model file

  • download model
huggingface-cli download \
  c00cjz00/phi-4-14b-it-R1-m22k_lora \
  unsloth.Q2_K.gguf \
  --local-dir /work/c00cjz00/github/hpc_ollama/home \
  --local-dir-use-symlinks False
  • phi4.modelfile
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM phi4:latest

FROM ./unsloth.Q2_K.gguf
TEMPLATE """{{- range $i, $_ := .Messages }}
{{- $last := eq (len (slice $.Messages $i)) 1 -}}
<|im_start|>{{ .Role }}<|im_sep|>
{{ .Content }}{{ if not $last }}<|im_end|>
{{ end }}
{{- if and (ne .Role "assistant") $last }}<|im_end|>
<|im_start|>assistant<|im_sep|>
{{ end }}
{{- end }}"""
PARAMETER stop <|im_start|>
PARAMETER stop <|im_end|>
PARAMETER stop <|im_sep|>
  • ollama
ollama create myphi4-on-q2 -f ./phi4.modelfile
Downloads last month
18
GGUF
Model size
14.7B params
Architecture
llama
Hardware compatibility
Log In to view the estimation

2-bit

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for c00cjz00/phi-4-14b-it-R1-m22k_gguf

Base model

microsoft/phi-4
Finetuned
unsloth/phi-4
Quantized
(24)
this model