mirrors/ollama-for-amd
1
0
Fork 0
mirror of https://github.com/likelovewant/ollama-for-amd.git synced 2025-12-21 22:33:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

resolve merge conflicts

Browse Source
This commit is contained in:
likelovewant
2024-07-30 18:53:59 +08:00
parent 7c8be11ca9 0be8baad2b
commit 776aa9ceb2
43 changed files with 178 additions and 202 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
README.md
View File

@@ -53,10 +53,10 @@ The official [Ollama Docker image](https://hub.docker.com/r/ollama/ollama) `olla
## Quickstart ## Quickstart
To run and chat with [Llama 3](https://ollama.com/library/llama3): To run and chat with [Llama 3.1](https://ollama.com/library/llama3.1):
``` ```
ollama run llama3 ollama run llama3.1
``` ```
## Model library ## Model library
@@ -67,8 +67,9 @@ Here are some example models that can be downloaded:
| Model | Parameters | Size | Download | | Model | Parameters | Size | Download |
| ------------------ | ---------- | ----- | ------------------------------ | | ------------------ | ---------- | ----- | ------------------------------ |
| Llama 3 | 8B | 4.7GB | `ollama run llama3` | | Llama 3.1 | 8B | 4.7GB | `ollama run llama3.1` |
| Llama 3 | 70B | 40GB | `ollama run llama3:70b` | | Llama 3.1 | 70B | 40GB | `ollama run llama3.1:70b` |
| Llama 3.1 | 405B | 231GB | `ollama run llama3.1:405b` |
| Phi 3 Mini | 3.8B | 2.3GB | `ollama run phi3` | | Phi 3 Mini | 3.8B | 2.3GB | `ollama run phi3` |
| Phi 3 Medium | 14B | 7.9GB | `ollama run phi3:medium` | | Phi 3 Medium | 14B | 7.9GB | `ollama run phi3:medium` |
| Gemma 2 | 9B | 5.5GB | `ollama run gemma2` | | Gemma 2 | 9B | 5.5GB | `ollama run gemma2` |
@@ -115,16 +116,16 @@ See the [guide](docs/import.md) on importing models for more information.
### Customize a prompt ### Customize a prompt
Models from the Ollama library can be customized with a prompt. For example, to customize the `llama3` model: Models from the Ollama library can be customized with a prompt. For example, to customize the `llama3.1` model:
``` ```
ollama pull llama3 ollama pull llama3.1
``` ```
Create a `Modelfile`: Create a `Modelfile`:
``` ```
FROM llama3 FROM llama3.1
# set the temperature to 1 [higher is more creative, lower is more coherent] # set the temperature to 1 [higher is more creative, lower is more coherent]
PARAMETER temperature 1 PARAMETER temperature 1
@@ -159,7 +160,7 @@ ollama create mymodel -f ./Modelfile
### Pull a model ### Pull a model
``` ```
ollama pull llama3 ollama pull llama3.1
``` ```
> This command can also be used to update a local model. Only the diff will be pulled. > This command can also be used to update a local model. Only the diff will be pulled.
@@ -167,13 +168,13 @@ ollama pull llama3
### Remove a model ### Remove a model
``` ```
ollama rm llama3 ollama rm llama3.1
``` ```
### Copy a model ### Copy a model
``` ```
ollama cp llama3 my-model ollama cp llama3.1 my-model
``` ```
### Multiline input ### Multiline input
@@ -197,14 +198,14 @@ The image features a yellow smiley face, which is likely the central focus of th
### Pass the prompt as an argument ### Pass the prompt as an argument
``` ```
$ ollama run llama3 "Summarize this file: $(cat README.md)" $ ollama run llama3.1 "Summarize this file: $(cat README.md)"
Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications. Ollama is a lightweight, extensible framework for building and running language models on the local machine. It provides a simple API for creating, running, and managing models, as well as a library of pre-built models that can be easily used in a variety of applications.
``` ```
### Show model information ### Show model information
``` ```
ollama show llama3 ollama show llama3.1
``` ```
### List models on your computer ### List models on your computer
@@ -232,7 +233,7 @@ Next, start the server:
Finally, in a separate shell, run a model: Finally, in a separate shell, run a model:
``` ```
./ollama run llama3 ./ollama run llama3.1
``` ```
## REST API ## REST API
@@ -243,7 +244,7 @@ Ollama has a REST API for running and managing models.
``` ```
curl http://localhost:11434/api/generate -d '{ curl http://localhost:11434/api/generate -d '{
"model": "llama3", "model": "llama3.1",
"prompt":"Why is the sky blue?" "prompt":"Why is the sky blue?"
}' }'
``` ```
@@ -252,7 +253,7 @@ curl http://localhost:11434/api/generate -d '{
``` ```
curl http://localhost:11434/api/chat -d '{ curl http://localhost:11434/api/chat -d '{
"model": "llama3", "model": "llama3.1",
"messages": [ "messages": [
{ "role": "user", "content": "why is the sky blue?" } { "role": "user", "content": "why is the sky blue?" }
] ]
@@ -407,7 +408,7 @@ See the [API documentation](./docs/api.md) for all endpoints.
- [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama) - [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama)
- [Ollama Copilot](https://github.com/bernardo-bruning/ollama-copilot) (Proxy that allows you to use ollama as a copilot like Github copilot) - [Ollama Copilot](https://github.com/bernardo-bruning/ollama-copilot) (Proxy that allows you to use ollama as a copilot like Github copilot)
- [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama) - [twinny](https://github.com/rjmacarthy/twinny) (Copilot and Copilot chat alternative using Ollama)
- [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and HuggingFace) - [Wingman-AI](https://github.com/RussellCanfield/wingman-ai) (Copilot code and chat alternative using Ollama and Hugging Face)
- [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension) - [Page Assist](https://github.com/n4ze3m/page-assist) (Chrome Extension)
- [AI Telegram Bot](https://github.com/tusharhero/aitelegrambot) (Telegram bot using Ollama in backend) - [AI Telegram Bot](https://github.com/tusharhero/aitelegrambot) (Telegram bot using Ollama in backend)
- [AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (Sublime Text 4 AI assistant plugin with Ollama support) - [AI ST Completion](https://github.com/yaroslavyaroslav/OpenAI-sublime-text) (Sublime Text 4 AI assistant plugin with Ollama support)

