mirror of
https://github.com/mudler/LocalAI.git
synced 2025-03-14 08:16:48 +00:00
feat(aio): update AIO image defaults (#5002)
* feat(aio): update AIO image defaults cpu: - text-to-text: llama3.1 - embeddings: granite-embeddings - vision: moonream2 gpu/intel: - text-to-text: localai-functioncall-qwen2.5-7b-v0.5 - embeddings: granite-embeddings - vision: minicpm Signed-off-by: Ettore Di Giacinto <mudler@localai.io> * feat(aio): use minicpm as moondream2 stopped working https://github.com/ggml-org/llama.cpp/pull/12322#issuecomment-2717483759 Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
GitHub
parent
e878556e98
commit
9f5dcf2d1e
@ -1,7 +1,7 @@
|
||||
name: text-embedding-ada-002
|
||||
embeddings: true
|
||||
name: text-embedding-ada-002
|
||||
parameters:
|
||||
model: huggingface://hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/llama-3.2-1b-instruct-q4_k_m.gguf
|
||||
model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
|
||||
|
||||
usage: |
|
||||
You can test this model with curl like this:
|
||||
|
||||
@ -1,101 +1,57 @@
|
||||
name: gpt-4
|
||||
mmap: true
|
||||
parameters:
|
||||
model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
|
||||
context_size: 8192
|
||||
|
||||
stopwords:
|
||||
- "<|im_end|>"
|
||||
- "<dummy32000>"
|
||||
- "</tool_call>"
|
||||
- "<|eot_id|>"
|
||||
- "<|end_of_text|>"
|
||||
|
||||
f16: true
|
||||
function:
|
||||
# disable injecting the "answer" tool
|
||||
disable_no_action: true
|
||||
|
||||
grammar:
|
||||
# This allows the grammar to also return messages
|
||||
mixed_mode: true
|
||||
# Suffix to add to the grammar
|
||||
#prefix: '<tool_call>\n'
|
||||
# Force parallel calls in the grammar
|
||||
# parallel_calls: true
|
||||
|
||||
return_name_in_function_response: true
|
||||
# Without grammar uncomment the lines below
|
||||
# Warning: this is relying only on the capability of the
|
||||
# LLM model to generate the correct function call.
|
||||
json_regex_match:
|
||||
- "(?s)<tool_call>(.*?)</tool_call>"
|
||||
- "(?s)<tool_call>(.*?)"
|
||||
replace_llm_results:
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
value: ""
|
||||
replace_function_results:
|
||||
# Replace everything that is not JSON array or object
|
||||
#
|
||||
- key: '(?s)^[^{\[]*'
|
||||
value: ""
|
||||
- key: '(?s)[^}\]]*$'
|
||||
value: ""
|
||||
- key: "'([^']*?)'"
|
||||
value: "_DQUOTE_${1}_DQUOTE_"
|
||||
- key: '\\"'
|
||||
value: "__TEMP_QUOTE__"
|
||||
- key: "\'"
|
||||
value: "'"
|
||||
- key: "_DQUOTE_"
|
||||
value: '"'
|
||||
- key: "__TEMP_QUOTE__"
|
||||
value: '"'
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
value: ""
|
||||
|
||||
no_mixed_free_string: true
|
||||
schema_type: llama3.1 # or JSON is supported too (json)
|
||||
response_regex:
|
||||
- <function=(?P<name>\w+)>(?P<arguments>.*)</function>
|
||||
mmap: true
|
||||
name: gpt-4
|
||||
parameters:
|
||||
model: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- <|eot_id|>
|
||||
- <|end_of_text|>
|
||||
template:
|
||||
chat: |
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
{{.Input }}
|
||||
<|start_header_id|>assistant<|end_header_id|>
|
||||
chat_message: |
|
||||
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
|
||||
{{- if .FunctionCall }}
|
||||
<tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
<tool_response>
|
||||
{{- end }}
|
||||
{{- if .Content}}
|
||||
{{.Content }}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall }}
|
||||
</tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
</tool_response>
|
||||
{{- end }}<|im_end|>
|
||||
<|start_header_id|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}<|end_header_id|>
|
||||
{{ if .FunctionCall -}}
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
The Function was executed and the response was:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content -}}
|
||||
{{ else if .FunctionCall -}}
|
||||
{{ range .FunctionCall }}
|
||||
[{{.FunctionCall.Name}}({{.FunctionCall.Arguments}})]
|
||||
{{ end }}
|
||||
{{ end -}}
|
||||
<|eot_id|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
function: |-
|
||||
<|im_start|>system
|
||||
You are a function calling AI model.
