feat(models): add phi-2-chat, llava-1.6, bakllava, cerbero (#1879)

embedded/models/bakllava.yaml

@@ -0,0 +1,40 @@
+backend: llama-cpp
+context_size: 4096
+f16: true
+
+gpu_layers: 90
+mmap: true
+name: bakllava
+
+roles:
+  user: "USER:"
+  assistant: "ASSISTANT:"
+  system: "SYSTEM:"
+
+mmproj: bakllava-mmproj.gguf
+parameters:
+  model: bakllava.gguf
+  temperature: 0.2
+  top_k: 40
+  top_p: 0.95
+  seed: -1
+mirostat: 2
+mirostat_eta: 1.0
+mirostat_tau: 1.0
+
+template:
+  chat: |
+    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input}}
+    ASSISTANT:
+
+download_files:
+- filename: bakllava.gguf
+  uri: huggingface://mys/ggml_bakllava-1/ggml-model-q4_k.gguf
+- filename: bakllava-mmproj.gguf
+  uri: huggingface://mys/ggml_bakllava-1/mmproj-model-f16.gguf
+
+usage: |
+    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+        "model": "bakllava",
+        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

embedded/models/cerbero.yaml

@@ -0,0 +1,24 @@
+backend: llama
+context_size: 8192
+f16: false
+gpu_layers: 90
+name: cerbero
+mmap: false
+parameters:
+  model: huggingface://galatolo/cerbero-7b-gguf/ggml-model-Q8_0.gguf
+  top_k: 80
+  temperature: 0.2
+  top_p: 0.7
+template:
+  completion: "{{.Input}}"
+  chat: "Questa è una conversazione tra un umano ed un assistente AI.\n{{.Input}}\n[|Assistente|]  "
+roles:
+  user: "[|Umano|] "
+  system: "[|Umano|] "
+  assistant: "[|Assistente|] "
+
+stopwords:
+- "[|Umano|]"
+
+trimsuffix: 
+- "\n"

embedded/models/llava-1.5.yaml

@@ -0,0 +1,33 @@
+backend: llama-cpp
+context_size: 4096
+f16: true
+
+gpu_layers: 90
+mmap: true
+name: llava-1.5
+
+roles:
+  user: "USER:"
+  assistant: "ASSISTANT:"
+  system: "SYSTEM:"
+
+mmproj: llava-v1.5-7b-mmproj-Q8_0.gguf
+parameters:
+  model: llava-v1.5-7b-Q4_K.gguf
+
+template:
+  chat: |
+    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input}}
+    ASSISTANT:
+
+download_files:
+- filename: llava-v1.5-7b-Q4_K.gguf
+  uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-Q4_K.gguf
+- filename: llava-v1.5-7b-mmproj-Q8_0.gguf
+  uri: huggingface://jartine/llava-v1.5-7B-GGUF/llava-v1.5-7b-mmproj-Q8_0.gguf
+
+usage: |
+    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+        "model": "llava-1.5",
+        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

embedded/models/llava-1.6-mistral.yaml

@@ -0,0 +1,33 @@
+backend: llama-cpp
+context_size: 4096
+f16: true
+
+gpu_layers: 90
+mmap: true
+name: llava-1.6-mistral
+
+roles:
+  user: "USER:"
+  assistant: "ASSISTANT:"
+  system: "SYSTEM:"
+
+mmproj: llava-v1.6-7b-mmproj-f16.gguf
+parameters:
+  model: llava-v1.6-mistral-7b.gguf
+
+template:
+  chat: |
+    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input}}
+    ASSISTANT:
+
+download_files:
+- filename: llava-v1.6-mistral-7b.gguf
+  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q6_K.gguf
+- filename: llava-v1.6-7b-mmproj-f16.gguf
+  uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf
+
+usage: |
+    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+        "model": "llava-1.6-mistral",
+        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

embedded/models/llava-1.6-vicuna.yaml

@@ -0,0 +1,37 @@
+backend: llama-cpp
+context_size: 4096
+f16: true
+
+gpu_layers: 90
+mmap: true
+name: llava-1.6-vicuna
+
+roles:
+  user: "USER:"
+  assistant: "ASSISTANT:"
+  system: "SYSTEM:"
+
+mmproj: mmproj-vicuna7b-f16.gguf
+parameters:
+  model: vicuna-7b-q5_k.gguf
+  temperature: 0.2
+  top_k: 40
+  top_p: 0.95
+  seed: -1
+
+template:
+  chat: |
+    A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.
+    {{.Input}}
+    ASSISTANT:
+
+download_files:
+- filename: vicuna-7b-q5_k.gguf
+  uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf
+- filename: mmproj-vicuna7b-f16.gguf
+  uri: https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf
+
+usage: |
+    curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+        "model": "llava-1.6-vicuna",
+        "messages": [{"role": "user", "content": [{"type":"text", "text": "What is in the image?"}, {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" }}], "temperature": 0.9}]}'

embedded/models/phi-2-chat.yaml

@@ -0,0 +1,25 @@
+name: phi-2-chat
+mmap: true
+parameters:
+  model: huggingface://l3utterfly/phi-2-layla-v1-chatml-gguf/phi-2-layla-v1-chatml-Q8_0.gguf
+
+template:
+  chat_message: |
+    <|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}}
+    {{if .Content}}{{.Content}}{{end}}
+    <|im_end|>
+  chat: |
+    {{.Input}}
+    <|im_start|>assistant
+  completion: |
+    {{.Input}}
+context_size: 4096
+f16: true
+stopwords:
+- <|im_end|>
+- <dummy32000>
+usage: |
+      curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
+          "model": "phi-2-chat",
+          "messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
+      }'