Skip to content

Commit

Permalink
Merge branch 'master' into intel-fix
Browse files Browse the repository at this point in the history
  • Loading branch information
dave-gray101 authored May 22, 2024
2 parents b91836c + 23fa92b commit 360732f
Show file tree
Hide file tree
Showing 2 changed files with 119 additions and 2 deletions.
64 changes: 64 additions & 0 deletions gallery/chatml-hercules.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,64 @@
---
name: "chatml-hercules"

config_file: |
mmap: true
function:
# disable injecting the "answer" tool
disable_no_action: true
grammar:
# This allows the grammar to also return messages
mixed_mode: 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)<|im_start|>call(.*?)<|im_end|>"
- "(?s)<|im_start|>call(.*?)"
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: '"'
template:
chat_message: |
<|im_start|>{{ if .FunctionCall -}}call{{else if eq .RoleName "tool"}}function{{else}}{{ .RoleName }}{{end}}
{{ if .Content -}}
{{.Content }}
{{ end -}}
{{ if .FunctionCall -}}
{{toJson .FunctionCall}}
{{ end -}}<|im_end|>
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 -}}
chat: |
{{.Input -}}
<|im_start|>assistant
completion: |
{{.Input}}
context_size: 4096
stopwords:
- '<|im_end|>'
- '<dummy32000>'
- '</s>'
57 changes: 55 additions & 2 deletions gallery/index.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
### START mudler's LocalAI specific-models
- &mudler
url: "github:mudler/LocalAI/gallery/mudler.yaml@master"
name: "localAI-llama3-8b-function-call-v0.2"
name: "LocalAI-llama3-8b-function-call-v0.2"
icon: "https://cdn-uploads.huggingface.co/production/uploads/647374aa7ff32a81ac6d35d4/us5JKi9z046p8K-cn_M0w.webp"
license: llama3
description: |
Expand All @@ -18,6 +18,7 @@
- gpu
- cpu
- llama3
- function-calling
overrides:
parameters:
model: LocalAI-Llama3-8b-Function-Call-v0.2-q4_k_m.bin
Expand Down Expand Up @@ -766,6 +767,7 @@
- filename: Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
sha256: 694c55b5215d03e59626cd4292076eaf31610ef27ba04737166766baa75d889f
uri: huggingface://MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.3-32k-GGUF/Llama-3-8B-Instruct-DPO-v0.3.Q4_K_M.gguf
### Start Yi
- &yi-chat
url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
icon: "https://raw.githubusercontent.com/01-ai/Yi/main/assets/img/Yi_logo_icon_light.svg"
Expand Down Expand Up @@ -1089,6 +1091,52 @@
- filename: llava-llama-3-8b-v1_1-mmproj-f16.gguf
sha256: eb569aba7d65cf3da1d0369610eb6869f4a53ee369992a804d5810a80e9fa035
uri: huggingface://xtuner/llava-llama-3-8b-v1_1-gguf/llava-llama-3-8b-v1_1-mmproj-f16.gguf
### ChatML
- url: "github:mudler/LocalAI/gallery/chatml.yaml@master"
name: "helpingai-9b"
license: hsul
icon: https://huggingface.co/OEvortex/HelpingAI-3B/resolve/main/HelpingAI.png
description: |
HelpingAI-9B is a large language model designed for emotionally intelligent conversational interactions. It is trained to engage users with empathy, understanding, and supportive dialogue across a wide range of topics and contexts. The model aims to provide a supportive AI companion that can attune to users' emotional states and communicative needs.
urls:
- https://huggingface.co/OEvortex/HelpingAI-9B
- https://huggingface.co/nold/HelpingAI-9B-GGUF
tags:
- llm
- gguf
- gpu
- cpu
- chatml
overrides:
context_size: 4096
parameters:
model: HelpingAI-9B_Q4_K_M.gguf
files:
- filename: HelpingAI-9B_Q4_K_M.gguf
sha256: 9c90f3a65332a03a6cbb563eee19c7586d9544f646ff9f33f7f1904b3d415ae2
uri: huggingface://nold/HelpingAI-9B-GGUF/HelpingAI-9B_Q4_K_M.gguf
- url: "github:mudler/LocalAI/gallery/chatml-hercules.yaml@master"
icon: "https://tse3.mm.bing.net/th/id/OIG1.vnrl3xpEcypR3McLW63q?pid=ImgGn"
urls:
- https://huggingface.co/Locutusque/Llama-3-Hercules-5.0-8B
- https://huggingface.co/bartowski/Llama-3-Hercules-5.0-8B-GGUF
name: "llama-3-hercules-5.0-8b"
tags:
- llm
- gguf
- gpu
- cpu
- chatml
- function-calling
description: |
Llama-3-Hercules-5.0-8B is a fine-tuned language model derived from Llama-3-8B. It is specifically designed to excel in instruction following, function calls, and conversational interactions across various scientific and technical domains.
overrides:
parameters:
model: Llama-3-Hercules-5.0-8B-Q4_K_M.gguf
files:
- filename: Llama-3-Hercules-5.0-8B-Q4_K_M.gguf
sha256: 83647caf4a23a91697585cff391e7d1236fac867392f9e49a6dab59f81b5f810
uri: huggingface://bartowski/Llama-3-Hercules-5.0-8B-GGUF/Llama-3-Hercules-5.0-8B-Q4_K_M.gguf
- &phi-2-chat
### START Phi-2
url: "github:mudler/LocalAI/gallery/phi-2-chat.yaml@master"
Expand Down Expand Up @@ -1228,8 +1276,9 @@
- llm
- gguf
- gpu
- llama2
- mistral
- cpu
- function-calling
overrides:
parameters:
model: Hermes-2-Pro-Mistral-7B.Q4_0.gguf
Expand Down Expand Up @@ -1264,6 +1313,7 @@
- gpu
- llama3
- cpu
- function-calling
description: |
Hermes-2 Θ (Theta) is the first experimental merged model released by Nous Research, in collaboration with Charles Goddard at Arcee, the team behind MergeKit.
Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.
Expand All @@ -1284,6 +1334,7 @@
- gguf
- gpu
- llama3
- function-calling
- cpu
urls:
- https://huggingface.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF
Expand All @@ -1300,6 +1351,7 @@
- gguf
- gpu
- llama3
- function-calling
- cpu
name: "hermes-2-pro-llama-3-8b:Q5_K_M"
urls:
Expand All @@ -1316,6 +1368,7 @@
- llm
- gguf
- gpu
- function-calling
- llama3
- cpu
name: "hermes-2-pro-llama-3-8b:Q8_0"
Expand Down

0 comments on commit 360732f

Please sign in to comment.