चेतावनी: ये तो डीआरफ्लिक हैं जो 'के साथ गलत' है.
यह शायद नीचे क्या काम नहीं करेगा, मैं इन्हें बनाने के लिए कैसे और फिर सभी कदमों के रूप में और काम करने के लिए एक नमूना ऐप मिलता है... तुम चुपके से किया गया है और उन्हें देखा है! वे शायद मध्य-बार के लिए तैयार हो जाएगा.
## परिचय
भाग 6 में आपका स्वागत हैपार्ट 4विंडोज़ क्लाएंट (w)पार्ट 5, एम्बेडिंग तथा सदिश खोज (e)पार्ट 3, और जीपिय सेटअप (यूयूयूपी.)पार्ट 2
अब रोमांचक भाग आता है: स्थानीय टी. वी.
उसी आवाज़ की तरह, उसी आवाज़ में एक - दूसरे का हाथ होता है; सिर्फ तेज़ उंगलियों को ।
हम आपके A4000 जीपी पर स्थानीय भाषा मॉडलों को स्थानीय रूप से चला लेंगे, अपने पिछले ब्लॉग पोस्ट पर आधारित संदर्भ जानकारी युक्त सुझाव तैयार कर रहे हैं। |--------|-----------|-------------------| | स्थानीय क्यों? | ✅ Complete | ❌ Data sent to third party | | इसके पहले, चलो समझते हैं क्यों हम स्थानीय मॉडलों पर चल रहे हैं... / मैं ... खोलने के API का उपयोग करने के बजाय. | ✅ Free after setup | ❌ Per-token pricing | | स्थानीय बनाम एपीआई तुलना | ✅ <1 second | ⚠️ Network dependent | | ALTANTATATAL स्थानीय _LYEANTH (ओनेई, ...) | ✅ Full control | ❌ Limited | | गोपनीयता | ✅ Any GGUF model | ❌ Provider's models only | | खर्च | ✅ Works offline | ❌ Requires internet | | हाल ही में@ info: whatsthis | ❌ Complex | ✅ Simple |
मनपसंद सूचना
ऑफ़लाइन
graph TB
A[C# Application] --> B{Integration Method}
B --> C[LLamaSharp]
B --> D[ONNX Runtime]
B --> E[TorchSharp]
B --> F[HTTP API]
C --> G[llama.cpp bindings]
G --> H[GGUF Models]
D --> I[ONNX Models]
I --> J[Limited Model Support]
E --> K[PyTorch Models]
K --> L[Complex Setup]
F --> M[External Process]
M --> N[Ollama, LM Studio]
class C recommended
class G,H llamaSharp
classDef recommended stroke:#333,stroke-width:4px
classDef llamaSharp stroke:#333,stroke-width:2px
सेटअप
एक लेखन सहायक, गोपनीयता और क़ीमती विषय के लिए ।
CUNA त्वरण बनायासक्रिय विकास तथा बड़े समुदाय
graph LR
A[Original Model<br/>Llama 2 7B<br/>~28GB float32] --> B[Quantization]
B --> C[Q4_K_M<br/>~4.1GB<br/>4-bit]
B --> D[Q5_K_M<br/>~4.8GB<br/>5-bit]
B --> E[Q6_K<br/>~5.5GB<br/>6-bit]
B --> F[Q8_0<br/>~7.2GB<br/>8-bit]
C --> G[Fast, Lower Quality]
D --> H[Balanced]
E --> I[Higher Quality]
F --> J[Near Original]
class A original
class C,D quantized
class H recommended
classDef original stroke:#333,stroke-width:2px
classDef quantized stroke:#333,stroke-width:2px
classDef recommended stroke:#333,stroke-width:2px
Lemma, मिस्पे, पाउ, गेमा, और अधिक के साथ काम करता है:
मूल मॉडल: 32- बिट फ्लोट (बहुत बड़ा, बहुत सही) |-------|---------------|------------|-----------|------------|------------|---------| | Q4: 4- बिट पूर्णांक (75% छोटा, छोटा क्वालिटी नुकसान) | 2.3GB | ~4GB | ✅ Easy | ✅ Easy | ✅ Easy | ⭐⭐⭐ Good | | Q5/Q6: ज़्यादातर प्रयोगों के लिए मीठा जगह | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐ Good | | क्यू8: पास- पृष्ठ विशेषता, अभी भी 4x छोटा | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | हार्डवेयर द्वारा मॉडल चयन | 4.1GB | ~6GB | ✅ Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐ Better | | IMTACT मॉडल आकार (Q4_M) आलेख+BGY+REGY+RGGEGEGGESUGEGGY+RGEGGGERSGY+EGEGEARS(Q_KS_KS_KSG_M) | 4.7GB | ~7GB | ⚠️ Very Tight | ✅ Good | ✅ Easy | ⭐⭐⭐⭐⭐ Best | | Ph-3 मिनी (3. 8B) | 7.4GB | ~10GB | ❌ No | ⚠️ Tight | ✅ Good | ⭐⭐⭐⭐ Better |
लाला 2 7B
लाला 3 8B: कोशिश करें या कोशिश करें13B मॉडलसिर्फ सीपीयू: कोई मॉडल काम करता है, बस धीमी गति के साथ शुरू होता है (Mh-3M के साथ शुरू होता है)