6
api/types.go
View File

@@ -114,6 +114,11 @@ func (t Tools) String() string {
return string(bts) return string(bts)
} }
func (t Tool) String() string {
bts, _ := json.Marshal(t)
return string(bts)
}
// Message is a single message in a chat sequence. The message contains the // Message is a single message in a chat sequence. The message contains the
// role ("system", "user", or "assistant"), the content and an optional list // role ("system", "user", or "assistant"), the content and an optional list
// of images. // of images.
@@ -209,6 +214,7 @@ type Options struct {
NumPredict int `json:"num_predict,omitempty"` NumPredict int `json:"num_predict,omitempty"`
TopK int `json:"top_k,omitempty"` TopK int `json:"top_k,omitempty"`
TopP float32 `json:"top_p,omitempty"` TopP float32 `json:"top_p,omitempty"`
MinP float32 `json:"min_p,omitempty"`
TFSZ float32 `json:"tfs_z,omitempty"` TFSZ float32 `json:"tfs_z,omitempty"`
TypicalP float32 `json:"typical_p,omitempty"` TypicalP float32 `json:"typical_p,omitempty"`
RepeatLastN int `json:"repeat_last_n,omitempty"` RepeatLastN int `json:"repeat_last_n,omitempty"`

2
app/ollama.iss
View File

@@ -138,7 +138,7 @@ SetupAppRunningError=Another Ollama installer is running.%n%nPlease cancel or fi
;FinishedHeadingLabel=Run your first model ;FinishedHeadingLabel=Run your first model
;FinishedLabel=%nRun this command in a PowerShell or cmd terminal.%n%n%n ollama run llama3 ;FinishedLabel=%nRun this command in a PowerShell or cmd terminal.%n%n%n ollama run llama3.1
;ClickFinish=%n ;ClickFinish=%n
[Registry] [Registry]

2
app/ollama_welcome.ps1
View File

@@ -4,5 +4,5 @@ write-host "Welcome to Ollama!"
write-host "" write-host ""
write-host "Run your first model:" write-host "Run your first model:"
write-host "" write-host ""
write-host "`tollama run llama3" write-host "`tollama run llama3.1"
write-host "" write-host ""

1
cmd/cmd.go
View File

@@ -1341,6 +1341,7 @@ func NewCLI() *cobra.Command {
envVars["OLLAMA_NUM_PARALLEL"], envVars["OLLAMA_NUM_PARALLEL"],
envVars["OLLAMA_NOPRUNE"], envVars["OLLAMA_NOPRUNE"],
envVars["OLLAMA_ORIGINS"], envVars["OLLAMA_ORIGINS"],
envVars["OLLAMA_SCHED_SPREAD"],
envVars["OLLAMA_TMPDIR"], envVars["OLLAMA_TMPDIR"],
envVars["OLLAMA_FLASH_ATTENTION"], envVars["OLLAMA_FLASH_ATTENTION"],
envVars["OLLAMA_LLM_LIBRARY"], envVars["OLLAMA_LLM_LIBRARY"],

