dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-26 12:45:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 15

Merge branch 'master' into update/CPPLLAMA_VERSION

Browse source
This commit is contained in:
Ettore Di Giacinto 2025-03-12 12:56:10 +01:00 • committed by GitHub
commit 963b21ce82
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 302 additions and 339 deletions
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
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:

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
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

60
aio/cpu/vision.yaml
View file

@ -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

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

@ -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:

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

@ -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

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

@ -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

4
aio/intel/embeddings.yaml
View file

@ -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:

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

@ -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

69
aio/intel/vision.yaml
View file

@ -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

58
gallery/index.yaml
View file

@ -4527,6 +4527,49 @@
- filename: OpenPipe_Deductive-Reasoning-Qwen-32B-Q4_K_M.gguf
sha256: 53a8314e572c60c867da897721d366f183dc6d2193c83a41ff8ad46a2a0692c8
uri: huggingface://bartowski/OpenPipe_Deductive-Reasoning-Qwen-32B-GGUF/OpenPipe_Deductive-Reasoning-Qwen-32B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "open-r1_olympiccoder-32b"
urls:
- https://huggingface.co/open-r1/OlympicCoder-32B
- https://huggingface.co/bartowski/open-r1_OlympicCoder-32B-GGUF
description: |
OlympicCoder-32B is a code mode that achieves very strong performance on competitive coding benchmarks such as LiveCodeBench andthe 2024 International Olympiad in Informatics.
overrides:
parameters:
model: open-r1_OlympicCoder-32B-Q4_K_M.gguf
files:
- filename: open-r1_OlympicCoder-32B-Q4_K_M.gguf
sha256: bb82e4aa2219f655d37c7efad8985582cf3c32de0e0299ecd2f304d32ac39f12
uri: huggingface://bartowski/open-r1_OlympicCoder-32B-GGUF/open-r1_OlympicCoder-32B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "open-r1_olympiccoder-7b"
urls:
- https://huggingface.co/open-r1/OlympicCoder-7B
- https://huggingface.co/bartowski/open-r1_OlympicCoder-7B-GGUF
description: |
OlympicCoder-7B is a code model that achieves strong performance on competitive coding benchmarks such as LiveCodeBench and the 2024 International Olympiad in Informatics.
overrides:
parameters:
model: open-r1_OlympicCoder-7B-Q4_K_M.gguf
files:
- filename: open-r1_OlympicCoder-7B-Q4_K_M.gguf
sha256: 21e18e7fd1fb244455a67d4dee538a4d86dc96d507c39a4ad16ef335fb9e6e2f
uri: huggingface://bartowski/open-r1_OlympicCoder-7B-GGUF/open-r1_OlympicCoder-7B-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "trashpanda-org_qwq-32b-snowdrop-v0"
icon: https://cdn-uploads.huggingface.co/production/uploads/675a77cf99ca23af9daacccc/Tdn0PJBFnG3J6UcjO9G94.png
urls:
- https://huggingface.co/trashpanda-org/QwQ-32B-Snowdrop-v0
- https://huggingface.co/bartowski/trashpanda-org_QwQ-32B-Snowdrop-v0-GGUF
description: |
R1 at home for RP, literally. Able to handle my cards with gimmicks and subtle tricks in them. With a good reasoning starter+prompt, I'm getting consistently-structured responses that have a good amount of variation across them still while rerolling. Char/scenario portrayal is good despite my focus on writing style, lorebooks are properly referenced at times. Slop doesn't seem to be too much of an issue with thinking enabled. Some user impersonation is rarely observed. Prose is refreshing if you take advantage of what I did (writing style fixation). I know I said Marigold would be my daily driver, but this one is that now, it's that good.
overrides:
parameters:
model: trashpanda-org_QwQ-32B-Snowdrop-v0-Q4_K_M.gguf
files:
- filename: trashpanda-org_QwQ-32B-Snowdrop-v0-Q4_K_M.gguf
sha256: 584d2f14f2f08ce499665c332bef30245b605ed2278e9075766237835f564c5f
uri: huggingface://bartowski/trashpanda-org_QwQ-32B-Snowdrop-v0-GGUF/trashpanda-org_QwQ-32B-Snowdrop-v0-Q4_K_M.gguf
- &llama31
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1
icon: https://avatars.githubusercontent.com/u/153379578
@ -9056,6 +9099,21 @@
- filename: TheDrummer_Gemmasutra-Pro-27B-v1.1-Q4_K_M.gguf
sha256: 218a14f0bf8266f9e77d16b8b4f5cc1dc76e97eb582a2c97cca5a3a2c35de86b
uri: huggingface://bartowski/TheDrummer_Gemmasutra-Pro-27B-v1.1-GGUF/TheDrummer_Gemmasutra-Pro-27B-v1.1-Q4_K_M.gguf
- !!merge <<: *gemma
name: "thedrummer_gemmasutra-small-4b-v1"
icon: https://cdn-uploads.huggingface.co/production/uploads/65f2fd1c25b848bd061b5c2e/Cekk7d2UAKu7LPsw8SxV7.png
urls:
- https://huggingface.co/TheDrummer/Gemmasutra-Small-4B-v1
- https://huggingface.co/bartowski/TheDrummer_Gemmasutra-Small-4B-v1-GGUF
description: |
An upscaled Gemma 2B tune with modern techniques. Au Revoir, Gemma!
overrides:
parameters:
model: TheDrummer_Gemmasutra-Small-4B-v1-Q4_K_M.gguf
files:
- filename: TheDrummer_Gemmasutra-Small-4B-v1-Q4_K_M.gguf
sha256: 81dd2e2d9546f5dc2150c45c62acabc112068b801ca50b79feceabb1bd4d6f1a
uri: huggingface://bartowski/TheDrummer_Gemmasutra-Small-4B-v1-GGUF/TheDrummer_Gemmasutra-Small-4B-v1-Q4_K_M.gguf
- &llama3
url: "github:mudler/LocalAI/gallery/llama3-instruct.yaml@master"
icon: https://avatars.githubusercontent.com/u/153379578