तकनीकी लेखन के लिए बढ़िया विशेषता
"mistral 7b gguf"**हम gGUF संस्करण का उपयोग करेंगे.**जीजीफ़ मॉडल पाना
# Install huggingface-cli
pip install huggingface-hub
# Download Mistral 7B Q5_K_M (recommended)
huggingface-cli download TheBloke/Mistral-7B-Instruct-v0.2-GGUF \
mistral-7b-instruct-v0.2.Q5_K_M.gguf \
--local-dir C:\models\mistral-7b \
--local-dir-use-symlinks False
प्रत्यक्ष लिंक
mistral-7b-instruct-v0.2.Q5_K_M.ggufएलला- 7BB- चैट-च्फ़C:\models\mistral-7b\cd Mostlylucid.BlogLLM.Core
dotnet add package LLamaSharp # Latest version
dotnet add package LLamaSharp.Backend.Cuda12 # Latest, matching CUDA version
ढूंढें
[LLamaSharp](https://github.com/SciSharp/LLamaSharp)(rgb4. 8GB)LLamaSharp.Backend.Cuda12 - डाउनलोड करेंइसमें सहेजेंनुआ पैकेज संस्थापित करें
using LLama;
using LLama.Common;
// Check if CUDA is available
bool cudaAvailable = NativeLibraryConfig.Instance.CudaEnabled;
Console.WriteLine($"CUDA Available: {cudaAvailable}");
दो पैकेज क्यों?false- कोर लाइब्रेरी
LLamaSharp.Backend.Cuda1212 घर की साफ - सफाई के लिएusing LLama;
using LLama.Common;
namespace Mostlylucid.BlogLLM.Core.Services
{
public class ModelParameters
{
public string ModelPath { get; set; } = string.Empty;
public int ContextSize { get; set; } = 4096; // Context window
public int GpuLayerCount { get; set; } = 35; // Layers on GPU (35 = all for 7B)
public int Seed { get; set; } = 1337; // For reproducibility
public float Temperature { get; set; } = 0.7f; // Creativity (0.0 = deterministic, 1.0 = creative)
public float TopP { get; set; } = 0.9f; // Nucleus sampling
public int MaxTokens { get; set; } = 500; // Max generation length
}
}
, चेक करें::
**सीयूडी 12.x संस्थापित (- पार्ट 2)**पैकेज संस्थापित
मॉडल पैरामीटर्सपैरामीटर व्याख्या
इससे बड़ा/ अधिक संदर्भ लेकिन धीमा व ज्यादा वीरैमगॉर्नेनोusa. kgm
निचला मूल्य = कम वीरैम परंतु धीमा करेंतापक्रम
using LLama;
using LLama.Common;
using Microsoft.Extensions.Logging;
namespace Mostlylucid.BlogLLM.Core.Services
{
public interface ILlmService
{
Task<string> GenerateAsync(string prompt, CancellationToken cancellationToken = default);
Task<string> GenerateWithContextAsync(string prompt, List<string> contextChunks, CancellationToken cancellationToken = default);
}
public class LlmService : ILlmService, IDisposable
{
private readonly LLamaWeights _model;
private readonly LLamaContext _context;
private readonly ILogger<LlmService> _logger;
private readonly ModelParameters _parameters;
public LlmService(ModelParameters parameters, ILogger<LlmService> logger)
{
_parameters = parameters;
_logger = logger;
_logger.LogInformation("Loading model from {ModelPath}", parameters.ModelPath);
// Configure model parameters
var modelParams = new ModelParams(parameters.ModelPath)
{
ContextSize = (uint)parameters.ContextSize,
GpuLayerCount = parameters.GpuLayerCount,
Seed = (uint)parameters.Seed,
UseMemoryLock = true, // Keep model in RAM
UseMemorymap = true // Memory-map the model file
};
// Load model
_model = LLamaWeights.LoadFromFile(modelParams);
_context = _model.CreateContext(modelParams);
_logger.LogInformation("Model loaded successfully. VRAM used: ~{VRAM}GB",
EstimateVRAMUsage(parameters.GpuLayerCount));
}
public async Task<string> GenerateAsync(string prompt, CancellationToken cancellationToken = default)
{
var executor = new InteractiveExecutor(_context);
var inferenceParams = new InferenceParams