47
cmd/interactive.go
View File

@@ -1,6 +1,7 @@
package cmd package cmd
import ( import (
"cmp"
"errors" "errors"
"fmt" "fmt"
"io" "io"
@@ -9,13 +10,14 @@ import (
"path/filepath" "path/filepath"
"regexp" "regexp"
"slices" "slices"
"sort"
"strings" "strings"
"github.com/spf13/cobra" "github.com/spf13/cobra"
"golang.org/x/exp/maps"
"github.com/ollama/ollama/api" "github.com/ollama/ollama/api"
"github.com/ollama/ollama/envconfig" "github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/parser"
"github.com/ollama/ollama/progress" "github.com/ollama/ollama/progress"
"github.com/ollama/ollama/readline" "github.com/ollama/ollama/readline"
"github.com/ollama/ollama/types/errtypes" "github.com/ollama/ollama/types/errtypes"
@@ -138,6 +140,7 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error {
fmt.Fprintln(os.Stderr, " /set parameter num_predict <int> Max number of tokens to predict") fmt.Fprintln(os.Stderr, " /set parameter num_predict <int> Max number of tokens to predict")
fmt.Fprintln(os.Stderr, " /set parameter top_k <int> Pick from top k num of tokens") fmt.Fprintln(os.Stderr, " /set parameter top_k <int> Pick from top k num of tokens")
fmt.Fprintln(os.Stderr, " /set parameter top_p <float> Pick token based on sum of probabilities") fmt.Fprintln(os.Stderr, " /set parameter top_p <float> Pick token based on sum of probabilities")
fmt.Fprintln(os.Stderr, " /set parameter min_p <float> Pick token based on top token probability * min_p")
fmt.Fprintln(os.Stderr, " /set parameter num_ctx <int> Set the context size") fmt.Fprintln(os.Stderr, " /set parameter num_ctx <int> Set the context size")
fmt.Fprintln(os.Stderr, " /set parameter temperature <float> Set creativity level") fmt.Fprintln(os.Stderr, " /set parameter temperature <float> Set creativity level")
fmt.Fprintln(os.Stderr, " /set parameter repeat_penalty <float> How strongly to penalize repetitions") fmt.Fprintln(os.Stderr, " /set parameter repeat_penalty <float> How strongly to penalize repetitions")
@@ -375,9 +378,9 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error {
return err return err
} }
req := &api.ShowRequest{ req := &api.ShowRequest{
Name: opts.Model, Name: opts.Model,
System: opts.System, System: opts.System,
Options: opts.Options, Options: opts.Options,
} }
resp, err := client.Show(cmd.Context(), req) resp, err := client.Show(cmd.Context(), req)
if err != nil { if err != nil {
@@ -506,31 +509,35 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error {
} }
func buildModelfile(opts runOptions) string { func buildModelfile(opts runOptions) string {
var mf strings.Builder var f parser.File
model := opts.ParentModel f.Commands = append(f.Commands, parser.Command{Name: "model", Args: cmp.Or(opts.ParentModel, opts.Model)})
if model == "" {
model = opts.Model
}
fmt.Fprintf(&mf, "FROM %s\n", model)
if opts.System != "" { if opts.System != "" {
fmt.Fprintf(&mf, "SYSTEM \"\"\"%s\"\"\"\n", opts.System) f.Commands = append(f.Commands, parser.Command{Name: "system", Args: opts.System})
} }
keys := make([]string, 0) keys := maps.Keys(opts.Options)
for k := range opts.Options { slices.Sort(keys)
keys = append(keys, k)
}
sort.Strings(keys)
for _, k := range keys { for _, k := range keys {
fmt.Fprintf(&mf, "PARAMETER %s %v\n", k, opts.Options[k]) v := opts.Options[k]
var cmds []parser.Command
switch t := v.(type) {
case []string:
for _, s := range t {
cmds = append(cmds, parser.Command{Name: k, Args: s})
}
default:
cmds = append(cmds, parser.Command{Name: k, Args: fmt.Sprintf("%v", t)})
}
f.Commands = append(f.Commands, cmds...)
} }
fmt.Fprintln(&mf)
for _, msg := range opts.Messages { for _, msg := range opts.Messages {
fmt.Fprintf(&mf, "MESSAGE %s \"\"\"%s\"\"\"\n", msg.Role, msg.Content) f.Commands = append(f.Commands, parser.Command{Name: "message", Args: fmt.Sprintf("%s: %s", msg.Role, msg.Content)})
} }
return mf.String() return f.String()
} }
func normalizeFilePath(fp string) string { func normalizeFilePath(fp string) string {

75
cmd/interactive_test.go
View File

@@ -1,12 +1,10 @@
package cmd package cmd
import ( import (
"bytes"
"testing" "testing"
"text/template"
"github.com/google/go-cmp/cmp"
"github.com/stretchr/testify/assert" "github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"github.com/ollama/ollama/api" "github.com/ollama/ollama/api"
) )
@@ -57,58 +55,53 @@ d:\path with\spaces\seven.svg inbetween7 c:\users\jdoe\eight.png inbetween8
func TestModelfileBuilder(t *testing.T) { func TestModelfileBuilder(t *testing.T) {
opts := runOptions{ opts := runOptions{
Model: "hork", Model: "hork",
System: "You are part horse and part shark, but all hork. Do horklike things", System: "You are part horse and part shark, but all hork. Do horklike things",
Messages: []api.Message{ Messages: []api.Message{
{Role: "user", Content: "Hey there hork!"}, {Role: "user", Content: "Hey there hork!"},
{Role: "assistant", Content: "Yes it is true, I am half horse, half shark."}, {Role: "assistant", Content: "Yes it is true, I am half horse, half shark."},
}, },
Options: map[string]interface{}{}, Options: map[string]any{
"temperature": 0.9,
"seed": 42,
"penalize_newline": false,
"stop": []string{"hi", "there"},
},
} }
opts.Options["temperature"] = 0.9 t.Run("model", func(t *testing.T) {
opts.Options["seed"] = 42 expect := `FROM hork
opts.Options["penalize_newline"] = false SYSTEM You are part horse and part shark, but all hork. Do horklike things
opts.Options["stop"] = []string{"hi", "there"}
mf := buildModelfile(opts)
expectedModelfile := `FROM {{.Model}}
SYSTEM """{{.System}}"""
PARAMETER penalize_newline false PARAMETER penalize_newline false
PARAMETER seed 42 PARAMETER seed 42
PARAMETER stop [hi there] PARAMETER stop hi
PARAMETER stop there
PARAMETER temperature 0.9 PARAMETER temperature 0.9
MESSAGE user Hey there hork!
MESSAGE user """Hey there hork!""" MESSAGE assistant Yes it is true, I am half horse, half shark.
MESSAGE assistant """Yes it is true, I am half horse, half shark."""
` `
tmpl, err := template.New("").Parse(expectedModelfile) actual := buildModelfile(opts)
require.NoError(t, err) if diff := cmp.Diff(expect, actual); diff != "" {
t.Errorf("mismatch (-want +got):\n%s", diff)
}
})
var buf bytes.Buffer t.Run("parent model", func(t *testing.T) {
err = tmpl.Execute(&buf, opts) opts.ParentModel = "horseshark"
require.NoError(t, err) expect := `FROM horseshark
assert.Equal(t, buf.String(), mf) SYSTEM You are part horse and part shark, but all hork. Do horklike things
opts.ParentModel = "horseshark"
mf = buildModelfile(opts)
expectedModelfile = `FROM {{.ParentModel}}
SYSTEM """{{.System}}"""
PARAMETER penalize_newline false PARAMETER penalize_newline false
PARAMETER seed 42 PARAMETER seed 42
PARAMETER stop [hi there] PARAMETER stop hi
PARAMETER stop there
PARAMETER temperature 0.9 PARAMETER temperature 0.9
MESSAGE user Hey there hork!
MESSAGE user """Hey there hork!""" MESSAGE assistant Yes it is true, I am half horse, half shark.
MESSAGE assistant """Yes it is true, I am half horse, half shark."""
` `
actual := buildModelfile(opts)
tmpl, err = template.New("").Parse(expectedModelfile) if diff := cmp.Diff(expect, actual); diff != "" {
require.NoError(t, err) t.Errorf("mismatch (-want +got):\n%s", diff)
}
var parentBuf bytes.Buffer })
err = tmpl.Execute(&parentBuf, opts)
require.NoError(t, err)
assert.Equal(t, parentBuf.String(), mf)
} }