|
||||
Here are the available tools:
|
||||
<tools>
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
</tools>
|
||||
You should call the tools provided to you sequentially
|
||||
Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
|
||||
<scratchpad>
|
||||
{step-by-step reasoning and plan in bullet points}
|
||||
</scratchpad>
|
||||
For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
|
||||
<tool_call>
|
||||
{"arguments": <args-dict>, "name": <function-name>}
|
||||
</tool_call><|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
function: |
|
||||
<|start_header_id|>system<|end_header_id|>
|
||||
You are an expert in composing functions. You are given a question and a set of possible functions.
|
||||
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
|
||||
If none of the functions can be used, point it out. If the given question lacks the parameters required by the function, also point it out. You should only return the function call in tools call sections.
|
||||
If you decide to invoke any of the function(s), you MUST put it in the format as follows:
|
||||
[func_name1(params_name1=params_value1,params_name2=params_value2,...),func_name2(params_name1=params_value1,params_name2=params_value2,...)]
|
||||
You SHOULD NOT include any other text in the response.
|
||||
Here is a list of functions in JSON format that you can invoke.
|
||||
{{toJson .Functions}}
|
||||
<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
{{.Input}}
|
||||
<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
download_files:
|
||||
- filename: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
|
||||
sha256: 2e220a14ba4328fee38cf36c2c068261560f999fadb5725ce5c6d977cb5126b5
|
||||
uri: huggingface://bartowski/Hermes-3-Llama-3.2-3B-GGUF/Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
|
||||
@ -1,31 +1,49 @@
|
||||
backend: llama-cpp
|
||||
context_size: 4096
|
||||
f16: true
|
||||
mmap: true
|
||||
mmproj: minicpm-v-2_6-mmproj-f16.gguf
|
||||
name: gpt-4o
|
||||
|
||||
roles:
|
||||
user: "USER:"
|
||||
assistant: "ASSISTANT:"
|
||||
system: "SYSTEM:"
|
||||
|
||||
mmproj: bakllava-mmproj.gguf
|
||||
parameters:
|
||||
model: bakllava.gguf
|
||||
|
||||
model: minicpm-v-2_6-Q4_K_M.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- </s>
|
||||
- <|endoftext|>
|
||||
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 -}}
|
||||
<|im_start|>assistant
|
||||
chat_message: |
|
||||
<|im_start|>{{ .RoleName }}
|
||||
{{ if .FunctionCall -}}
|
||||
Function call:
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
Function response:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content }}
|
||||
{{ end -}}
|
||||
{{ if .FunctionCall -}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{ end -}}<|im_end|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
ASSISTANT:
|
||||
function: |
|
||||
<|im_start|>system
|
||||
You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
For each function call return a json object with function name and arguments
|
||||
<|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>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": "gpt-4-vision-preview",
|
||||
"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}]}'
|
||||
- filename: minicpm-v-2_6-Q4_K_M.gguf
|
||||
sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
|
||||
- filename: minicpm-v-2_6-mmproj-f16.gguf
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
|
||||
sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
|
||||
@ -1,7 +1,7 @@
|
||||
embeddings: true
|
||||
name: text-embedding-ada-002
|
||||
backend: sentencetransformers
|
||||
parameters:
|
||||
model: all-MiniLM-L6-v2
|
||||
model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
|
||||
|
||||
usage: |
|
||||
You can test this model with curl like this:
|
||||
|
||||
@ -1,101 +1,53 @@
|
||||
name: gpt-4
|
||||
mmap: true
|
||||
parameters:
|
||||
model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
|
||||
context_size: 8192
|
||||
|
||||
stopwords:
|
||||
- "<|im_end|>"
|
||||
- "<dummy32000>"
|
||||
- "</tool_call>"
|
||||
- "<|eot_id|>"
|
||||
- "<|end_of_text|>"
|
||||
|
||||
context_size: 4096
|
||||
f16: true
|
||||
function:
|
||||
# disable injecting the "answer" tool
|
||||
disable_no_action: true
|
||||
|
||||
capture_llm_results:
|
||||
- (?s)<Thought>(.*?)</Thought>
|
||||
grammar:
|
||||
# This allows the grammar to also return messages
|
||||
mixed_mode: true
|
||||
# Suffix to add to the grammar
|
||||
#prefix: '<tool_call>\n'