{
Temperature = _parameters.Temperature,
TopP = _parameters.TopP,
MaxTokens = _parameters.MaxTokens,
AntiPrompts = new[] { "\n\nUser:", "###" } // Stop generation at these
};
var result = new StringBuilder();
_logger.LogInformation("Generating response for prompt: {Prompt}", TruncateForLog(prompt));
await foreach (var token in executor.InferAsync(prompt, inferenceParams, cancellationToken))
{
result.Append(token);
}
var response = result.ToString().Trim();
_logger.LogInformation("Generated {Tokens} tokens", CountTokens(response));
return response;
}
public async Task<string> GenerateWithContextAsync(
string prompt,
List<string> contextChunks,
CancellationToken cancellationToken = default)
{
// Build prompt with retrieved context
var fullPrompt = BuildContextualPrompt(prompt, contextChunks);
_logger.LogInformation("Context chunks: {Count}, Total prompt tokens: ~{Tokens}",
contextChunks.Count, CountTokens(fullPrompt));
return await GenerateAsync(fullPrompt, cancellationToken);
}
private string BuildContextualPrompt(string userPrompt, List<string> contextChunks)
{
var sb = new StringBuilder();
sb.AppendLine("You are a helpful writing assistant for a technical blog.");
sb.AppendLine("Use the following excerpts from past blog posts as context:");
sb.AppendLine();
for (int i = 0; i < contextChunks.Count; i++)
{
sb.AppendLine($"--- Context {i + 1} ---");
sb.AppendLine(contextChunks[i]);
sb.AppendLine();
}
sb.AppendLine("---");
sb.AppendLine();
sb.AppendLine("Based on the context above, help with the following:");
sb.AppendLine(userPrompt);
sb.AppendLine();
sb.AppendLine("Response:");
return sb.ToString();
}
private int CountTokens(string text)
{
// Rough estimate: 1 token ≈ 4 characters
return text.Length / 4;
}
private string TruncateForLog(string text, int maxLength = 100)
{
if (text.Length <= maxLength) return text;
return text.Substring(0, maxLength) + "...";
}
private double EstimateVRAMUsage(int gpuLayers)
{
// Rough estimate for 7B model
return (gpuLayers / 35.0) * 6.0; // ~6GB for full 7B model
}
public void Dispose()
{
_context?.Dispose();
_model?.Dispose();
}
}
}
1. 1. 0+ = बहुत जटिल (प्रयोगात्मक हो सकता है):
using Microsoft.Extensions.Logging;
class Program
{
static async Task Main(string[] args)
{
// Setup logging
var loggerFactory = LoggerFactory.Create(builder => builder.AddConsole());
var logger = loggerFactory.CreateLogger<LlmService>();
// Configure model
var parameters = new ModelParameters
{
ModelPath = @"C:\models\mistral-7b\mistral-7b-instruct-v0.2.Q5_K_M.gguf",
ContextSize = 4096,
GpuLayerCount = 35,
Temperature = 0.7f,
MaxTokens = 200
};
// Create service
using var llmService = new LlmService(parameters, logger);
// Test simple generation
Console.WriteLine("=== Test 1: Simple Generation ===\n");
var response1 = await llmService.GenerateAsync(
"Explain what Docker Compose is in 2-3 sentences."
);
Console.WriteLine(response1);
Console.WriteLine("\n");
// Test with context
Console.WriteLine("=== Test 2: Generation with Context ===\n");
var context = new List<string>
{
"Docker Compose is a tool for defining and running multi-container Docker applications. With Compose, you use a YAML file to configure your application's services.",
"In development, Docker Compose makes it easy to spin up all dependencies (databases, caches, etc.) with one command: docker-compose up."
