Modelfile

# Modelfile
models:
  - name: llama
    config:
      model_path: llama.gguf
      tokenizer_path: llama_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: starcoder2
    config:
      model_path: starcoder2.gguf
      tokenizer_path: starcoder2_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: qwen2
    config:
      model_path: qwen2.gguf
      tokenizer_path: qwen2_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: gemma2
    config:
      model_path: gemma2.gguf
      tokenizer_path: gemma2_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: meta_llama_31
    config:
      model_path: meta_llama_31.gguf
      tokenizer_path: meta_llama_31_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: gemma2_9b
    config:
      model_path: gemma2_9b.gguf
      tokenizer_path: gemma2_9b_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: phi3
    config:
      model_path: phi3.gguf
      tokenizer_path: phi3_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: meta_llama_31_instruct
    config:
      model_path: meta_llama_31_instruct.gguf
      tokenizer_path: meta_llama_31_instruct_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: gpt2_xl
    config:
      model_path: gpt2_xl.gguf
      tokenizer_path: gpt2_xl_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: qwen2_math_7b
    config:
      model_path: qwen2_math_7b.gguf
      tokenizer_path: qwen2_math_7b_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: wizardlm_7b
    config:
      model_path: wizardlm_7b.gguf
      tokenizer_path: wizardlm_7b_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9
  - name: wizardlm_13b
    config:
      model_path: wizardlm_13b.gguf
      tokenizer_path: wizardlm_13b_tokenizer.model
      max_length: 2048
      temperature: 0.7
      top_k: 40
      top_p: 0.9