跳转至

Ollama 模型文件

[!NOTE] Modelfile 语法正在开发中

模型文件是创建和共享 Ollama 模型的蓝图。

目录

格式

Modelfile 的格式:

# comment
INSTRUCTION arguments
Instruction Description
FROM (required) Defines the base model to use.
PARAMETER Sets the parameters for how Ollama will run the model.
TEMPLATE The full prompt template to be sent to the model.
SYSTEM Specifies the system message that will be set in the template.
ADAPTER Defines the (Q)LoRA adapters to apply to the model.
LICENSE Specifies the legal license.
MESSAGE Specify message history.

示例

基本 Modelfile

一个创建马里奥蓝图的 Modelfile 示例:

FROM llama3.2
# sets the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
PARAMETER num_ctx 4096

# sets a custom system message to specify the behavior of the chat assistant
SYSTEM You are Mario from super mario bros, acting as an assistant.

要使用这个:

  1. 将其保存为文件(例如 Modelfile
  2. ollama create choose-a-model-name -f <location of the file e.g. ./Modelfile>'
  3. ollama run choose-a-model-name
  4. 开始使用模型!

更多示例可在示例目录中找到。

要查看给定模型的Modelfile,请使用ollama show --modelfile命令。

```bash

ollama show --modelfile llama3.2 # Modelfile generated by "ollama show" # To build a new Modelfile based on this one, replace the FROM line with: # FROM llama3.2:latest FROM /Users/pdevine/.ollama/models/blobs/sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29 TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>""" PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>" PARAMETER stop "<|reserved_special_token" ```

指令

FROM(必需)

FROM 指令定义了在创建模型时要使用的基础模型。

FROM <model name>:<tag>

基于现有模型构建

FROM llama3.2

可用的基础模型列表:

https://github.com/ollama/ollama#model-library 可以在以下位置找到其他模型: https://ollama.com/library

从Safetensors模型构建

FROM <model directory>

模型目录应包含支持架构的 Safetensors 权重。

目前支持的模型架构: * Llama(包括 Llama 2、Llama 3、Llama 3.1 和 Llama 3.2) * Mistral(包括 Mistral 1、Mistral 2 和 Mixtral) * Gemma(包括 Gemma 1 和 Gemma 2) * Phi3

从GGUF文件构建

FROM ./ollama-model.gguf

GGUF 文件的位置应指定为绝对路径或相对于 Modelfile 的位置。

参数

PARAMETER 指令定义了一个在运行模型时可以设置的参数。

PARAMETER <parameter> <parametervalue>

有效的参数和值

Parameter Description Value Type Example Usage
mirostat Enable Mirostat sampling for controlling perplexity. (default: 0, 0 = disabled, 1 = Mirostat, 2 = Mirostat 2.0) int mirostat 0
mirostat_eta Influences how quickly the algorithm responds to feedback from the generated text. A lower learning rate will result in slower adjustments, while a higher learning rate will make the algorithm more responsive. (Default: 0.1) float mirostat_eta 0.1
mirostat_tau Controls the balance between coherence and diversity of the output. A lower value will result in more focused and coherent text. (Default: 5.0) float mirostat_tau 5.0
num_ctx Sets the size of the context window used to generate the next token. (Default: 2048) int num_ctx 4096
repeat_last_n Sets how far back for the model to look back to prevent repetition. (Default: 64, 0 = disabled, -1 = num_ctx) int repeat_last_n 64
repeat_penalty Sets how strongly to penalize repetitions. A higher value (e.g., 1.5) will penalize repetitions more strongly, while a lower value (e.g., 0.9) will be more lenient. (Default: 1.1) float repeat_penalty 1.1
temperature The temperature of the model. Increasing the temperature will make the model answer more creatively. (Default: 0.8) float temperature 0.7
seed Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt. (Default: 0) int seed 42
stop Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return. Multiple stop patterns may be set by specifying multiple separate stop parameters in a modelfile. string stop "AI assistant:"
tfs_z Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting. (default: 1) float tfs_z 1
num_predict Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context) int num_predict 42
top_k Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40) int top_k 40
top_p Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9) float top_p 0.9
min_p Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter p represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with p=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0) float min_p 0.05

模板

要传递给模型的完整提示模板 TEMPLATE。它可能包括(可选)系统消息、用户消息和模型的响应。注意:语法可能是模型特定的。模板使用 Go 模板语法

模板变量

Variable Description
{{ .System }} The system message used to specify custom behavior.
{{ .Prompt }} The user prompt message.
{{ .Response }} The response from the model. When generating a response, text after this variable is omitted.
TEMPLATE """{{ if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{ if .Prompt }}<|im_start|>user
{{ .Prompt }}<|im_end|>
{{ end }}<|im_start|>assistant
"""

SYSTEM

SYSTEM 指令指定了模板中要使用的系统消息(如果适用)。

SYSTEM """<system message>"""

ADAPTER

ADAPTER 指令指定了一个应应用于基础模型的微调 LoRA 适配器。适配器的值应为绝对路径或相对于 Modelfile 的路径。基础模型应使用 FROM 指令指定。如果基础模型与适配器微调时所用的基础模型不同,行为将不可预测。

Safetensor 适配器

ADAPTER <path to safetensor adapter>

目前支持的 Safetensor 适配器: * Llama(包括 Llama 2、Llama 3 和 Llama 3.1) * Mistral(包括 Mistral 1、Mistral 2 和 Mixtral) * Gemma(包括 Gemma 1 和 Gemma 2)

GGUF 适配器

ADAPTER ./ollama-lora.gguf

许可证

LICENSE 指令允许你指定与此 Modelfile 一起使用的模型的共享或分发所依据的法律许可证。

LICENSE """
<license text>
"""

MESSAGE

MESSAGE 指令允许你为模型指定消息历史,以便模型在响应时使用。通过多次使用 MESSAGE 命令来构建对话,可以引导模型以类似的方式回答。

MESSAGE <role> <message>

有效的角色

Role Description
system Alternate way of providing the SYSTEM message for the model.
user An example message of what the user could have asked.
assistant An example message of how the model should respond.

示例对话

MESSAGE user Is Toronto in Canada?
MESSAGE assistant yes
MESSAGE user Is Sacramento in Canada?
MESSAGE assistant no
MESSAGE user Is Ontario in Canada?
MESSAGE assistant yes

注意事项

  • Modelfile 不区分大小写。在示例中,使用大写指令是为了更容易区分它与参数。
  • 指令可以按任意顺序排列。在示例中,FROM 指令放在首位是为了保持可读性。