|
||||
# Force parallel calls in the grammar
|
||||
# parallel_calls: true
|
||||
|
||||
return_name_in_function_response: true
|
||||
# Without grammar uncomment the lines below
|
||||
# Warning: this is relying only on the capability of the
|
||||
# LLM model to generate the correct function call.
|
||||
json_regex_match:
|
||||
- "(?s)<tool_call>(.*?)</tool_call>"
|
||||
- "(?s)<tool_call>(.*?)"
|
||||
properties_order: name,arguments
|
||||
json_regex_match:
|
||||
- (?s)<Output>(.*?)</Output>
|
||||
replace_llm_results:
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
- key: (?s)<Thought>(.*?)</Thought>
|
||||
value: ""
|
||||
replace_function_results:
|
||||
# Replace everything that is not JSON array or object
|
||||
#
|
||||
- key: '(?s)^[^{\[]*'
|
||||
value: ""
|
||||
- key: '(?s)[^}\]]*$'
|
||||
value: ""
|
||||
- key: "'([^']*?)'"
|
||||
value: "_DQUOTE_${1}_DQUOTE_"
|
||||
- key: '\\"'
|
||||
value: "__TEMP_QUOTE__"
|
||||
- key: "\'"
|
||||
value: "'"
|
||||
- key: "_DQUOTE_"
|
||||
value: '"'
|
||||
- key: "__TEMP_QUOTE__"
|
||||
value: '"'
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
value: ""
|
||||
|
||||
mmap: true
|
||||
name: gpt-4
|
||||
parameters:
|
||||
model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- </s>
|
||||
template:
|
||||
chat: |
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
chat_message: |
|
||||
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
|
||||
{{- if .FunctionCall }}
|
||||
<tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
<tool_response>
|
||||
{{- end }}
|
||||
{{- if .Content}}
|
||||
<|im_start|>{{ .RoleName }}
|
||||
{{ if .FunctionCall -}}
|
||||
Function call:
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
Function response:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content }}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall}}
|
||||
{{ end -}}
|
||||
{{ if .FunctionCall -}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall }}
|
||||
</tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
</tool_response>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end -}}<|im_end|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
function: |-
|
||||
function: |
|
||||
<|im_start|>system
|
||||
You are a function calling AI model.
|
||||
Here are the available tools:
|
||||
<tools>
|
||||
You are an AI assistant that executes function calls, and these are the tools at your disposal:
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
</tools>
|
||||
You should call the tools provided to you sequentially
|
||||
Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
|
||||
<scratchpad>
|
||||
{step-by-step reasoning and plan in bullet points}
|
||||
</scratchpad>
|
||||
For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
|
||||
<tool_call>
|
||||
{"arguments": <args-dict>, "name": <function-name>}
|
||||
</tool_call><|im_end|>
|
||||
<|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
<|im_start|>assistant
|
||||
|
||||
download_files:
|
||||
- filename: localai-functioncall-phi-4-v0.3-q4_k_m.gguf
|
||||
sha256: 23fee048ded2a6e2e1a7b6bbefa6cbf83068f194caa9552aecbaa00fec8a16d5
|
||||
uri: huggingface://mudler/LocalAI-functioncall-phi-4-v0.3-Q4_K_M-GGUF/localai-functioncall-phi-4-v0.3-q4_k_m.gguf
|
||||
@ -1,35 +1,49 @@
|
||||
backend: llama-cpp
|
||||
context_size: 4096
|
||||
f16: true
|
||||
mmap: true
|
||||
mmproj: minicpm-v-2_6-mmproj-f16.gguf
|
||||
name: gpt-4o
|
||||
|
||||
roles:
|
||||
user: "USER:"
|
||||
assistant: "ASSISTANT:"
|
||||
system: "SYSTEM:"
|
||||
|
||||
mmproj: llava-v1.6-7b-mmproj-f16.gguf
|
||||
parameters:
|
||||
model: llava-v1.6-mistral-7b.Q5_K_M.gguf
|
||||
temperature: 0.2
|
||||
top_k: 40
|
||||
top_p: 0.95
|
||||
seed: -1
|
||||
|
||||
model: minicpm-v-2_6-Q4_K_M.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- </s>
|
||||
- <|endoftext|>
|
||||
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 -}}
|
||||
<|im_start|>assistant
|
||||
chat_message: |
|
||||
<|im_start|>{{ .RoleName }}
|
||||
{{ if .FunctionCall -}}
|
||||
Function call:
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
Function response:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content }}
|
||||
{{ end -}}
|
||||
{{ if .FunctionCall -}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{ end -}}<|im_end|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
