初始化项目，由ModelHub XC社区提供模型

Model: Mungert/sarvam-translate-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,85 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f16.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+sarvam-translate.imatrix filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f32.mmproj filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-q8_0.mmproj filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-f16.mmproj filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-bf16.mmproj filter=lfs diff=lfs merge=lfs -text
+sarvam-translate-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,354 @@
+---
+library_name: transformers
+license: gpl-3.0
+language:
+- as
+- bn
+- brx
+- doi
+- gom
+- gu
+- en
+- hi
+- kn
+- ks
+- mai
+- ml
+- mni
+- mr
+- ne
+- or
+- pa
+- sa
+- sat
+- sd
+- ta
+- te
+- ur
+base_model:
+- google/gemma-3-4b-it
+base_model_relation: finetune
+pipeline_tag: translation
+---
+
+# <span style="color: #7FFF7F;">sarvam-translate GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`1f63e75f`](https://github.com/ggerganov/llama.cpp/commit/1f63e75f3b5dc7f44dbe63c8a41d23958fe95bc0).
+
+
+
+
+## <span style="color: #7FFF7F;"> Quantization beyond the IMatrix</span>
+
+Testing a new quantization method using rules to bump important layers above what the standard imatrix would use.
+
+I have found that the standard IMatrix does not perform very well at low bit quantiztion and for MOE models. So I am using llama.cpp --tensor-type to bump up selected layers. See [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+This does create larger model files but increases precision for a given model size.
+
+### **Please provide feedback on how you find this method performs**
+
+
+
+
+## **Choosing the Right Model Format**  
+
+Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
+
+### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
+- A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
+- Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
+- Recommended if your hardware supports **BF16 acceleration** (check your device's specs).  
+- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
+
+📌 **Use BF16 if:**  
+✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
+✔ You want **higher precision** while saving memory.  
+✔ You plan to **requantize** the model into another format.  
+
+📌 **Avoid BF16 if:**  
+❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
+❌ You need compatibility with older devices that lack BF16 optimization.  
+
+---
+
+### **F16 (Float 16) – More widely supported than BF16**  
+- A 16-bit floating-point **high precision** but with less of range of values than BF16. 
+- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
+- Slightly lower numerical precision than BF16 but generally sufficient for inference.  
+
+📌 **Use F16 if:**  
+✔ Your hardware supports **FP16** but **not BF16**.  
+✔ You need a **balance between speed, memory usage, and accuracy**.  
+✔ You are running on a **GPU** or another device optimized for FP16 computations.  
+
+📌 **Avoid F16 if:**  
+❌ Your device lacks **native FP16 support** (it may run slower than expected).  
+❌ You have memory limitations.  
+
+---
+
+### **Hybrid Precision Models (e.g., `bf16_q8_0`, `f16_q4_K`) – Best of Both Worlds**  
+These formats selectively **quantize non-essential layers** while keeping **key layers in full precision** (e.g., attention and output layers).
+
+- Named like `bf16_q8_0` (meaning **full-precision BF16 core layers + quantized Q8_0 other layers**).  
+- Strike a **balance between memory efficiency and accuracy**, improving over fully quantized models without requiring the full memory of BF16/F16.  
+
+📌 **Use Hybrid Models if:**  
+✔ You need **better accuracy than quant-only models** but can’t afford full BF16/F16 everywhere.  
+✔ Your device supports **mixed-precision inference**.  
+✔ You want to **optimize trade-offs** for production-grade models on constrained hardware.  
+
+📌 **Avoid Hybrid Models if:**  
+❌ Your target device doesn’t support **mixed or full-precision acceleration**.  
+❌ You are operating under **ultra-strict memory limits** (in which case use fully quantized formats).  
+
+---
+
+### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
+Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
+- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
+- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
+
+📌 **Use Quantized Models if:**  
+✔ You are running inference on a **CPU** and need an optimized model.  
+✔ Your device has **low VRAM** and cannot load full-precision models.  
+✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
+
+📌 **Avoid Quantized Models if:**  
+❌ You need **maximum accuracy** (full-precision models are better for this).  
+❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
+
+---
+
+### **Very Low-Bit Quantization (IQ3_XS, IQ3_S, IQ3_M, Q4_K, Q4_0)**  
+These models are optimized for **very high memory efficiency**, making them ideal for **low-power devices** or **large-scale deployments** where memory is a critical constraint.  
+
+- **IQ3_XS**: Ultra-low-bit quantization (3-bit) with **very high memory efficiency**.  
+  - **Use case**: Best for **ultra-low-memory devices** where even Q4_K is too large.  
+  - **Trade-off**: Lower accuracy compared to higher-bit quantizations.  
+
+- **IQ3_S**: Small block size for **maximum memory efficiency**.  
+  - **Use case**: Best for **low-memory devices** where **IQ3_XS** is too aggressive.  
+
+- **IQ3_M**: Medium block size for better accuracy than **IQ3_S**.  
+  - **Use case**: Suitable for **low-memory devices** where **IQ3_S** is too limiting.  
+
+- **Q4_K**: 4-bit quantization with **block-wise optimization** for better accuracy.  
+  - **Use case**: Best for **low-memory devices** where **Q6_K** is too large.  
+
+- **Q4_0**: Pure 4-bit quantization, optimized for **ARM devices**.  
+  - **Use case**: Best for **ARM-based devices** or **low-memory environments**.  
+
+### **Ultra Low-Bit Quantization (IQ1_S IQ1_M IQ2_S IQ2_M IQ2_XS IQ2_XSS)** 
+- *Ultra-low-bit quantization (1 2-bit) with **extreme memory efficiency**.  
+  - **Use case**: Best for  cases were you have to fit the model into very constrained memory
+  - **Trade-off**: Very Low Accuracy. May not function as expected. Please test fully before using.
+
+---
+
+### **Summary Table: Model Format Selection**  
+
+
+| Model Format             | Precision        | Memory Usage     | Device Requirements             | Best Use Case                                                |  
+|--------------------------|------------------|------------------|----------------------------------|--------------------------------------------------------------|  
+| **BF16**                 | Very High        | High             | BF16-supported GPU/CPU           | High-speed inference with reduced memory                    |  
+| **F16**                  | High             | High             | FP16-supported GPU/CPU           | Inference when BF16 isn’t available                     |  
+| **Q4_K**                 | Medium-Low       | Low              | CPU or Low-VRAM devices          | Memory-constrained inference                                |  
+| **Q6_K**                 | Medium           | Moderate         | CPU with more memory             | Better accuracy with quantization                           |  
+| **Q8_0**                 | High             | Moderate         | GPU/CPU with moderate VRAM       | Highest accuracy among quantized models                     |  
+| **IQ3_XS**               | Low              | Very Low         | Ultra-low-memory devices         | Max memory efficiency, low accuracy                         |  
+| **IQ3_S**                | Low              | Very Low         | Low-memory devices               | Slightly more usable than IQ3_XS                            |  
+| **IQ3_M**                | Low-Medium       | Low              | Low-memory devices               | Better accuracy than IQ3_S                                  |  
+| **Q4_0**                 | Low              | Low              | ARM-based/embedded devices       | Llama.cpp automatically optimizes for ARM inference                                 |  
+| **Ultra Low-Bit (IQ1/2_*)** | Very Low      | Extremely Low     | Tiny edge/embedded devices        | Fit models in extremely tight memory; low accuracy           |  
+| **Hybrid (e.g., `bf16_q8_0`)** | Medium–High | Medium           | Mixed-precision capable hardware | Balanced performance and memory, near-FP accuracy in critical layers |
