Skip to content

Commit

Permalink
replace phi3 with phi3.5, add llama 3.2 models
Browse files Browse the repository at this point in the history
  • Loading branch information
@amakropoulos
amakropoulos committed Sep 26, 2024
1 parent a3db5d7 commit 75eaf19
Show file tree
Hide file tree
Showing 2 changed files with 26 additions and 38 deletions.
6 changes: 4 additions & 2 deletions Runtime/LLMUnitySetup.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -114,11 +114,13 @@ public class LLMUnitySetup
("OpenHermes 2.5 7B", "https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF/resolve/main/openhermes-2.5-mistral-7b.Q4_K_M.gguf?download=true", null),
}},
{"Small models", new(string, string, string)[]
{
("Phi 3", "https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf?download=true", null),
{
("Llama 3.2 3B", "https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF/resolve/main/llama-3.2-3b-instruct-q4_k_m.gguf", null),
("Phi 3.5 4B", "https://huggingface.co/bartowski/Phi-3.5-mini-instruct-GGUF/resolve/main/Phi-3.5-mini-instruct-Q4_K_M.gguf", null),
}},
{"Tiny models", new(string, string, string)[]
{
("Llama 3.2 1B", "https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF/resolve/main/llama-3.2-1b-instruct-q4_k_m.gguf", null),
("Qwen 2 0.5B", "https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF/resolve/main/qwen2-0_5b-instruct-q4_k_m.gguf?download=true", null),
}},
};
Expand Down
58 changes: 22 additions & 36 deletions Third Party Notices.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -30,29 +30,31 @@ The following models can be downloaded with LLMUnity:

Developer: Meta<br>
Origin: [link](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)<br>
Quantization: [link](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF)<br>
License Type: "llama3.1"<br>
License: [link](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)

##### modified by: bartowski/Meta-Llama-3-8B-Instruct-GGUF
### meta-llama/Llama-3.2-1B-Instruct

Developer:bartowski<br>
Origin: [link](https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF)<br>
License Type: "llama3.1"<br>
License: [link](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B/blob/main/LICENSE)
Developer: Meta<br>
Origin: [link](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct)<br>
Quantization: [link](https://huggingface.co/hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF)<br>
License Type: "llama3.2"<br>
License: [link](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct/blob/main/LICENSE.txt)

<br>
### meta-llama/Llama-3.2-3B-Instruct

Developer: Meta<br>
Origin: [link](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)<br>
Quantization: [link](https://huggingface.co/hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF)<br>
License Type: "llama3.2"<br>
License: [link](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt)

### google/gemma-2-9b-it

Developer: Google<br>
Origin: [link](https://huggingface.co/google/gemma-2-9b-it)<br>
License Type: "gemma"<br>
License: [link](https://ai.google.dev/gemma/terms)

##### modified by: bartowski/gemma-2-9b-it-GGUF

Developer:bartowski<br>
Origin: [link](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF)<br>
Quantization: [link](https://huggingface.co/bartowski/gemma-2-9b-it-GGUF)<br>
License Type: "gemma"<br>
License: [link](https://ai.google.dev/gemma/terms)

Expand All @@ -62,47 +64,37 @@ License: [link](https://ai.google.dev/gemma/terms)

Developer: Mistral AI<br>
Origin: [link](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)<br>
Quantization: [link](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)

##### modified by: TheBloke/Mistral-7B-Instruct-v0.2-GGUF

Developer: TheBloke<br>
Origin: [link](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GGUF)

<br>

### microsoft/Phi-3-mini-4k-instruct-gguf

Developer: Microsoft<br>
Origin: [link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf)<br>
Origin: [link](https://huggingface.co/microsoft/Phi-3.5-mini-instruct)<br>
Quantization: [link](https://huggingface.co/bartowski/Phi-3.5-mini-instruct-GGUF)<br>
License Type: "MIT"<br>
License: [link](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/blob/main/LICENSE)
License: [link](https://huggingface.co/microsoft/Phi-3.5-mini-instruct/resolve/main/LICENSE)

<br>

### teknium/OpenHermes-2.5-Mistral-7B

Developer: teknium<br>
Origin: [link](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)<br>
Quantization: [link](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)

##### modified by: TheBloke/OpenHermes-2.5-Mistral-7B-GGUF

Developer: TheBloke<br>
Origin: [link](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/TheBloke/OpenHermes-2.5-Mistral-7B-GGUF)

<br>

### Qwen/Qwen2-0.5B-Instruct-GGUF

Developer: Qwen<br>
Origin: [link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF)<br>
Quantization: [link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF/blob/main/LICENSE)

Expand All @@ -116,12 +108,6 @@ The following model is used for testing purposes:

Developer: BEEspoke Data<br>
Origin: [link](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes)<br>
Quantization: [link](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes)

##### modified by: afrideva/smol_llama-220M-openhermes-GGUF

Developer: afrideva<br>
Origin: [link](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF)<br>
License Type: "Apache 2.0"<br>
License: [link](https://huggingface.co/afrideva/smol_llama-220M-openhermes-GGUF)

0 comments on commit 75eaf19

Please sign in to comment.