3
docs/api.md
View File

@@ -336,6 +336,7 @@ curl http://localhost:11434/api/generate -d '{
"num_predict": 100, "num_predict": 100,
"top_k": 20, "top_k": 20,
"top_p": 0.9, "top_p": 0.9,
"min_p": 0.0,
"tfs_z": 0.5, "tfs_z": 0.5,
"typical_p": 0.7, "typical_p": 0.7,
"repeat_last_n": 33, "repeat_last_n": 33,
@@ -586,7 +587,7 @@ Final response:
##### Request ##### Request
Send a chat message with a conversation history. Send a chat message with images. The images should be provided as an array, with the individual images encoded in Base64.
```shell ```shell
curl http://localhost:11434/api/chat -d '{ curl http://localhost:11434/api/chat -d '{

2
docs/docker.md
View File

@@ -63,7 +63,7 @@ docker run -d --device /dev/kfd --device /dev/dri -v ollama:/root/.ollama -p 114
Now you can run a model: Now you can run a model:
``` ```
docker exec -it ollama ollama run llama3 docker exec -it ollama ollama run llama3.1
``` ```
### Try different models ### Try different models

6
docs/faq.md
View File

@@ -227,7 +227,7 @@ curl http://localhost:11434/api/chat -d '{"model": "mistral"}'
To preload a model using the CLI, use the command: To preload a model using the CLI, use the command:
```shell ```shell
ollama run llama3 "" ollama run llama3.1 ""
``` ```
## How do I keep a model loaded in memory or make it unload immediately? ## How do I keep a model loaded in memory or make it unload immediately?
@@ -273,3 +273,7 @@ The following server settings may be used to adjust how Ollama handles concurren
- `OLLAMA_MAX_QUEUE` - The maximum number of requests Ollama will queue when busy before rejecting additional requests. The default is 512 - `OLLAMA_MAX_QUEUE` - The maximum number of requests Ollama will queue when busy before rejecting additional requests. The default is 512
Note: Windows with Radeon GPUs currently default to 1 model maximum due to limitations in ROCm v5.7 for available VRAM reporting. Once ROCm v6.2 is available, Windows Radeon will follow the defaults above. You may enable concurrent model loads on Radeon on Windows, but ensure you don't load more models than will fit into your GPUs VRAM. Note: Windows with Radeon GPUs currently default to 1 model maximum due to limitations in ROCm v5.7 for available VRAM reporting. Once ROCm v6.2 is available, Windows Radeon will follow the defaults above. You may enable concurrent model loads on Radeon on Windows, but ensure you don't load more models than will fit into your GPUs VRAM.
## How does Ollama load models on multiple GPUs?
Installing multiple GPUs of the same brand can be a great way to increase your available VRAM to load larger models. When you load a new model, Ollama evaluates the required VRAM for the model against what is currently available. If the model will entirely fit on any single GPU, Ollama will load the model on that GPU. This typically provides the best performance as it reduces the amount of data transfering across the PCI bus during inference. If the model does not fit entirely on one GPU, then it will be spread across all the available GPUs.

1
docs/modelfile.md
View File

@@ -141,6 +141,7 @@ PARAMETER <parameter> <parametervalue>
| num_predict | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context) | int | num_predict 42 | | 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_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 | | 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 |
### TEMPLATE ### TEMPLATE

4
docs/tutorials/langchainjs.md
View File

@@ -15,7 +15,7 @@ import { Ollama } from "@langchain/community/llms/ollama";
const ollama = new Ollama({ const ollama = new Ollama({
baseUrl: "http://localhost:11434", baseUrl: "http://localhost:11434",
model: "llama3", model: "llama3.1",
}); });
const answer = await ollama.invoke(`why is the sky blue?`); const answer = await ollama.invoke(`why is the sky blue?`);
@@ -23,7 +23,7 @@ const answer = await ollama.invoke(`why is the sky blue?`);
console.log(answer); console.log(answer);
``` ```
That will get us the same thing as if we ran `ollama run llama3 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app. That will get us the same thing as if we ran `ollama run llama3.1 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
```bash ```bash
npm install cheerio npm install cheerio

2
docs/windows.md
View File

@@ -23,6 +23,8 @@ Logs will often be helpful in diagnosing the problem (see
* NVIDIA 452.39 or newer Drivers if you have an NVIDIA card * NVIDIA 452.39 or newer Drivers if you have an NVIDIA card
* AMD Radeon Driver https://www.amd.com/en/support if you have a Radeon card * AMD Radeon Driver https://www.amd.com/en/support if you have a Radeon card
Ollama uses unicode characters for progress indication, which may render as unknown squares in some older terminal fonts in Windows 10. If you see this, try changing your terminal font settings.
## API Access ## API Access
Here's a quick example showing API access from `powershell` Here's a quick example showing API access from `powershell`

