model-conversion : add model card template for embeddings [no ci]

examples/model-conversion/Makefile

@@ -144,6 +144,15 @@ perplexity-run:
 hf-create-model:
 	@./scripts/utils/hf-create-model.py -m "${MODEL_NAME}" -ns "${NAMESPACE}" -b "${ORIGINAL_BASE_MODEL}"
 
+hf-create-model-dry-run:
+	@./scripts/utils/hf-create-model.py -m "${MODEL_NAME}" -ns "${NAMESPACE}" -b "${ORIGINAL_BASE_MODEL}" -d
+
+hf-create-model-embedding:
+	@./scripts/utils/hf-create-model.py -m "${MODEL_NAME}" -ns "${NAMESPACE}" -b "${ORIGINAL_BASE_MODEL}" -e
+
+hf-create-model-embedding-dry-run:
+	@./scripts/utils/hf-create-model.py -m "${MODEL_NAME}" -ns "${NAMESPACE}" -b "${ORIGINAL_BASE_MODEL}" -e -d
+
 hf-create-model-private:
 	@./scripts/utils/hf-create-model.py -m "${MODEL_NAME}" -ns "${NAMESPACE}" -b "${ORIGINAL_BASE_MODEL}" -p
 

examples/model-conversion/README.md

@@ -285,13 +285,21 @@ For the following targets a `HF_TOKEN` environment variable is required.
 This will create a new model repsository on Hugging Face with the specified
 model name.
 ```console
-(venv) $ make hf-create-model MODEL_NAME='TestModel' NAMESPACE="danbev"
+(venv) $ make hf-create-model MODEL_NAME='TestModel' NAMESPACE="danbev" ORIGINAL_BASE_MODEL="some-base-model"
 Repository ID:  danbev/TestModel-GGUF
 Repository created: https://huggingface.co/danbev/TestModel-GGUF
 ```
 Note that we append a `-GGUF` suffix to the model name to ensure a consistent
 naming convention for GGUF models.
 
+An embedding model can be created using the following command:
+```console
+(venv) $ make hf-create-model-embedding MODEL_NAME='TestEmbeddingModel' NAMESPACE="danbev" ORIGINAL_BASE_MODEL="some-base-model"
+```
+The only difference is that the model card for an embedding model will be different
+with regards to the llama-server command and also how to access/call the embedding
+endpoint.
+
 ### Upload a GGUF model to model repository
 The following target uploads a model to an existing Hugging Face model repository.
 ```console

examples/model-conversion/scripts/embedding/modelcard.template

@@ -0,0 +1,48 @@
+---
+base_model:
+- {base_model}
+---
+# {model_name} GGUF
+
+Recommended way to run this model:
+
+```sh
+llama-server -hf {namespace}/{model_name}-GGUF
+```
+
+Then the endpoint can be accessed at http://localhost:8080/embedding, for
+example using `curl`:
+```console
+curl --request POST \
+    --url http://localhost:8080/embedding \
+    --header "Content-Type: application/json" \
+    --data '{{"input": "Hello embeddings"}}' \
+    --silent
+```
+
+Alternatively, the `llama-embedding` command line tool can be used:
+```sh
+llama-embedding -hf {namespace}/{model_name}-GGUF --verbose-prompt -p "Hello embeddings"
+```
+
+#### embd_normalize
+When a model uses pooling, or the pooling method is specified using `--pooling`,
+the normalization can be controlled by the `embd_normalize` parameter.
+
+The default value is `2` which means that the embeddings are normalized using
+the Euclidean norm (L2). Other options are:
+* -1 No normalization
+*  0 Max absolute
+*  1 Taxicab
+*  2 Euclidean/L2
+* \>2 P-Norm
+
+This can be passed in the request body to `llama-server`, for example:
+```sh
+    --data '{{"input": "Hello embeddings", "embd_normalize": -1}}' \
+```
+
+And for `llama-embedding`, by passing `--embd-normalize <value>`, for example:
+```sh
+llama-embedding -hf {namespace}/{model_name}-GGUF  --embd-normalize -1 -p "Hello embeddings"
+```

examples/model-conversion/scripts/utils/hf-create-model.py

@@ -26,38 +26,53 @@ def load_template_and_substitute(template_path, **kwargs):
 parser.add_argument('--org-base-model', '-b', help='Original Base model name', default="")
 parser.add_argument('--no-card', action='store_true', help='Skip creating model card')
 parser.add_argument('--private', '-p', action='store_true', help='Create private model')
+parser.add_argument('--embedding', '-e', action='store_true', help='Use embedding model card template')
+parser.add_argument('--dry-run', '-d', action='store_true', help='Print repository info and template without creating repository')
 
 args = parser.parse_args()
 
 repo_id = f"{args.namespace}/{args.model_name}-GGUF"
 print("Repository ID: ", repo_id)
 
-repo_url = api.create_repo(
-    repo_id=repo_id,
-    repo_type="model",
-    private=args.private,
-    exist_ok=False
-)
+repo_url = None
+if not args.dry_run:
+    repo_url = api.create_repo(
+        repo_id=repo_id,
+        repo_type="model",
+        private=args.private,
+        exist_ok=False
+    )
 
 if not args.no_card:
-    template_path = "scripts/readme.md.template"
+    if args.embedding:
+        template_path = "scripts/embedding/modelcard.template"
+    else:
+        template_path = "scripts/causal/modelcard.template"
+
+    print("Template path: ", template_path)
+
     model_card_content = load_template_and_substitute(
         template_path,
         model_name=args.model_name,
         namespace=args.namespace,
         base_model=args.org_base_model,
     )
 
-    if model_card_content:
-        api.upload_file(
-            path_or_fileobj=model_card_content.encode('utf-8'),
-            path_in_repo="README.md",
-            repo_id=repo_id
-        )
-        print("Model card created successfully.")
+    if args.dry_run:
+        print("\nTemplate Content:\n")
+        print(model_card_content)
     else:
-        print("Failed to create model card.")
+        if model_card_content:
+            api.upload_file(
+                path_or_fileobj=model_card_content.encode('utf-8'),
+                path_in_repo="README.md",
+                repo_id=repo_id
+            )
+            print("Model card created successfully.")
+        else:
+            print("Failed to create model card.")
 
-print(f"Repository created: {repo_url}")
+if not args.dry_run and repo_url:
+    print(f"Repository created: {repo_url}")