ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-04 09:42:53 +00:00
Code Issues Actions 16 Packages Projects Releases Wiki Activity

feat(aio): update AIO image defaults (#5002)

Browse Source 
* 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 2025-03-12 12:55:06 +01:00 committed by GitHub
parent e878556e98
commit 9f5dcf2d1e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
9 changed files with 244 additions and 339 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
aio/cpu/embeddings.yaml
View File

@ -1,7 +1,7 @@
name: text-embedding-ada-002
embeddings: true embeddings: true
name: text-embedding-ada-002
parameters: 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: | usage: |
You can test this model with curl like this: You can test this model with curl like this:

142
aio/cpu/text-to-text.yaml
View File

@ -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 context_size: 8192
f16: true
stopwords:
- "<|im_end|>"
- "<dummy32000>"
- "</tool_call>"
- "<|eot_id|>"
- "<|end_of_text|>"
function: function:
# disable injecting the "answer" tool
disable_no_action: true
grammar: grammar:
# This allows the grammar to also return messages no_mixed_free_string: true
mixed_mode: true schema_type: llama3.1 # or JSON is supported too (json)
# Suffix to add to the grammar response_regex:
#prefix: '<tool_call>\n' - <function=(?P<name>\w+)>(?P<arguments>.*)</function>
# Force parallel calls in the grammar mmap: true
# parallel_calls: true name: gpt-4
parameters:
return_name_in_function_response: true model: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
# Without grammar uncomment the lines below stopwords:
# Warning: this is relying only on the capability of the - <|im_end|>
# LLM model to generate the correct function call. - <dummy32000>
json_regex_match: - <|eot_id|>
- "(?s)<tool_call>(.*?)</tool_call>" - <|end_of_text|>
- "(?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: ""
template: template:
chat: | chat: |
{{.Input -}} <|begin_of_text|><|start_header_id|>system<|end_header_id|>
<|im_start|>assistant You are a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>
{{.Input }}
<|start_header_id|>assistant<|end_header_id|>
chat_message: | 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}} <|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 }} {{ if .FunctionCall -}}
<tool_call> {{ else if eq .RoleName "tool" -}}
{{- else if eq .RoleName "tool" }} The Function was executed and the response was:
<tool_response> {{ end -}}
{{- end }} {{ if .Content -}}
{{- if .Content}} {{.Content -}}
{{.Content }} {{ else if .FunctionCall -}}
{{- end }} {{ range .FunctionCall }}
{{- if .FunctionCall}} [{{.FunctionCall.Name}}({{.FunctionCall.Arguments}})]
{{toJson .FunctionCall}} {{ end }}
{{- end }} {{ end -}}
{{- if .FunctionCall }} <|eot_id|>
</tool_call>
{{- else if eq .RoleName "tool" }}
</tool_response>
{{- end }}<|im_end|>
completion: | completion: |
{{.Input}} {{.Input}}
function: |- function: |
<|im_start|>system <|start_header_id|>system<|end_header_id|>
You are a function calling AI model. You are an expert in composing functions. You are given a question and a set of possible functions.
Here are the available tools: Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
<tools> 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.
{{range .Functions}} If you decide to invoke any of the function(s), you MUST put it in the format as follows:
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }} [func_name1(params_name1=params_value1,params_name2=params_value2,...),func_name2(params_name1=params_value1,params_name2=params_value2,...)]
{{end}} You SHOULD NOT include any other text in the response.
</tools> Here is a list of functions in JSON format that you can invoke.
You should call the tools provided to you sequentially {{toJson .Functions}}
Please use <scratchpad> XML tags to record your reasoning and planning before you call the functions as follows: <|eot_id|><|start_header_id|>user<|end_header_id|>
<scratchpad> {{.Input}}
{step-by-step reasoning and plan in bullet points} <|eot_id|><|start_header_id|>assistant<|end_header_id|>
</scratchpad>
For each function call return a json object with function name and arguments within <tool_call> XML tags as follows: download_files:
<tool_call> - filename: Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
{"arguments": <args-dict>, "name": <function-name>} sha256: 2e220a14ba4328fee38cf36c2c068261560f999fadb5725ce5c6d977cb5126b5
</tool_call><|im_end|> uri: huggingface://bartowski/Hermes-3-Llama-3.2-3B-GGUF/Hermes-3-Llama-3.2-3B-Q4_K_M.gguf
{{.Input -}}
<|im_start|>assistant