2
examples/go-chat/main.go
View File

@@ -35,7 +35,7 @@ func main() {
ctx := context.Background() ctx := context.Background()
req := &api.ChatRequest{ req := &api.ChatRequest{
Model: "llama3", Model: "llama3.1",
Messages: messages, Messages: messages,
} }

2
examples/go-generate-streaming/main.go
View File

@@ -16,7 +16,7 @@ func main() {
// By default, GenerateRequest is streaming. // By default, GenerateRequest is streaming.
req := &api.GenerateRequest{ req := &api.GenerateRequest{
Model: "gemma", Model: "gemma2",
Prompt: "how many planets are there?", Prompt: "how many planets are there?",
} }

2
examples/go-generate/main.go
View File

@@ -15,7 +15,7 @@ func main() {
} }
req := &api.GenerateRequest{ req := &api.GenerateRequest{
Model: "gemma", Model: "gemma2",
Prompt: "how many planets are there?", Prompt: "how many planets are there?",
// set streaming to false // set streaming to false

0
examples/go-http-generate/README.md
View File

8
examples/langchain-python-rag-document/README.md
View File

@@ -4,6 +4,14 @@ This example provides an interface for asking questions to a PDF document.
## Setup ## Setup
1. Ensure you have the `llama3.1` model installed:
```
ollama pull llama3.1
```
2. Install the Python Requirements.
``` ```
pip install -r requirements.txt pip install -r requirements.txt
``` ```

2
examples/langchain-python-rag-document/main.py
View File

@@ -51,7 +51,7 @@ while True:
template=template, template=template,
) )
llm = Ollama(model="llama3:8b", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])) llm = Ollama(model="llama3.1", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
qa_chain = RetrievalQA.from_chain_type( qa_chain = RetrievalQA.from_chain_type(
llm, llm,
retriever=vectorstore.as_retriever(), retriever=vectorstore.as_retriever(),

4
examples/langchain-python-rag-websummary/README.md
View File

@@ -4,10 +4,10 @@ This example summarizes the website, [https://ollama.com/blog/run-llama2-uncenso
## Running the Example ## Running the Example
1. Ensure you have the `llama2` model installed: 1. Ensure you have the `llama3.1` model installed:
```bash ```bash
ollama pull llama2 ollama pull llama3.1
``` ```
2. Install the Python Requirements. 2. Install the Python Requirements.

2
examples/langchain-python-rag-websummary/main.py
View File

@@ -5,7 +5,7 @@ from langchain.chains.summarize import load_summarize_chain
loader = WebBaseLoader("https://ollama.com/blog/run-llama2-uncensored-locally") loader = WebBaseLoader("https://ollama.com/blog/run-llama2-uncensored-locally")
docs = loader.load() docs = loader.load()
llm = Ollama(model="llama3") llm = Ollama(model="llama3.1")
chain = load_summarize_chain(llm, chain_type="stuff") chain = load_summarize_chain(llm, chain_type="stuff")
result = chain.invoke(docs) result = chain.invoke(docs)

4
examples/langchain-python-simple/README.md
View File

@@ -4,10 +4,10 @@ This example is a basic "hello world" of using LangChain with Ollama.
## Running the Example ## Running the Example
1. Ensure you have the `llama3` model installed: 1. Ensure you have the `llama3.1` model installed:
```bash ```bash
ollama pull llama3 ollama pull llama3.1
``` ```
2. Install the Python Requirements. 2. Install the Python Requirements.

2
examples/langchain-python-simple/main.py
View File

@@ -1,6 +1,6 @@
from langchain.llms import Ollama from langchain.llms import Ollama
input = input("What is your question?") input = input("What is your question?")
llm = Ollama(model="llama3") llm = Ollama(model="llama3.1")
res = llm.predict(input) res = llm.predict(input)
print (res) print (res)

2
examples/modelfile-mario/Modelfile
View File

@@ -1,4 +1,4 @@
FROM llama3 FROM llama3.1
PARAMETER temperature 1 PARAMETER temperature 1
SYSTEM """ SYSTEM """
You are Mario from super mario bros, acting as an assistant. You are Mario from super mario bros, acting as an assistant.

6
examples/modelfile-mario/readme.md
View File

@@ -2,12 +2,12 @@
# Example character: Mario # Example character: Mario
This example shows how to create a basic character using Llama3 as the base model. This example shows how to create a basic character using Llama3.1 as the base model.
To run this example: To run this example:
1. Download the Modelfile 1. Download the Modelfile
2. `ollama pull llama3` to get the base model used in the model file. 2. `ollama pull llama3.1` to get the base model used in the model file.
3. `ollama create NAME -f ./Modelfile` 3. `ollama create NAME -f ./Modelfile`
4. `ollama run NAME` 4. `ollama run NAME`
@@ -18,7 +18,7 @@ Ask it some questions like "Who are you?" or "Is Peach in trouble again?"
What the model file looks like: What the model file looks like:
``` ```
FROM llama3 FROM llama3.1
PARAMETER temperature 1 PARAMETER temperature 1
SYSTEM """ SYSTEM """
You are Mario from Super Mario Bros, acting as an assistant. You are Mario from Super Mario Bros, acting as an assistant.

