feat: add /models/apply endpoint to prepare models (#286)

tests/fixtures/completion.tmpl

@@ -1 +0,0 @@
-{{.Input}}

tests/fixtures/config.yaml

@@ -1,32 +0,0 @@
-- name: list1
-  parameters:
-    model: testmodel
-    top_p: 80
-    top_k: 0.9
-    temperature: 0.1
-  context_size: 10
-  stopwords:
-  - "HUMAN:"
-  - "### Response:"
-  roles:
-    user: "HUMAN:"
-    system: "GPT:"
-  template:
-    completion: completion
-    chat: ggml-gpt4all-j
-- name: list2
-  parameters:
-    top_p: 80
-    top_k: 0.9
-    temperature: 0.1
-    model: testmodel
-  context_size: 10
-  stopwords:
-  - "HUMAN:"
-  - "### Response:"
-  roles:
-    user: "HUMAN:"
-    system: "GPT:"
-  template:
-    completion: completion
-    chat: ggml-gpt4all-j

tests/fixtures/embeddings.yaml

@@ -1,6 +0,0 @@
-name: text-embedding-ada-002
-parameters:
-  model: bert
-threads: 14
-backend: bert-embeddings
-embeddings: true

tests/fixtures/gallery_simple.yaml

@@ -0,0 +1,40 @@
+name: "cerebras"
+description: |
+    cerebras
+license: "Apache 2.0"
+
+config_file: |
+    parameters:
+      model: cerebras
+      top_k: 80
+      temperature: 0.2
+      top_p: 0.7
+    context_size: 1024
+    stopwords:
+    - "HUMAN:"
+    - "GPT:"
+    roles:
+      user: ""
+      system: ""
+    template:
+      completion: "cerebras-completion"
+      chat: cerebras-chat
+
+files:
+    - filename: "cerebras"
+      sha256: "c947051ae4dba9530ca55d923a7a484acd65664c8633462c8ccd4bb7848f2c65"
+      uri: "https://huggingface.co/concedo/cerebras-111M-ggml/resolve/main/cerebras-111m-q4_2.bin"
+
+prompt_templates:
+    - name: "cerebras-completion"
+      content: |
+        Complete the prompt
+        ### Prompt:
+        {{.Input}}
+        ### Response:
+    - name: "cerebras-chat"
+      content: |
+        The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
+        ### Prompt:
+        {{.Input}}
+        ### Response:

tests/fixtures/ggml-gpt4all-j.tmpl

@@ -1,4 +0,0 @@
-The prompt below is a question to answer, a task to complete, or a conversation to respond to; decide which and write an appropriate response.
-### Prompt:
-{{.Input}}
-### Response:

tests/fixtures/gpt4.yaml

@@ -1,16 +0,0 @@
-name: gpt4all
-parameters:
-  model: testmodel
-  top_p: 80
-  top_k: 0.9
-  temperature: 0.1
-context_size: 10
-stopwords:
-- "HUMAN:"
-- "### Response:"
-roles:
-  user: "HUMAN:"
-  system: "GPT:"
-template:
-  completion: completion
-  chat: ggml-gpt4all-j

tests/fixtures/gpt4_2.yaml

@@ -1,16 +0,0 @@
-name: gpt4all-2
-parameters:
-  model: testmodel
-  top_p: 80
-  top_k: 0.9
-  temperature: 0.1
-context_size: 10
-stopwords:
-- "HUMAN:"
-- "### Response:"
-roles:
-  user: "HUMAN:"
-  system: "GPT:"
-template:
-  completion: completion
-  chat: ggml-gpt4all-j

tests/fixtures/rwkv.yaml

@@ -1,19 +0,0 @@
-name: rwkv_test
-parameters:
-  model: rwkv
-  top_k: 80
-  temperature: 0.9
-  max_tokens: 100
-  top_p: 0.8
-context_size: 1024
-threads: 14
-backend: "rwkv"
-cutwords:
-- "Bob:.*"
-roles:
-  user: "Bob:"
-  system: "Alice:"
-  assistant: "Alice:"
-template:
-  completion: rwkv_completion
-  chat: rwkv_chat

tests/fixtures/rwkv_chat.tmpl

@@ -1,13 +0,0 @@
-The following is a verbose detailed conversation between Bob and a woman, Alice. Alice is intelligent, friendly and likeable. Alice is likely to agree with Bob.
-
-Bob: Hello Alice, how are you doing?
-
-Alice: Hi Bob! Thanks, I'm fine. What about you?
-
-Bob: I am very good! It's nice to see you. Would you mind me chatting with you for a while?
-
-Alice: Not at all! I'm listening.
-
-{{.Input}}
-
-Alice: 

tests/fixtures/rwkv_completion.tmpl

@@ -1 +0,0 @@
-Complete the following sentence: {{.Input}} 

tests/fixtures/whisper.yaml

@@ -1,4 +0,0 @@
-name: whisper-1
-backend: whisper
-parameters:
-  model: whisper-en