60
aio/cpu/vision.yaml
View File

@ -1,31 +1,49 @@
backend: llama-cpp
context_size: 4096 context_size: 4096
f16: true f16: true
mmap: true mmap: true
mmproj: minicpm-v-2_6-mmproj-f16.gguf
name: gpt-4o name: gpt-4o
roles:
user: "USER:"
assistant: "ASSISTANT:"
system: "SYSTEM:"
mmproj: bakllava-mmproj.gguf
parameters: parameters:
model: bakllava.gguf model: minicpm-v-2_6-Q4_K_M.gguf
stopwords:
- <|im_end|>
- <dummy32000>
- </s>
- <|endoftext|>
template: template:
chat: | 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}} {{.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: download_files:
- filename: bakllava.gguf - filename: minicpm-v-2_6-Q4_K_M.gguf
uri: huggingface://mys/ggml_bakllava-1/ggml-model-q4_k.gguf sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
- filename: bakllava-mmproj.gguf uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
uri: huggingface://mys/ggml_bakllava-1/mmproj-model-f16.gguf - filename: minicpm-v-2_6-mmproj-f16.gguf
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
usage: | sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
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}]}'

4
aio/gpu-8g/embeddings.yaml
View File

@ -1,7 +1,7 @@
embeddings: true
name: text-embedding-ada-002 name: text-embedding-ada-002
backend: sentencetransformers
parameters: parameters:
model: all-MiniLM-L6-v2 model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
usage: | usage: |
You can test this model with curl like this: You can test this model with curl like this:

118
aio/gpu-8g/text-to-text.yaml
View File

@ -1,101 +1,53 @@
name: gpt-4 context_size: 4096
mmap: true f16: 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|>"
function: function:
# disable injecting the "answer" tool capture_llm_results:
disable_no_action: true - (?s)<Thought>(.*?)</Thought>
grammar: grammar:
# This allows the grammar to also return messages properties_order: name,arguments
mixed_mode: true json_regex_match:
# Suffix to add to the grammar - (?s)<Output>(.*?)</Output>
#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: replace_llm_results:
# Drop the scratchpad content from responses - key: (?s)<Thought>(.*?)</Thought>
- key: "(?s)<scratchpad>.*</scratchpad>"
value: "" value: ""
replace_function_results: mmap: true
# Replace everything that is not JSON array or object name: gpt-4
# parameters:
- key: '(?s)^[^{\[]*' model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
value: "" stopwords:
- key: '(?s)[^}\]]*$' - <|im_end|>
value: "" - <dummy32000>
- key: "'([^']*?)'" - </s>
value: "_DQUOTE_${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: ""
template: template:
chat: | chat: |
{{.Input -}} {{.Input -}}
<|im_start|>assistant <|im_start|>assistant
chat_message: | 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}} <|im_start|>{{ .RoleName }}
{{- if .FunctionCall }} {{ if .FunctionCall -}}
<tool_call> Function call:
{{- else if eq .RoleName "tool" }} {{ else if eq .RoleName "tool" -}}
<tool_response> Function response:
{{- end }} {{ end -}}
{{- if .Content}} {{ if .Content -}}
{{.Content }} {{.Content }}
{{- end }} {{ end -}}
{{- if .FunctionCall}} {{ if .FunctionCall -}}
{{toJson .FunctionCall}} {{toJson .FunctionCall}}
{{- end }} {{ end -}}<|im_end|>
{{- if .FunctionCall }}
</tool_call>
{{- else if eq .RoleName "tool" }}
</tool_response>
{{- end }}<|im_end|>
completion: | completion: |
{{.Input}} {{.Input}}
function: |- function: |
<|im_start|>system <|im_start|>system
You are a function calling AI model. You are an AI assistant that executes function calls, and these are the tools at your disposal:
Here are the available tools:
<tools>
{{range .Functions}} {{range .Functions}}
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }} {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
{{end}} {{end}}
</tools> <|im_end|>
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 -}} {{.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

64
aio/gpu-8g/vision.yaml
View File

@ -1,35 +1,49 @@
backend: llama-cpp
context_size: 4096 context_size: 4096
f16: true f16: true
mmap: true mmap: true
mmproj: minicpm-v-2_6-mmproj-f16.gguf
name: gpt-4o name: gpt-4o
roles:
user: "USER:"
assistant: "ASSISTANT:"
system: "SYSTEM:"
mmproj: llava-v1.6-7b-mmproj-f16.gguf
parameters: parameters:
model: llava-v1.6-mistral-7b.Q5_K_M.gguf model: minicpm-v-2_6-Q4_K_M.gguf
temperature: 0.2 stopwords:
top_k: 40 - <|im_end|>
top_p: 0.95 - <dummy32000>
seed: -1 - </s>
- <|endoftext|>
template: template:
chat: | 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}} {{.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: download_files:
- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf - filename: minicpm-v-2_6-Q4_K_M.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.gguf sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
- filename: llava-v1.6-7b-mmproj-f16.gguf uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf - filename: minicpm-v-2_6-mmproj-f16.gguf
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
usage: | sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
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}]}'