2
examples/python-dockerit/dockerit.py
View File

@@ -4,7 +4,7 @@ imageName = input("Enter the name of the image: ")
client = docker.from_env() client = docker.from_env()
s = requests.Session() s = requests.Session()
output="" output=""
with s.post('http://localhost:11434/api/generate', json={'model': 'dockerit', 'prompt': inputDescription}, stream=True) as r: with s.post('http://localhost:11434/api/generate', json={'model': 'mattw/dockerit', 'prompt': inputDescription}, stream=True) as r:
for line in r.iter_lines(): for line in r.iter_lines():
if line: if line:
j = json.loads(line) j = json.loads(line)

2
examples/python-json-datagenerator/predefinedschema.py
View File

@@ -2,7 +2,7 @@ import requests
import json import json
import random import random
model = "llama3" model = "llama3.1"
template = { template = {
"firstName": "", "firstName": "",
"lastName": "", "lastName": "",

2
examples/python-json-datagenerator/randomaddresses.py
View File

@@ -12,7 +12,7 @@ countries = [
"France", "France",
] ]
country = random.choice(countries) country = random.choice(countries)
model = "llama3" model = "llama3.1"
prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters." prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters."

4
examples/python-json-datagenerator/readme.md
View File

@@ -6,10 +6,10 @@ There are two python scripts in this example. `randomaddresses.py` generates ran
## Running the Example ## Running the Example
1. Ensure you have the `llama3` model installed: 1. Ensure you have the `llama3.1` model installed:
```bash ```bash
ollama pull llama3 ollama pull llama3.1
``` ```
2. Install the Python Requirements. 2. Install the Python Requirements.

2
examples/python-simplechat/client.py
View File

@@ -2,7 +2,7 @@ import json
import requests import requests
# NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve` # NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
model = "llama3" # TODO: update this for whatever model you wish to use model = "llama3.1" # TODO: update this for whatever model you wish to use
def chat(messages): def chat(messages):

4
examples/python-simplechat/readme.md
View File

@@ -4,10 +4,10 @@ The **chat** endpoint is one of two ways to generate text from an LLM with Ollam
## Running the Example ## Running the Example
1. Ensure you have the `llama3` model installed: 1. Ensure you have the `llama3.1` model installed:
```bash ```bash
ollama pull llama3 ollama pull llama3.1
``` ```
2. Install the Python Requirements. 2. Install the Python Requirements.

2
examples/typescript-simplechat/client.ts
View File

@@ -1,6 +1,6 @@
import * as readline from "readline"; import * as readline from "readline";
const model = "llama3"; const model = "llama3.1";
type Message = { type Message = {
role: "assistant" | "user" | "system"; role: "assistant" | "user" | "system";
content: string; content: string;

15
gpu/amd_linux.go
View File

@@ -10,6 +10,7 @@ import (
"path/filepath" "path/filepath"
"regexp" "regexp"
"slices" "slices"
"sort"
"strconv" "strconv"
"strings" "strings"
@@ -82,6 +83,20 @@ func AMDGetGPUInfo() []RocmGPUInfo {
// The amdgpu driver always exposes the host CPU(s) first, but we have to skip them and subtract // The amdgpu driver always exposes the host CPU(s) first, but we have to skip them and subtract
// from the other IDs to get alignment with the HIP libraries expectations (zero is the first GPU, not the CPU) // from the other IDs to get alignment with the HIP libraries expectations (zero is the first GPU, not the CPU)
matches, _ := filepath.Glob(GPUPropertiesFileGlob) matches, _ := filepath.Glob(GPUPropertiesFileGlob)
sort.Slice(matches, func(i, j int) bool {
// /sys/class/kfd/kfd/topology/nodes/<number>/properties
a, err := strconv.ParseInt(filepath.Base(filepath.Dir(matches[i])), 10, 64)
if err != nil {
slog.Debug("parse err", "error", err, "match", matches[i])
return false
}
b, err := strconv.ParseInt(filepath.Base(filepath.Dir(matches[j])), 10, 64)
if err != nil {
slog.Debug("parse err", "error", err, "match", matches[i])
return false
}
return a < b
})
cpuCount := 0 cpuCount := 0
for _, match := range matches { for _, match := range matches {
slog.Debug("evaluating amdgpu node " + match) slog.Debug("evaluating amdgpu node " + match)

9
llm/ext_server/server.cpp vendored
View File

@@ -2438,15 +2438,6 @@ static void server_params_parse(int argc, char **argv, server_params &sparams, g
params.lora_adapter.emplace_back(lora_adapter, std::stof(argv[i])); params.lora_adapter.emplace_back(lora_adapter, std::stof(argv[i]));
params.use_mmap = false; params.use_mmap = false;
} }
else if (arg == "--lora-base")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
params.lora_base = argv[i];
}
else if (arg == "-v" || arg == "--verbose") else if (arg == "-v" || arg == "--verbose")
{ {
server_verbose = true; server_verbose = true;