};
var response2 = await llmService.GenerateWithContextAsync(
"Write an introduction paragraph for a blog post about using Docker Compose for development dependencies.",
context
);
Console.WriteLine(response2);
}
}
: संकेतों के रूप में वे तैयार कर रहे हैं (सच्चे समय आउटपुट):
=== Test 1: Simple Generation ===
Docker Compose is a tool that allows you to define and run multi-container Docker applications using a simple YAML configuration file. It simplifies the process of managing multiple containers, networking, and volumes, making it ideal for development environments.
=== Test 2: Generation with Context ===
If you've ever found yourself juggling multiple terminal windows to start databases, caches, and other services for local development, Docker Compose is about to become your new best friend. This powerful tool lets you define your entire development environment in a single YAML file and spin everything up with one command. In this post, we'll explore how to leverage Docker Compose to manage all your development dependencies, making your local setup reproducible, shareable, and incredibly easy to manage.
कॉन्टेक्स्ट बिल्डिंग
एन्टी- साइन्स
namespace Mostlylucid.BlogLLM.Client.Services
{
public class SuggestionService : ISuggestionService
{
private readonly BatchEmbeddingService _embeddingService;
private readonly QdrantVectorStore _vectorStore;
private readonly ILlmService _llmService; // NEW
public SuggestionService(
BatchEmbeddingService embeddingService,
QdrantVectorStore vectorStore,
ILlmService llmService) // NEW
{
_embeddingService = embeddingService;
_vectorStore = vectorStore;
_llmService = llmService;
}
public async Task<string> GenerateAiSuggestionAsync(
string currentText,
List<SimilarPost> context)
{
// Extract text from similar posts
var contextChunks = context
.Take(3) // Top 3 most similar
.Select(p => p.FullText)
.ToList();
// Determine what type of suggestion to generate
var prompt = DeterminePromptType(currentText);
// Generate suggestion
var suggestion = await _llmService.GenerateWithContextAsync(
prompt,
contextChunks
);
return suggestion;
}
private string DeterminePromptType(string currentText)
{
// Analyze what user is writing
var lines = currentText.Split('\n');
var lastLine = lines.LastOrDefault(l => !string.IsNullOrWhiteSpace(l)) ?? "";
// Is user starting a new section?
if (lastLine.StartsWith("## "))
{
return "Suggest 3-5 bullet points for what this section could cover.";
}
// Is user writing code?
if (lastLine.Contains("```"))
{
return "Suggest relevant code examples that might be useful here.";
}
// Is user writing an introduction?
if (currentText.Length < 500 && currentText.Contains("## Introduction"))
{
return "Suggest 2-3 sentences to continue this introduction based on similar posts.";
}
// Default: continue current thought
return "Suggest 1-2 sentences to continue the current paragraph in a natural way.";
}
}
}
public partial class SuggestionsViewModel : ViewModelBase
{
[RelayCommand]
private async Task RegenerateSuggestion()
{
IsGenerating = true;
AiSuggestion = "Generating...";
try
{
var currentText = GetCurrentEditorText(); // From messaging
var suggestion = await _suggestionService.GenerateAiSuggestionAsync(
currentText,
SimilarPosts.ToList()
);
AiSuggestion = suggestion;
}
catch (Exception ex)
{
AiSuggestion = $"Error: {ex.Message}";
}
finally
{
IsGenerating = false;
}
}
}
मॉडल काम कर रहा है और कोरे, संदर्भ-क्रम पाठ तैयार कर रहा है.
public class LlmServiceFactory
{
private static LlmService? _instance;
private static readonly object _lock = new();
public static LlmService GetInstance(ModelParameters parameters, ILogger<LlmService> logger)
{
if (_instance == null)
{
lock (_lock)
{
if (_instance == null)
{
_instance = new LlmService(parameters, logger);
}
}
}
return _instance;
}
}
अब हम भाग 5 से हमारे विंडोज़ क्लाएंट में एकीकृत की पीढ़ी है.
