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

tests/models_fixtures/completion.tmpl

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

tests/models_fixtures/config.yaml

@@ -0,0 +1,32 @@
+- 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/models_fixtures/embeddings.yaml

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

tests/models_fixtures/ggml-gpt4all-j.tmpl

@@ -0,0 +1,4 @@
+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/models_fixtures/gpt4.yaml

@@ -0,0 +1,16 @@
+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/models_fixtures/gpt4_2.yaml

@@ -0,0 +1,16 @@
+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/models_fixtures/rwkv.yaml

@@ -0,0 +1,19 @@
+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/models_fixtures/rwkv_chat.tmpl

@@ -0,0 +1,13 @@
+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/models_fixtures/rwkv_completion.tmpl

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

tests/models_fixtures/whisper.yaml

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