1
llm/llama.cpp

Submodule llm/llama.cpp deleted from a8db2a9ce6

10
llm/patches/05-default-pretokenizer.diff
View File

@@ -1,8 +1,8 @@
diff --git a/src/llama.cpp b/src/llama.cpp diff --git a/src/llama.cpp b/src/llama.cpp
index 8fe51971..7113ba64 100644 index a207451f..2ddf431d 100644
--- a/src/llama.cpp --- a/src/llama.cpp
+++ b/src/llama.cpp +++ b/src/llama.cpp
@@ -5433,16 +5433,7 @@ static void llm_load_vocab( @@ -5347,16 +5347,7 @@ static void llm_load_vocab(
if (vocab.type == LLAMA_VOCAB_TYPE_BPE) { if (vocab.type == LLAMA_VOCAB_TYPE_BPE) {
vocab.tokenizer_add_space_prefix = false; vocab.tokenizer_add_space_prefix = false;
vocab.tokenizer_clean_spaces = true; vocab.tokenizer_clean_spaces = true;
@@ -20,9 +20,9 @@ index 8fe51971..7113ba64 100644
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT; vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_DEFAULT;
} else if ( } else if (
tokenizer_pre == "llama3" || tokenizer_pre == "llama3" ||
@@ -5526,7 +5517,8 @@ static void llm_load_vocab( @@ -5443,7 +5434,8 @@ static void llm_load_vocab(
vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_SMOLLM; tokenizer_pre == "codeshell") {
vocab.tokenizer_clean_spaces = false; vocab.type_pre = LLAMA_VOCAB_PRE_TYPE_CODESHELL;
} else { } else {
- throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str())); - throw std::runtime_error(format("unknown pre-tokenizer type: '%s'", tokenizer_pre.c_str()));
+ LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__); + LLAMA_LOG_WARN("%s: missing or unrecognized pre-tokenizer type, using: 'default'\n", __func__);

6
llm/patches/09-lora.diff
View File

@@ -2,7 +2,7 @@ diff --git a/common/common.cpp b/common/common.cpp
index dbb724fb..c26fe6ee 100644 index dbb724fb..c26fe6ee 100644
--- a/common/common.cpp --- a/common/common.cpp
+++ b/common/common.cpp +++ b/common/common.cpp
@@ -2087,14 +2087,29 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par @@ -2087,14 +2087,27 @@ std::tuple<struct llama_model *, struct llama_context *> llama_init_from_gpt_par
for (unsigned int i = 0; i < params.lora_adapter.size(); ++i) { for (unsigned int i = 0; i < params.lora_adapter.size(); ++i) {
const std::string & lora_adapter = std::get<0>(params.lora_adapter[i]); const std::string & lora_adapter = std::get<0>(params.lora_adapter[i]);
float lora_scale = std::get<1>(params.lora_adapter[i]); float lora_scale = std::get<1>(params.lora_adapter[i]);
@@ -20,9 +20,7 @@ index dbb724fb..c26fe6ee 100644
+ int err = llama_model_apply_lora_from_file(model, + int err = llama_model_apply_lora_from_file(model,
+ lora_adapter.c_str(), + lora_adapter.c_str(),
+ lora_scale, + lora_scale,
+ ((i > 0) || params.lora_base.empty()) + nullptr,
+ ? NULL
+ : params.lora_base.c_str(),
+ params.n_threads); + params.n_threads);
+ if (err != 0) { + if (err != 0) {
+ fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__); + fprintf(stderr, "%s: error: failed to apply lora adapter\n", __func__);

70
llm/patches/10-llama3-rope.diff
View File

@@ -1,70 +0,0 @@
From 2f872f294fb6f5c6e8f983b68c40ea656053dd92 Mon Sep 17 00:00:00 2001
From: Michael Yang <mxyng@pm.me>
Date: Tue, 23 Jul 2024 14:33:29 -0700
Subject: [PATCH] llama 3.1 rope scaling
---
src/llama.cpp | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/src/llama.cpp b/src/llama.cpp
index 8fe51971..a9969df8 100644
--- a/src/llama.cpp
+++ b/src/llama.cpp
@@ -2472,6 +2472,7 @@ struct llama_layer {
// long rope factors
struct ggml_tensor * rope_long = nullptr;
struct ggml_tensor * rope_short = nullptr;
+ struct ggml_tensor * rope_freqs = nullptr;
// bitnet scale
struct ggml_tensor * wq_scale;
@@ -6143,6 +6144,8 @@ static bool llm_load_tensors(
layer.ffn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd});
+ layer.rope_freqs = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ROPE_FREQS, "weight"), { n_embd/n_head/2 }, llama_model_loader::TENSOR_NOT_REQUIRED | (i != 0 ? llama_model_loader::TENSOR_DUPLICATED : 0));
+
if (n_expert == 0) {
layer.ffn_gate = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff});
layer.ffn_down = ml.create_tensor(ctx_split, tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd});
@@ -8620,6 +8623,10 @@ struct llm_build_context {
// choose long/short freq factors based on the context size
const auto n_ctx_pre_seq = cparams.n_ctx / cparams.n_seq_max;
+ if (model.layers[il].rope_freqs != nullptr) {
+ return model.layers[il].rope_freqs;
+ }
+
if (n_ctx_pre_seq > hparams.n_ctx_orig_yarn) {
return model.layers[il].rope_long;
}
@@ -8814,6 +8821,9 @@ struct llm_build_context {
// self-attention
{
+ // rope freq factors for llama3; may return nullptr for llama2 and other models
+ struct ggml_tensor * rope_factors = build_rope_factors(il);
+
// compute Q and K and RoPE them
struct ggml_tensor * Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
cb(Qcur, "Qcur", il);
@@ -8837,14 +8847,14 @@ struct llm_build_context {
}
Qcur = ggml_rope_ext(
- ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, nullptr,
+ ctx0, ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head, n_tokens), inp_pos, rope_factors,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
ext_factor, attn_factor, beta_fast, beta_slow
);
cb(Qcur, "Qcur", il);
Kcur = ggml_rope_ext(
- ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos, nullptr,
+ ctx0, ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens), inp_pos, rope_factors,
n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
ext_factor, attn_factor, beta_fast, beta_slow
);
--
2.45.2