4
aio/intel/embeddings.yaml
View File

@ -1,7 +1,7 @@
embeddings: true
name: text-embedding-ada-002 name: text-embedding-ada-002
backend: sentencetransformers
parameters: parameters:
model: all-MiniLM-L6-v2 model: huggingface://bartowski/granite-embedding-107m-multilingual-GGUF/granite-embedding-107m-multilingual-f16.gguf
usage: | usage: |
You can test this model with curl like this: You can test this model with curl like this:

118
aio/intel/text-to-text.yaml
View File

@ -1,103 +1,53 @@
name: gpt-4 context_size: 4096
mmap: false f16: true
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|>"
function: function:
# disable injecting the "answer" tool capture_llm_results:
disable_no_action: true - (?s)<Thought>(.*?)</Thought>
grammar: grammar:
# This allows the grammar to also return messages properties_order: name,arguments
mixed_mode: true json_regex_match:
# Suffix to add to the grammar - (?s)<Output>(.*?)</Output>
#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: replace_llm_results:
# Drop the scratchpad content from responses - key: (?s)<Thought>(.*?)</Thought>
- key: "(?s)<scratchpad>.*</scratchpad>"
value: "" value: ""
replace_function_results: mmap: true
# Replace everything that is not JSON array or object name: gpt-4
# parameters:
- key: '(?s)^[^{\[]*' model: localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf
value: "" stopwords:
- key: '(?s)[^}\]]*$' - <|im_end|>
value: "" - <dummy32000>
- key: "'([^']*?)'" - </s>
value: "_DQUOTE_${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: ""
template: template:
chat: | chat: |
{{.Input -}} {{.Input -}}
<|im_start|>assistant <|im_start|>assistant
chat_message: | 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}} <|im_start|>{{ .RoleName }}
{{- if .FunctionCall }} {{ if .FunctionCall -}}
<tool_call> Function call:
{{- else if eq .RoleName "tool" }} {{ else if eq .RoleName "tool" -}}
<tool_response> Function response:
{{- end }} {{ end -}}
{{- if .Content}} {{ if .Content -}}
{{.Content }} {{.Content }}
{{- end }} {{ end -}}
{{- if .FunctionCall}} {{ if .FunctionCall -}}
{{toJson .FunctionCall}} {{toJson .FunctionCall}}
{{- end }} {{ end -}}<|im_end|>
{{- if .FunctionCall }}
</tool_call>
{{- else if eq .RoleName "tool" }}
</tool_response>
{{- end }}<|im_end|>
completion: | completion: |
{{.Input}} {{.Input}}
function: |- function: |
<|im_start|>system <|im_start|>system
You are a function calling AI model. You are an AI assistant that executes function calls, and these are the tools at your disposal:
Here are the available tools:
<tools>
{{range .Functions}} {{range .Functions}}
{'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }} {'type': 'function', 'function': {'name': '{{.Name}}', 'description': '{{.Description}}', 'parameters': {{toJson .Parameters}} }}
{{end}} {{end}}
</tools> <|im_end|>
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 -}} {{.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

69
aio/intel/vision.yaml
View File

@ -1,35 +1,50 @@
backend: llama-cpp
context_size: 4096 context_size: 4096
mmap: false f16: true
f16: false mmap: true
mmproj: minicpm-v-2_6-mmproj-f16.gguf
name: gpt-4o name: gpt-4o
roles:
user: "USER:"
assistant: "ASSISTANT:"
system: "SYSTEM:"
mmproj: llava-v1.6-7b-mmproj-f16.gguf
parameters: parameters:
model: llava-v1.6-mistral-7b.Q5_K_M.gguf model: minicpm-v-2_6-Q4_K_M.gguf
temperature: 0.2 stopwords:
top_k: 40 - <|im_end|>
top_p: 0.95 - <dummy32000>
seed: -1 - </s>
- <|endoftext|>
template: template:
chat: | 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}} {{.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: download_files:
- filename: llava-v1.6-mistral-7b.Q5_K_M.gguf - filename: minicpm-v-2_6-Q4_K_M.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/llava-v1.6-mistral-7b.Q5_K_M.gguf sha256: 3a4078d53b46f22989adbf998ce5a3fd090b6541f112d7e936eb4204a04100b1
- filename: llava-v1.6-7b-mmproj-f16.gguf uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/ggml-model-Q4_K_M.gguf
uri: huggingface://cjpais/llava-1.6-mistral-7b-gguf/mmproj-model-f16.gguf - filename: minicpm-v-2_6-mmproj-f16.gguf
uri: huggingface://openbmb/MiniCPM-V-2_6-gguf/mmproj-model-f16.gguf
usage: | sha256: 4485f68a0f1aa404c391e788ea88ea653c100d8e98fe572698f701e5809711fd
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}]}'