初始化项目，由ModelHub XC社区提供模型

Model: Mungert/granite-3b-code-base-128k-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,76 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+granite-3b-code-base-128k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k.imatrix filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-3b-code-base-128k-q4_1.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,349 @@
+---
+pipeline_tag: text-generation
+inference: false
+license: apache-2.0
+datasets:
+- codeparrot/github-code-clean
+- bigcode/starcoderdata
+# - Stackexchange
+# - CommonCrawl
+- open-web-math/open-web-math
+- math-ai/StackMathQA
+# - Arxiv
+# - Wikipedia
+# - conceptofmind/FLAN_2022 # Original link is broken, we used IBM's filtered version
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+model-index:
+- name: granite-3b-code-base-128k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack 
+        name: HumanEvalSynthesis (Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 36.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis (Average)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 30.5
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain (Average)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 22.4
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix (Average)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 19.9
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repoqa  
+        name:  RepoQA (Python@16K)
+    metrics:
+    - name: pass@1 (thresh=0.5)
+      type: pass@1 (thresh=0.5)
+      value: 40.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repoqa  
+        name:  RepoQA (C++@16K)
+    metrics:
+    - name: pass@1 (thresh=0.5)
+      type: pass@1 (thresh=0.5)
+      value: 36.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repoqa  
+        name:  RepoQA (Java@16K)
+    metrics:
+    - name: pass@1 (thresh=0.5)
+      type: pass@1 (thresh=0.5)
+      value: 37.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repoqa  
+        name:  RepoQA (TypeScript@16K)
+    metrics:
+    - name: pass@1 (thresh=0.5)
+      type: pass@1 (thresh=0.5)
+      value: 27.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repoqa  
+        name:  RepoQA (Rust@16K)
+    metrics:
+    - name: pass@1 (thresh=0.5)
+      type: pass@1 (thresh=0.5)
+      value: 29.0
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: lcc  
+        name:  LCC (Balanced)
+    metrics:
+    - name: Exact Match@4K 
+      type: Exact Match@4K
+      value: 54.6
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: lcc  
+        name:  LCC (Balanced)
+    metrics:
+    - name: Exact Match@8K 
+      type: Exact Match@8K
+      value: 56.8
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: lcc  
+        name:  LCC (Balanced)
+    metrics:
+    - name: Exact Match@16K 
+      type: Exact Match@16K
+      value: 52.2
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: lcc  
+        name:  LCC (Balanced)
+    metrics:
+    - name: Exact Match@32K 
+      type: Exact Match@32K
+      value: 57.8
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repobench  
+        name: RepoBench-P (Balanced)
+    metrics:
+    - name: Exact Match@4K 
+      type: Exact Match@4K
+      value: 39.8
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repobench  
+        name: RepoBench-P (Balanced)
+    metrics:
+    - name: Exact Match@8K 
+      type: Exact Match@8K
+      value: 46.8
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repobench  
+        name: RepoBench-P (Balanced)
+    metrics:
+    - name: Exact Match@16K 
+      type: Exact Match@16K
+      value: 43.1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+        type: repobench  
+        name: RepoBench-Pn(Balanced)
+    metrics:
+    - name: Exact Match@32K 
+      type: Exact Match@32K
+      value: 45.3
+      verified: false
+---
+
+# <span style="color: #7FFF7F;">granite-3b-code-base-128k 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 [`0a5a3b5c`](https://github.com/ggerganov/llama.cpp/commit/0a5a3b5cdfd887cf0f8e09d9ff89dee130cfcdde).
+
+
+
+
+
+---
+
+## <span style="color: #7FFF7F;">Quantization Beyond the IMatrix</span>
+
+I've been experimenting with a new quantization approach that selectively elevates the precision of key layers beyond what the default IMatrix configuration provides.
+
+In my testing, standard IMatrix quantization underperforms at lower bit depths, especially with Mixture of Experts (MoE) models. To address this, I'm using the `--tensor-type` option in `llama.cpp` to manually "bump" important layers to higher precision. You can see the implementation here:  
+👉 [Layer bumping with llama.cpp](https://github.com/Mungert69/GGUFModelBuilder/blob/main/model-converter/tensor_list_builder.py)
+
+While this does increase model file size, it significantly improves precision for a given quantization level.
+
+### **I'd love your feedback—have you tried this? How does it perform for you?**
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)
+
+# Granite-3B-Code-Base-128K
+
+## Model Summary
+**Granite-3B-Code-Base-128K** extends the context length of Granite-3B-Code-Base from 2K to 128K with continual pretraining using the original training data but with repository-level file packing and per-language length upsampling, that we found to be critical for long-context pretraining. 
+We adopt an progressive training strategy where we doubled the context window until it reached the desired length of 128K by appropriately adjusting RoPE theta. We trained on 4B tokens total for all stages, which is only 0.1% of Granite-3B-Code-Base's original pre-training data. 
+
+- **Developers:** IBM Research
+- **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)
+- **Paper:** [Scaling Granite Code Models to 128K Context](https://arxiv.org/abs/2405.04324)
+- **Release Date**: July 18th, 2024
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).
+
+## Usage
+### Intended use
+Prominent enterprise use cases of LLMs in software engineering productivity with 128K context length support that includes code generation, code explanation, code fixing, generating unit tests, generating documentation, addressing technical debt issues, vulnerability detection, code translation, and more. All Granite Code Base models, including the **3B parameter model**, are able to handle these tasks as they were trained on a large amount of code data from 116 programming languages. 
+
+### Generation
+This is a simple example of how to use **Granite-3B-Code-Base-128K** model.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # or "cpu"
+model_path = "ibm-granite/granite-3b-code-base-128k"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+# change input text as desired
+input_text = "def generate():"
+# tokenize the text
+input_tokens = tokenizer(input_text, return_tensors="pt")
+# transfer tokenized inputs to the device
+for i in input_tokens:
+    input_tokens[i] = input_tokens[i].to(device)
+# generate output tokens
+output = model.generate(**input_tokens)
+# decode output tokens into text
+output = tokenizer.batch_decode(output)
+# loop over the batch to print, in this example the batch size is 1
+for i in output:
+    print(i)
+```
+
+## Training Data
+Starting from the base Granite model, this model was further pretrained on repository-level code data with per-language context-length oversampling, allowing it to effectively utilize up to 128K tokens of context. This continued training stage focused on a curated selection of programming languages, such as Python, C, C++, Go, Java, JavaScript, and TypeScript.
+
+## Infrastructure
+We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.
+
+## Ethical Considerations and Limitations
+The use of Large Language Models involves risks and ethical considerations people must be aware of. Regarding code generation, caution is urged against complete reliance on specific code models for crucial decisions or impactful information as the generated code is not guaranteed to work as intended. **Granite-3B-Code-Base-128K** model is not the exception in this regard. Even though this model is suited for multiple code-related tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying source code verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use **Granite-3B-Code-Base-128K** model with ethical intentions and in a responsible way. 
+
+
+<!--End Original Model Card-->
+
+---
+
+# <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](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. 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! 😊