1
llm/server.go
View File

@@ -727,6 +727,7 @@ func (s *llmServer) Completion(ctx context.Context, req CompletionRequest, fn fu
"temperature": req.Options.Temperature, "temperature": req.Options.Temperature,
"top_k": req.Options.TopK, "top_k": req.Options.TopK,
"top_p": req.Options.TopP, "top_p": req.Options.TopP,
"min_p": req.Options.MinP,
"tfs_z": req.Options.TFSZ, "tfs_z": req.Options.TFSZ,
"typical_p": req.Options.TypicalP, "typical_p": req.Options.TypicalP,
"repeat_last_n": req.Options.RepeatLastN, "repeat_last_n": req.Options.RepeatLastN,

2
macapp/src/app.tsx
View File

@@ -19,7 +19,7 @@ export default function () {
const [step, setStep] = useState<Step>(Step.WELCOME) const [step, setStep] = useState<Step>(Step.WELCOME)
const [commandCopied, setCommandCopied] = useState<boolean>(false) const [commandCopied, setCommandCopied] = useState<boolean>(false)
const command = 'ollama run llama3' const command = 'ollama run llama3.1'
return ( return (
<div className='drag'> <div className='drag'>

3
openai/openai.go
View File

@@ -218,6 +218,9 @@ func toChatCompletion(id string, r api.ChatResponse) ChatCompletion {
Index: 0, Index: 0,
Message: Message{Role: r.Message.Role, Content: r.Message.Content, ToolCalls: toolCalls}, Message: Message{Role: r.Message.Role, Content: r.Message.Content, ToolCalls: toolCalls},
FinishReason: func(reason string) *string { FinishReason: func(reason string) *string {
if len(toolCalls) > 0 {
reason = "tool_calls"
}
if len(reason) > 0 { if len(reason) > 0 {
return &reason return &reason
} }

1
parser/parser_test.go
View File

@@ -451,6 +451,7 @@ func TestParseFileParameters(t *testing.T) {
"num_predict 1": {"num_predict", "1"}, "num_predict 1": {"num_predict", "1"},
"top_k 1": {"top_k", "1"}, "top_k 1": {"top_k", "1"},
"top_p 1.0": {"top_p", "1.0"}, "top_p 1.0": {"top_p", "1.0"},
"min_p 0.05": {"min_p", "0.05"},
"tfs_z 1.0": {"tfs_z", "1.0"}, "tfs_z 1.0": {"tfs_z", "1.0"},
"typical_p 1.0": {"typical_p", "1.0"}, "typical_p 1.0": {"typical_p", "1.0"},
"repeat_last_n 1": {"repeat_last_n", "1"}, "repeat_last_n 1": {"repeat_last_n", "1"},

20
scripts/install.sh
View File

@@ -198,19 +198,29 @@ if check_gpu lspci amdgpu || check_gpu lshw amdgpu; then
exit 0 exit 0
fi fi
CUDA_REPO_ERR_MSG="NVIDIA GPU detected, but your OS and Architecture are not supported by NVIDIA. Please install the CUDA driver manually https://docs.nvidia.com/cuda/cuda-installation-guide-linux/"
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-7-centos-7 # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-7-centos-7
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-8-rocky-8 # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-8-rocky-8
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-9-rocky-9 # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-9-rocky-9
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#fedora # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#fedora
install_cuda_driver_yum() { install_cuda_driver_yum() {
status 'Installing NVIDIA repository...' status 'Installing NVIDIA repository...'
case $PACKAGE_MANAGER in case $PACKAGE_MANAGER in
yum) yum)
$SUDO $PACKAGE_MANAGER -y install yum-utils $SUDO $PACKAGE_MANAGER -y install yum-utils
$SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo" >/dev/null ; then
$SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
else
error $CUDA_REPO_ERR_MSG
fi
;; ;;
dnf) dnf)
$SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo" >/dev/null ; then
$SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
else
error $CUDA_REPO_ERR_MSG
fi
;; ;;
esac esac
@@ -235,7 +245,11 @@ install_cuda_driver_yum() {
# ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#debian # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#debian
install_cuda_driver_apt() { install_cuda_driver_apt() {
status 'Installing NVIDIA repository...' status 'Installing NVIDIA repository...'
curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb if curl -I --silent --fail --location "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb" >/dev/null ; then
curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb
else
error $CUDA_REPO_ERR_MSG
fi
case $1 in case $1 in
debian) debian)