public class StatefulLlmService
{
private readonly InferenceParams _defaultParams;
private string _cachedPromptPrefix = string.Empty;
public async Task<string> GenerateWithPrefixAsync(string prefix, string newPrompt)
{
// If prefix matches cached, reuse KV cache
if (prefix == _cachedPromptPrefix)
{
// Only process new tokens
return await GenerateAsync(newPrompt);
}
// Process entire prompt and cache
_cachedPromptPrefix = prefix;
return await GenerateAsync(prefix + newPrompt);
}
}
सुझाव निवेदन अद्यतन करें
परफ़ॉर्मेंस ऑप्टीमाइज़ेशन
public async Task<List<string>> GenerateBatchAsync(List<string> prompts)
{
var results = new List<string>();
foreach (var prompt in prompts)
{
// With KV cache reuse, subsequent prompts are faster
results.Add(await GenerateAsync(prompt));
}
return results;
}
निवेदन के बीच भरी हुई मॉडल को रखें:
private string PromptContinueWriting(string currentText, List<string> context)
{
return $@"You are a technical blog writing assistant.
Here are excerpts from similar blog posts:
{string.Join("\n\n", context.Select((c, i) => $"--- Post {i + 1} ---\n{c}"))}
Current draft:
{currentText}
Task: Suggest 2-3 sentences to naturally continue the current paragraph.
Keep the same technical depth and casual, pragmatic tone.
Suggestion:";
}
private string PromptSectionStructure(string sectionTitle, List<string> context)
{
return $@"You are a technical blog writing assistant.
Similar sections from past posts:
{string.Join("\n\n", context)}
New section: {sectionTitle}
Task: Suggest 4-6 bullet points for what this section should cover.
Format as a markdown list.
Bullets:";
}
private string PromptCodeExample(string description, List<string> context)
{
return $@"You are a C# coding assistant.
Relevant code from past posts:
{string.Join("\n\n", context)}
Task: {description}
Provide a clean, well-commented C# code example.
Code:";
}
बहुत से सुझावों के लिए, उन्हें बैच करें:
public class VramMonitor
{
[DllImport("nvml.dll")]
private static extern int nvmlDeviceGetMemoryInfo(IntPtr device, ref NvmlMemory memory);
[StructLayout(LayoutKind.Sequential)]
public struct NvmlMemory
{
public ulong Total;
public ulong Free;
public ulong Used;
}
public static (ulong used, ulong total) GetVramUsage()
{
// Simplified - actual implementation needs proper NVML initialization
var memory = new NvmlMemory();
// nvmlDeviceGetMemoryInfo(device, ref memory);
return (memory.Used / 1024 / 1024, memory.Total / 1024 / 1024); // Convert to MB
}
}
public class LlmServiceWithUnload : IDisposable
{
private LlmService? _service;
private readonly Timer _unloadTimer;
private DateTime _lastUsed;
public LlmServiceWithUnload()
{
_unloadTimer = new Timer(CheckForUnload, null, TimeSpan.FromMinutes(1), TimeSpan.FromMinutes(1));
}
private void CheckForUnload(object? state)
{
if (_service != null && (DateTime.Now - _lastUsed) > TimeSpan.FromMinutes(10))
{
_service.Dispose();
_service = null;
GC.Collect();
Console.WriteLine("Model unloaded due to inactivity");
}
}
public async Task<string> GenerateAsync(string prompt)
{
_lastUsed = DateTime.Now;
if (_service == null)
{
// Reload model
_service = CreateService();
}
return await _service.GenerateAsync(prompt);
}
}
लिखना जारी रखें
public async Task<string> GenerateWithRetryAsync(string prompt, int maxRetries = 3)
{
for (int i = 0; i < maxRetries; i++)
{
try
{
return await GenerateAsync(prompt);
}
catch (OutOfMemoryException)
{
_logger.LogWarning("OOM error, reducing max tokens");
_parameters.MaxTokens = Math.Max(100, _parameters.MaxTokens / 2);
}
catch (Exception ex)
{
_logger.LogError(ex, "Generation failed, attempt {Attempt}/{Max}", i + 1, maxRetries);
if (i == maxRetries - 1) throw;
await Task.Delay(1000 * (i + 1)); // Exponential backoff
}
}
throw new Exception("Generation failed after retries");
}
कोड उदाहरण
हम सफलतापूर्वक स्थानीय एनएफएम को एकीकृत किया है:**एलएचएआ तीव्र**C# एकीकरण के लिए
पार्ट 7: सामग्री बनाना बनाने की इंजीनियरिंग की पूर्वसूचना देता है (g)
भाग ६: स्थानीय संयोजन(यह पोस्ट)!
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.