+
+---
+
+
+
+
+
+# Sarvam-Translate
+<p align="center">
+  <a href="https://dashboard.sarvam.ai/translate"
+     target="_blank" rel="noopener noreferrer">
+    <img
+      src="https://img.shields.io/badge/🚀 Try on Sarvam&nbsp;Playground-1488CC?style=for-the-badge&logo=rocket"
+      alt="Try on Sarvam Playground"
+    />
+  </a>
+</p>
+Sarvam-Translate is an advanced translation model from Sarvam AI, specifically designed for comprehensive, document-level translation across the 22 official Indian languages, built on Gemma3-4B-IT. It addresses modern translation needs by moving beyond isolated sentences to handle long-context inputs, diverse content types, and various formats. Sarvam-Translate aims to provide high-quality, contextually aware translations for Indian languages, which have traditionally lagged behind high-resource languages in LLM performance.
+
+Learn more about Sarvam-Translate in our detailed [blog post](https://www.sarvam.ai/blogs/sarvam-translate).
+
+## Key Features
+- **Comprehensive Indian Language Support**: Focus on the 22 official Indian languages, ensuring nuanced and accurate translations.
+- **Advanced Document-Level Translation**: Translates entire documents, web pages, speeches, textbooks, and scientific articles, not just isolated sentences.
+- **Versatile Format Handling**: Processes a wide array of input formats, including markdown, digitized content (handling OCR errors), documents with embedded math and chemistry equations, and code files (translating only comments).
+- **Context-Aware & Inclusive**: Engineered to respect different contexts, formats, styles (formal/informal), and ensure inclusivity (e.g., appropriate gender attribution).
+
+## Supported languages list
+
+`Assamese`, `Bengali`, `Bodo`, `Dogri`, `Gujarati`, `English`, `Hindi`, `Kannada`, `Kashmiri`, `Konkani`, `Maithili`, `Malayalam`, `Manipuri`, `Marathi`, `Nepali`, `Odia`, `Punjabi`, `Sanskrit`, `Santali`, `Sindhi`, `Tamil`, `Telugu`, `Urdu`
+
+## Quickstart
+The following code snippet demonstrates how to use Sarvam-Translate using Transformers.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "sarvamai/sarvam-translate"
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name).to('cuda:0')
+
+# Translation task
+tgt_lang = "Hindi"
+input_txt = "Be the change you wish to see in the world."
+
+# Chat-style message prompt
+messages = [
+    {"role": "system", "content": f"Translate the text below to {tgt_lang}."},
+    {"role": "user", "content": input_txt}
+]
+
+# Apply chat template to structure the conversation
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+# Tokenize and move input to model device
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+# Generate the output
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=0.01,
+    num_return_sequences=1
+)
+output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+output_text = tokenizer.decode(output_ids, skip_special_tokens=True)
+
+print("Input:", input_txt)
+print("Translation:", output_text)
+
+```
+
+## vLLM Deployment
+
+
+### Server:
+```bash
+vllm serve sarvamai/sarvam-translate --port 8000 --dtype bfloat16
+```
+
+### Client:
+```python
+from openai import OpenAI
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+
+tgt_lang = 'Hindi'
+input_txt = 'Be the change you wish to see in the world.'
+messages = [{"role": "system", "content": f"Translate the text below to {tgt_lang}."}, {"role": "user", "content": input_txt}]
+
+
+response = client.chat.completions.create(model=model, messages=messages, temperature=0.01)
+output_text = response.choices[0].message.content
+
+print("Input:", input_txt)
+print("Translation:", output_text)
+```
+
+## With Sarvam APIs
+
+Refer our [python client documentation](https://pypi.org/project/sarvamai/).
+
+Sample code:
+
+```python
+from sarvamai import SarvamAI
+client = SarvamAI()
+response = client.text.translate(
+    input="Be the change you wish to see in the world.",
+    source_language_code="en-IN",
+    target_language_code="hi-IN",
+    speaker_gender="Male",
+    model="sarvam-translate:v1",
+)
+```
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a Quantum Network Monitor Agent to run the .net code from. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊

sarvam-translate-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0dd1047ec70d350f21bff12cf652d181a7f24a4e161a81dc6b70e7b1384c63
+size 7767802624

sarvam-translate-bf16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c6336bdbf47bb5e4fcd83a7f37850cb43ef9f46a4ac379a92075ce8370a135
+size 851251936

sarvam-translate-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:201a879cec3f63540553f89d424dc4d17d76827b57a5ad420d190050cabff98d
+size 5845959424

sarvam-translate-f16.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a160f9b04e99a45f5f61455ae7ba4ec911171ec3a2245734cecf0513dc653d
+size 851251936

sarvam-translate-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ffbe90b5d2136985db6f2f4ec75decf0bda066538e8d00b591716018860d407
+size 5845959424

sarvam-translate-f32.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2e22ad8b798e265afa0fb83d580accb34a4160c1e5d2ef6a328ec73c9c8763
+size 1673392864

sarvam-translate-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5d3ea22e04fdc533fabbcc558cf9d774c134d18014476f311925cf2dbc0e2ef
+size 1368816704

sarvam-translate-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50eace1f97bd2bf342543d5acfa8613c635f4364621deb3a8765929649cbbae3
+size 1290992704

sarvam-translate-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a728006bf069cb82f6f3f6e094e043b362f1c71f407e96e0079ddbdfd551598
+size 1592908864

sarvam-translate-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b02dc6ee39c6431e465a960d0862ed65ee1209de4764cd1a1a6e30f2c0e3b8c
+size 1532288064

sarvam-translate-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af81dc6f484b14626278b8718b89cac0b9acef034535ef95bab730a1a34789b3
+size 1494154304

sarvam-translate-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ad84a8c2eea43cf0fca7cd59b36a9c00eda4f17772342de4feb1c0bf17340a
+size 1402403904

sarvam-translate-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e2926a8956400f9b6365e86f83fa60be00bcdd1554406cd137d35c75ce891b
+size 1875369024

sarvam-translate-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f0e811a165c8124e7459ec2570aa48f7c01b7ff4a556e19d0ab716a9ca7e80
+size 1848212544

sarvam-translate-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd7eda12c05b88ba828447a8c6c5a7dc8ae649924b53babf68bb02a2bcb09bb
+size 1774238784

sarvam-translate-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f27fcd33db120886ae1ba91a3e3b35ed6de46d1c13cc732950a714b29e128c
+size 1700265024

sarvam-translate-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1473bba165e8ab817edc523f7b5a2c334b2c54371d168986dfbf822fd9cb40
+size 2363511104

sarvam-translate-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be7969239c58d754fb4619c208de8897825fe6953a8deda67cffe32447875f0
+size 2263241024

sarvam-translate-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c013ae57a9ad7317ad88f37e38ed91049d859695e12ea3df513bba475887b7c0
+size 1716384064

sarvam-translate-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945e3d9ad582922718d79c73ac9be15a1d5fe4eb4bc11a28ddf5511306bb0ebe
+size 1537244224

sarvam-translate-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00e55b9e0b79740ef98185e19beb8f423bf98987730f4aa00d0be49f3831d4a
+size 2082730304

sarvam-translate-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e713b1ea98152db76e0fb36030cf373a2109c75796e2d99aea67194b4b550f4a
+size 1875901504

sarvam-translate-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed49603845a8e0cc5d578d48df027998ae1bfa2e721c724ae6edc4f4a0b35a8
+size 2190453824

sarvam-translate-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b37a82bc3d5976cd84045941a4891334746bc7b90dd24c06d50d4a80eeb8bc20
+size 2432947264

sarvam-translate-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b61ebb739505d9884482170087949b3076e1c095b24bdab68f3d018ef1dab2d
+size 2464497984

sarvam-translate-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe82f5ff77f83d8aa8b78c1c1e78f3690f473e3c211ce2d869fe4da79ed1afeb
+size 2397589824

sarvam-translate-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14c72e442b991ec166dc77e19d7ed45146e83f9bd879c0fbbb8599156cb97aad
+size 2675440704

sarvam-translate-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a6fac6f63d2fac7946abfee1f756332c573e991c49ff391698610c77b1fd7b
+size 2917934144

sarvam-translate-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d7cb9af6983d89129fa3c7de0c098d9e0516d8b05f4d82f0738236087f6055
+size 2835267904

sarvam-translate-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cba78da0f422904031fbc6dfa3ac4d6b0c8eb0a2e117e5f2fe6a4c7d26d66c4
+size 2800800064

sarvam-translate-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46266d04e37d69f1df3d4b6708d58d8ec54ef8c8c1d363ce614a8c3ab7a632fa
+size 3190739264

sarvam-translate-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f53e8684210b3ba170fdee2bb01d286ddecede28f033293fddd3e5cdff316964
+size 4130401024

sarvam-translate-q8_0.mmproj

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92d18f715001de72083431366accd65f55b753e765fe3738f8b1806cdfbaa2e7
+size 591378016

sarvam-translate-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:040a74815c596ec0d25f4356ef7a99e5387cd36f24111304c7b61a121ba8216a
+size 1235472704

sarvam-translate-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0300e9d3ce60709c3736d3b2b25a5ea706e65ab1574e3aba73b33ea48c4cdbe
+size 1385877824

sarvam-translate.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e2492ca95820bf901f0fef40d9d15f3702d75b60f81001fec93661c1db3439
+size 3419902