Skip to content
This repository has been archived by the owner on Sep 27, 2024. It is now read-only.

phi-2 #53

Merged
merged 3 commits into from
Dec 22, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 59 additions & 0 deletions models/phi-2.json
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
{
"_descriptorVersion": "0.0.1",
"datePublished": "2023-12-13T21:22:37",
"name": "Phi 2",
"description": "Phi-2 is a 2.7 billion parameter Transformer model, an extension of Phi-1.5, with additional training data including synthetic NLP texts and curated web content. It demonstrates near state-of-the-art performance in benchmarks for common sense, language understanding, and logical reasoning within its parameter class. Phi-2 has not undergone reinforcement learning fine-tuning and is open-source, aimed at enabling safety research like toxicity reduction and bias understanding. It is designed for QA, chat, and code formats and has a context length of 2048 tokens. The model was trained on 250 billion tokens from a dataset combining AOAI GPT-3.5 synthetic data and filtered web data, using 1.4 trillion training tokens. It utilized 96xA100-80G GPUs over a span of 14 days. Phi-2 is intended solely for research use.",
"author": {
"name": "Microsoft Research",
"url": "https://www.microsoft.com/en-us/research/",
"blurb": "Advancing science and technology to benefit humanity"
},
"numParameters": "3B",
"resources": {
"canonicalUrl": "https://huggingface.co/microsoft/phi-2",
"paperUrl": "https://arxiv.org/abs/2309.05463",
"downloadUrl": "https://huggingface.co/TheBloke/phi-2-GGUF"
},
"trainedFor": "chat",
"arch": "phi2",
"files": {
"highlighted": {
"economical": {
"name": "phi-2.Q4_K_S.gguf"
},
"most_capable": {
"name": "phi-2.Q6_K.gguf"
}
},
"all": [
{
"name": "phi-2.Q4_K_S.gguf",
"url": "https://huggingface.co/TheBloke/phi-2-GGUF/resolve/main/phi-2.Q4_K_S.gguf",
"sizeBytes": 1615568736,
"quantization": "Q4_K_S",
"format": "gguf",
"sha256checksum": "67df519f789817dee8c9b927227e7795ac07e1b20b58eb21fe109a2af328928a",
"publisher": {
"name": "TheBloke",
"socialUrl": "https://twitter.com/TheBlokeAI"
},
"respository": "TheBloke/phi-2-GGUF",
"repositoryUrl": "https://huggingface.co/TheBloke/phi-2-GGUF"
},
{
"name": "phi-2.Q6_K.gguf",
"url": "https://huggingface.co/TheBloke/phi-2-GGUF/resolve/main/phi-2.Q6_K.gguf",
"sizeBytes": 2285059936,
"quantization": "Q6_K",
"format": "gguf",
"sha256checksum": "9a654a17bee234d85b726bbdaec8e9a3365bbc187238998bc4f84c89afb046d6",
"publisher": {
"name": "TheBloke",
"socialUrl": "https://twitter.com/TheBlokeAI"
},
"respository": "TheBloke/phi-2-GGUF",
"repositoryUrl": "https://huggingface.co/TheBloke/phi-2-GGUF"
}
]
}
}
2 changes: 1 addition & 1 deletion schema.json
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@
},
"arch": {
"type": "string",
"enum": ["llama", "pythia", "gpt-neo-x", "gpt-j", "mpt", "replit", "starcoder", "falcon", "mistral", "stablelm"]
"enum": ["llama", "pythia", "gpt-neo-x", "gpt-j", "mpt", "replit", "starcoder", "falcon", "mistral", "stablelm", "phi2"]
},
"description": {
"type": "string"
Expand Down
Loading