOKEN}/g" codegen.yaml sed -i "s/meta-llama\/CodeLlama-7b-hf/${MODEL_ID}/g" codegen.yaml kubectl apply -f codegen.yaml diff --git a/CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml b/CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml index dd1675ce3..8dd3c2b57 100644 --- a/CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml +++ b/CodeGen/kubernetes/intel/cpu/xeon/gmc/codegen_xeon.yaml @@ -29,6 +29,6 @@ spec: internalService: serviceName: tgi-service config: - MODEL_ID: meta-llama/CodeLlama-7b-hf + MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct endpoint: /generate isDownstreamService: true diff --git a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml index 96cc68266..4e6d8f91c 100644 --- a/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ b/CodeGen/kubernetes/intel/cpu/xeon/manifest/codegen.yaml @@ -64,7 +64,7 @@ metadata: app.kubernetes.io/version: "2.1.0" app.kubernetes.io/managed-by: Helm data: - MODEL_ID: "meta-llama/CodeLlama-7b-hf" + MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct" PORT: "2080" HF_TOKEN: "insert-your-huggingface-token-here" http_proxy: "" diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml b/CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml index 2e3782057..d9a927e5c 100644 --- a/CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml +++ b/CodeGen/kubernetes/intel/hpu/gaudi/gmc/codegen_gaudi.yaml @@ -29,6 +29,6 @@ spec: internalService: serviceName: tgi-gaudi-svc config: - MODEL_ID: meta-llama/CodeLlama-7b-hf + MODEL_ID: Qwen/Qwen2.5-Coder-7B-Instruct endpoint: /generate isDownstreamService: true diff --git a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml index c4a43a7c3..b506d17d4 100644 --- a/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml +++ b/CodeGen/kubernetes/intel/hpu/gaudi/manifest/codegen.yaml @@ -64,7 +64,7 @@ metadata: app.kubernetes.io/version: "2.1.0" app.kubernetes.io/managed-by: Helm data: - MODEL_ID: "meta-llama/CodeLlama-7b-hf" + MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct" PORT: "2080" HF_TOKEN: "insert-your-huggingface-token-here" http_proxy: "" diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md index c5463ad10..892014a5e 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md @@ -137,7 +137,7 @@ export COLLECTION_NAME="Conversations" export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" export RERANK_MODEL_ID="BAAI/bge-reranker-base" export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" -export LLM_MODEL_ID_CODEGEN="meta-llama/CodeLlama-7b-hf" +export LLM_MODEL_ID_CODEGEN="Qwen/Qwen2.5-Coder-7B-Instruct" export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" export TGI_LLM_ENDPOINT="http://${host_ip}:9009" diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh b/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh index 0139b532a..ca369b5ee 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh @@ -8,7 +8,7 @@ export COLLECTION_NAME="Conversations" export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" export RERANK_MODEL_ID="BAAI/bge-reranker-base" export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" -export LLM_MODEL_ID_CODEGEN="meta-llama/CodeLlama-7b-hf" +export LLM_MODEL_ID_CODEGEN="Qwen/Qwen2.5-Coder-7B-Instruct" export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" export TGI_LLM_ENDPOINT="http://${host_ip}:9009" diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml index 6c52c5d92..05788f61a 100644 --- a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml @@ -39,7 +39,7 @@ metadata: app.kubernetes.io/version: "1.4" app.kubernetes.io/managed-by: Helm data: - MODEL_ID: "meta-llama/CodeLlama-7b-hf" + MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct" PORT: "2080" HUGGING_FACE_HUB_TOKEN: "insert-your-huggingface-token-here" HF_TOKEN: "insert-your-huggingface-token-here" diff --git a/supported_examples.md b/supported_examples.md index e913fd22e..66efb401a 100644 --- a/supported_examples.md +++ b/supported_examples.md @@ -65,7 +65,7 @@ This document introduces the supported examples of GenAIExamples. The supported | Framework | LLM | Serving | HW | Description | | ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------- | --------------------------------------------------------------- | ----------- | ----------- | -| [LangChain](https://www.langchain.com)/[LlamaIndex](https://www.llamaindex.ai) | [meta-llama/CodeLlama-7b-hf](https://huggingface.co/meta-llama/CodeLlama-7b-hf) | [TGI](https://github.com/huggingface/text-generation-inference) | Xeon/Gaudi2 | Copilot | +| [LangChain](https://www.langchain.com)/[LlamaIndex](https://www.llamaindex.ai) | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) | [TGI](https://github.com/huggingface/text-generation-inference) | Xeon/Gaudi2 | Copilot | ### CodeTrans From a2ecf0ac777c86fbac0faf814180c6c46937f18e Mon Sep 17 00:00:00 2001 From: "pre-commit-ci[bot]" <66853113+pre-commit-ci[bot]@users.noreply.github.com> Date: Wed, 23 Oct 2024 06:49:59 +0000 Subject: [PATCH 2/5] [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --- CodeGen/README.md | 6 +++--- supported_examples.md | 4 ++-- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/CodeGen/README.md b/CodeGen/README.md index 03955ff00..013c31d37 100644 --- a/CodeGen/README.md +++ b/CodeGen/README.md @@ -85,12 +85,12 @@ Currently we support two ways of deploying ChatQnA services with docker compose: By default, the LLM model is set to a default value as listed below: -| Service | Model | -| ------------ | ------------------------------------------------------------------------------- | +| Service | Model | +| ------------ | --------------------------------------------------------------------------------------- | | LLM_MODEL_ID | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) may be a gated model that requires submitting an access request through Hugging Face. You can replace it with another model. -Change the `LLM_MODEL_ID` below for your needs, such as: [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) +Change the `LLM_MODEL_ID` below for your needs, such as: [deepseek-ai/deepseek-coder-6.7b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-instruct) If you choose to use `meta-llama/CodeLlama-7b-hf` as LLM model, you will need to visit [here](https://huggingface.co/meta-llama/CodeLlama-7b-hf), click the `Expand to review and access` button to ask for model access. diff --git a/supported_examples.md b/supported_examples.md index 66efb401a..00ce346f5 100644 --- a/supported_examples.md +++ b/supported_examples.md @@ -63,8 +63,8 @@ This document introduces the supported examples of GenAIExamples. The supported [CodeGen](./CodeGen/README.md) is an example of copilot designed for code generation in Visual Studio Code. -| Framework | LLM | Serving | HW | Description | -| ------------------------------------------------------------------------------ | ------------------------------------------------------------------------------- | --------------------------------------------------------------- | ----------- | ----------- | +| Framework | LLM | Serving | HW | Description | +| ------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------- | --------------------------------------------------------------- | ----------- | ----------- | | [LangChain](https://www.langchain.com)/[LlamaIndex](https://www.llamaindex.ai) | [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) | [TGI](https://github.com/huggingface/text-generation-inference) | Xeon/Gaudi2 | Copilot | ### CodeTrans From c58ea38e1545cab86d2591b64ce8b7476adc379b Mon Sep 17 00:00:00 2001 From: "Yao, Qing" Date: Thu, 24 Oct 2024 11:24:32 +0800 Subject: [PATCH 3/5] Fix docker compose yaml in Productivity Suite. Signed-off-by: Yao, Qing --- .../docker_compose/intel/cpu/xeon/compose.yaml | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml index 2e56d6584..00ef93d3b 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml @@ -165,10 +165,10 @@ services: https_proxy: ${https_proxy} http_proxy: ${http_proxy} MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP} - EMBEDDING_SERVICE_HOST_IP: ${EMBEDDING_SERVICE_HOST_IP} + EMBEDDING_SERVER_HOST_IP: ${EMBEDDING_SERVICE_HOST_IP} RETRIEVER_SERVICE_HOST_IP: ${RETRIEVER_SERVICE_HOST_IP} - RERANK_SERVICE_HOST_IP: ${RERANK_SERVICE_HOST_IP} - LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP_CHATQNA} + RERANK_SERVER_HOST_IP: ${RERANK_SERVICE_HOST_IP} + LLM_SERVER_HOST_IP: ${LLM_SERVICE_HOST_IP_CHATQNA} ipc: host restart: always tgi_service_codegen: From 902e15111debf22a73427f097098f4c50eaf3d26 Mon Sep 17 00:00:00 2001 From: "Yao, Qing" Date: Thu, 24 Oct 2024 13:50:46 +0800 Subject: [PATCH 4/5] Fix PORT env in docker compose yaml for Productivity Suite. Signed-off-by: Yao, Qing --- ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml index 00ef93d3b..f6882d9e8 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml @@ -166,9 +166,12 @@ services: http_proxy: ${http_proxy} MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP} EMBEDDING_SERVER_HOST_IP: ${EMBEDDING_SERVICE_HOST_IP} + EMBEDDING_SERVER_PORT: 6006 RETRIEVER_SERVICE_HOST_IP: ${RETRIEVER_SERVICE_HOST_IP} RERANK_SERVER_HOST_IP: ${RERANK_SERVICE_HOST_IP} + RERANK_SERVER_PORT: 8008 LLM_SERVER_HOST_IP: ${LLM_SERVICE_HOST_IP_CHATQNA} + LLM_SERVER_PORT: 9009 ` ipc: host restart: always tgi_service_codegen: From 6f13da0c3b0b0d63a42774463e417fa20786a631 Mon Sep 17 00:00:00 2001 From: "Yao, Qing" Date: Mon, 28 Oct 2024 08:40:08 +0800 Subject: [PATCH 5/5] Revert changes in Productivity Suite. Signed-off-by: Yao, Qing --- .../docker_compose/intel/cpu/xeon/README.md | 2 +- .../docker_compose/intel/cpu/xeon/compose.yaml | 9 +++------ .../docker_compose/intel/cpu/xeon/set_env.sh | 2 +- .../kubernetes/intel/cpu/xeon/manifest/codegen.yaml | 2 +- 4 files changed, 6 insertions(+), 9 deletions(-) diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md index 892014a5e..c5463ad10 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/README.md @@ -137,7 +137,7 @@ export COLLECTION_NAME="Conversations" export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" export RERANK_MODEL_ID="BAAI/bge-reranker-base" export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" -export LLM_MODEL_ID_CODEGEN="Qwen/Qwen2.5-Coder-7B-Instruct" +export LLM_MODEL_ID_CODEGEN="meta-llama/CodeLlama-7b-hf" export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" export TGI_LLM_ENDPOINT="http://${host_ip}:9009" diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml index f6882d9e8..2e56d6584 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/compose.yaml @@ -165,13 +165,10 @@ services: https_proxy: ${https_proxy} http_proxy: ${http_proxy} MEGA_SERVICE_HOST_IP: ${MEGA_SERVICE_HOST_IP} - EMBEDDING_SERVER_HOST_IP: ${EMBEDDING_SERVICE_HOST_IP} - EMBEDDING_SERVER_PORT: 6006 + EMBEDDING_SERVICE_HOST_IP: ${EMBEDDING_SERVICE_HOST_IP} RETRIEVER_SERVICE_HOST_IP: ${RETRIEVER_SERVICE_HOST_IP} - RERANK_SERVER_HOST_IP: ${RERANK_SERVICE_HOST_IP} - RERANK_SERVER_PORT: 8008 - LLM_SERVER_HOST_IP: ${LLM_SERVICE_HOST_IP_CHATQNA} - LLM_SERVER_PORT: 9009 ` + RERANK_SERVICE_HOST_IP: ${RERANK_SERVICE_HOST_IP} + LLM_SERVICE_HOST_IP: ${LLM_SERVICE_HOST_IP_CHATQNA} ipc: host restart: always tgi_service_codegen: diff --git a/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh b/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh index ca369b5ee..0139b532a 100644 --- a/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh +++ b/ProductivitySuite/docker_compose/intel/cpu/xeon/set_env.sh @@ -8,7 +8,7 @@ export COLLECTION_NAME="Conversations" export EMBEDDING_MODEL_ID="BAAI/bge-base-en-v1.5" export RERANK_MODEL_ID="BAAI/bge-reranker-base" export LLM_MODEL_ID="Intel/neural-chat-7b-v3-3" -export LLM_MODEL_ID_CODEGEN="Qwen/Qwen2.5-Coder-7B-Instruct" +export LLM_MODEL_ID_CODEGEN="meta-llama/CodeLlama-7b-hf" export TEI_EMBEDDING_ENDPOINT="http://${host_ip}:6006" export TEI_RERANKING_ENDPOINT="http://${host_ip}:8808" export TGI_LLM_ENDPOINT="http://${host_ip}:9009" diff --git a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml index 05788f61a..6c52c5d92 100644 --- a/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml +++ b/ProductivitySuite/kubernetes/intel/cpu/xeon/manifest/codegen.yaml @@ -39,7 +39,7 @@ metadata: app.kubernetes.io/version: "1.4" app.kubernetes.io/managed-by: Helm data: - MODEL_ID: "Qwen/Qwen2.5-Coder-7B-Instruct" + MODEL_ID: "meta-llama/CodeLlama-7b-hf" PORT: "2080" HUGGING_FACE_HUB_TOKEN: "insert-your-huggingface-token-here" HF_TOKEN: "insert-your-huggingface-token-here"