ASSISTANT:
|
||||
function: |
|
||||
<|im_start|>system
|
||||
You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
For each function call return a json object with function name and arguments
|
||||
<|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
|
||||
download_files:
|
||||
- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf
|
||||
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.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": "gpt-4-vision-preview",
|
||||
"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}]}'
|
||||
- filename: minicpm-v-2_6-Q4_K_M.gguf
|
||||
sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
|
||||
- filename: minicpm-v-2_6-mmproj-f16.gguf
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
|
||||
sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
|
||||
@ -1,7 +1,7 @@
|
||||
embeddings: true
|
||||
name: text-embedding-ada-002
|
||||
backend: sentencetransformers
|
||||
parameters:
|
||||
model: all-MiniLM-L6-v2
|
||||
model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
|
||||
|
||||
usage: |
|
||||
You can test this model with curl like this:
|
||||
|
||||
@ -1,103 +1,53 @@
|
||||
name: gpt-4
|
||||
mmap: false
|
||||
context_size: 8192
|
||||
|
||||
f16: false
|
||||
parameters:
|
||||
model: huggingface://NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
|
||||
|
||||
stopwords:
|
||||
- "<|im_end|>"
|
||||
- "<dummy32000>"
|
||||
- "</tool_call>"
|
||||
- "<|eot_id|>"
|
||||
- "<|end_of_text|>"
|
||||
|
||||
context_size: 4096
|
||||
f16: true
|
||||
function:
|
||||
# disable injecting the "answer" tool
|
||||
disable_no_action: true
|
||||
|
||||
capture_llm_results:
|
||||
- (?s)<Thought>(.*?)</Thought>
|
||||
grammar:
|
||||
# This allows the grammar to also return messages
|
||||
mixed_mode: true
|
||||
# Suffix to add to the grammar
|
||||
#prefix: '<tool_call>\n'
|
||||
# Force parallel calls in the grammar
|
||||
# parallel_calls: true
|
||||
|
||||
return_name_in_function_response: true
|
||||
# Without grammar uncomment the lines below
|
||||
# Warning: this is relying only on the capability of the
|
||||
# LLM model to generate the correct function call.
|
||||
json_regex_match:
|
||||
- "(?s)<tool_call>(.*?)</tool_call>"
|
||||
- "(?s)<tool_call>(.*?)"
|
||||
properties_order: name,arguments
|
||||
json_regex_match:
|
||||
- (?s)<Output>(.*?)</Output>
|
||||
replace_llm_results:
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
- key: (?s)<Thought>(.*?)</Thought>
|
||||
value: ""
|
||||
replace_function_results:
|
||||
# Replace everything that is not JSON array or object
|
||||
#
|
||||
- key: '(?s)^[^{\[]*'
|
||||
value: ""
|
||||
- key: '(?s)[^}\]]*$'
|
||||
value: ""
|
||||
- key: "'([^']*?)'"
|
||||
value: "_DQUOTE_${1}_DQUOTE_"
|
||||
- key: '\\"'
|
||||
value: "__TEMP_QUOTE__"
|
||||
- key: "\'"
|
||||
value: "'"
|
||||
- key: "_DQUOTE_"
|
||||
value: '"'
|
||||
- key: "__TEMP_QUOTE__"
|
||||
value: '"'
|
||||
# Drop the scratchpad content from responses
|
||||
- key: "(?s)<scratchpad>.*</scratchpad>"
|
||||
value: ""
|
||||
|
||||
mmap: true
|
||||
name: gpt-4
|
||||
parameters:
|
||||
model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- </s>
|
||||
template:
|
||||
chat: |
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
chat_message: |
|
||||
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "tool"}}tool{{else if eq .RoleName "user"}}user{{end}}
|
||||
{{- if .FunctionCall }}
|
||||
<tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
<tool_response>
|
||||
{{- end }}
|
||||
{{- if .Content}}
|
||||
<|im_start|>{{ .RoleName }}
|
||||
{{ if .FunctionCall -}}
|
||||
Function call:
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
Function response:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content }}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall}}
|
||||
{{ end -}}
|
||||
{{ if .FunctionCall -}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{- end }}
|
||||
{{- if .FunctionCall }}
|
||||
</tool_call>
|
||||
{{- else if eq .RoleName "tool" }}
|
||||
</tool_response>
|
||||
{{- end }}<|im_end|>
|
||||
{{ end -}}<|im_end|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
function: |-
|
||||
function: |
|
||||
<|im_start|>system
|
||||
You are a function calling AI model.
|
||||
Here are the available tools:
|
||||
<tools>
|
||||
You are an AI assistant that executes function calls, and these are the tools at your disposal:
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
</tools>
|
||||
You should call the tools provided to you sequentially
|
||||
Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows:
|
||||
<scratchpad>
|
||||
{step-by-step reasoning and plan in bullet points}
|
||||
</scratchpad>
|
||||
For each function call return a json object with function name and arguments within <tool_call> XML tags as follows:
|
||||
<tool_call>
|
||||
{"arguments": <args-dict>, "name": <function-name>}
|
||||
</tool_call><|im_end|>
|
||||
<|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
|
||||
download_files:
|
||||
- filename: localai-functioncall-phi-4-v0.3-q4_k_m.gguf
|
||||
sha256: 23fee048ded2a6e2e1a7b6bbefa6cbf83068f194caa9552aecbaa00fec8a16d5
|
||||
uri: huggingface://mudler/LocalAI-functioncall-phi-4-v0.3-Q4_K_M-GGUF/localai-functioncall-phi-4-v0.3-q4_k_m.gguf
|
||||
@ -1,35 +1,50 @@
|
||||
backend: llama-cpp
|
||||
context_size: 4096
|
||||
mmap: false
|
||||
f16: false
|
||||
f16: true
|
||||
mmap: true
|
||||
mmproj: minicpm-v-2_6-mmproj-f16.gguf
|
||||
name: gpt-4o
|
||||
|
||||
roles:
|
||||
user: "USER:"
|
||||
assistant: "ASSISTANT:"
|
||||
system: "SYSTEM:"
|
||||
|
||||
mmproj: llava-v1.6-7b-mmproj-f16.gguf
|
||||
parameters:
|
||||
model: llava-v1.6-mistral-7b.Q5_K_M.gguf
|
||||
temperature: 0.2
|
||||
top_k: 40
|
||||
top_p: 0.95
|
||||
seed: -1
|
||||
|
||||
model: minicpm-v-2_6-Q4_K_M.gguf
|
||||
stopwords:
|
||||
- <|im_end|>
|
||||
- <dummy32000>
|
||||
- </s>
|
||||
- <|endoftext|>
|
||||
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 -}}
|
||||
<|im_start|>assistant
|
||||
chat_message: |
|
||||
<|im_start|>{{ .RoleName }}
|
||||
{{ if .FunctionCall -}}
|
||||
Function call:
|
||||
{{ else if eq .RoleName "tool" -}}
|
||||
Function response:
|
||||
{{ end -}}
|
||||
{{ if .Content -}}
|
||||
{{.Content }}
|
||||
{{ end -}}
|
||||
{{ if .FunctionCall -}}
|
||||
{{toJson .FunctionCall}}
|
||||
{{ end -}}<|im_end|>
|
||||
completion: |
|
||||
{{.Input}}
|
||||
ASSISTANT:
|
||||
function: |
|
||||
<|im_start|>system
|
||||
You are a function calling AI model. You are provided with functions to execute. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools:
|
||||
{{range .Functions}}
|
||||
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
|
||||
{{end}}
|
||||
For each function call return a json object with function name and arguments
|
||||
<|im_end|>
|
||||
{{.Input -}}
|
||||
<|im_start|>assistant
|
||||
|
||||
|
||||
download_files:
|
||||
- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf
|
||||
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.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": "gpt-4-vision-preview",
|
||||
"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}]}'
|
||||
- filename: minicpm-v-2_6-Q4_K_M.gguf
|
||||
sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
|
||||
- filename: minicpm-v-2_6-mmproj-f16.gguf
|
||||
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
|
||||
sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
|
||||
Loading…
x
Reference in New Issue
Block a user