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

granite-3b-code-base-128k-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705fa7d56ba7fbc893b200c3444e827ed2bff0ded03f463fcc146b7cc96bb489
+size 6969219680

granite-3b-code-base-128k-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf75ae1c98e79a7cbe9846e52073d56ee5e0d4a7fd409dd95883f0b132d3d01
+size 5003139680

granite-3b-code-base-128k-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e46feb1ecd61a70aa00fb169a4da117167cf50217610d3f364034e507912bb0b
+size 5003139680

granite-3b-code-base-128k-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe8b7485df36d139fa08c50c0c7167e77835bbc970c6882720a56e9d3df4912
+size 1273854912

granite-3b-code-base-128k-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a72289beddc09220b66dfc71492aa38c463f5e6999201940571ce8bc34fdfa5
+size 1214053312

granite-3b-code-base-128k-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f8f176557d38cd99d68896900498883ad9de85a6d0734e9aecc85b75243c8e
+size 1173912512

granite-3b-code-base-128k-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86979aab62f45504a43d87bc2e109263adb727c277d13fea89ac2dd7a6fb40df
+size 1077042112

granite-3b-code-base-128k-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:211402b4231729eefee161394408d4b382f34ff89926c3b2fead90836f56e578
+size 1654987712

granite-3b-code-base-128k-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0cc960b8794f06c721dcbcfeaf385596f2e4451cd3b36c4a82684ecdce149a
+size 1654987712

granite-3b-code-base-128k-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b70e0d9757405b6f81aa593abd3472e17ace154e12c8747d5ee80785e1112f
+size 1482955712

granite-3b-code-base-128k-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5904aff168c3a8d0b487a24145adfa41678b118b5073f9a43ca7b3ceb817684a
+size 1437080512

granite-3b-code-base-128k-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6061e3acdd0ec37981391e01ed8de1ce9175490c3b4e555e9eddcb40355ab4
+size 1997331392

granite-3b-code-base-128k-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c8770bcf54554a98e408443f9410438d4350421354ab85ca961ef826584ae3
+size 1892473792

granite-3b-code-base-128k-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2e0726f3f444d3b7b4afeb76e43dadc9a84bd903509c53eb2e47a3335af68a0
+size 1331321792

granite-3b-code-base-128k-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1961afc4687e7a1b1ea4e0759314b21615750a72c8f8cb68e9bec385edc083
+size 1314610112

granite-3b-code-base-128k-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5539ef8d0677f70b2e93e48f5f586ad26d74147265b38ec118847ee50f746d6
+size 1713888192

granite-3b-code-base-128k-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77af5b53fa8612503055da7edf16b972a7b2b685816a06257807eabfebaa4f7e
+size 1697176512

granite-3b-code-base-128k-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69eb4ac1ac5513eeeafef387d7d007a3c081880f9b9dc415622b9005890561ae
+size 1964891072

granite-3b-code-base-128k-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ef010d88af773c7290c6c48c9afdf5e8a07b9afaa28427c14fd8591d869a80
+size 2182470592

granite-3b-code-base-128k-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341f79f315c1aced35c474498e1e2d1abf33832af176c39bd33b3c607ac9cc7e
+size 2104236992

granite-3b-code-base-128k-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa7ebede6f140f103cf549d38087b5d385bf78501c1a6842c5bdd6141dd71d5
+size 2036652992

granite-3b-code-base-128k-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19231bb13848c4988c64ec0c449172f2fa7f641908ae0c2ac37196e1fdc01aa
+size 2400050112

granite-3b-code-base-128k-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dde82af1cf7ec24d2faa864b3c24410d9fd3860bdc8d13386d3eab1c1e79dce
+size 2617629632

granite-3b-code-base-128k-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9851c78e176ee3e3b4eb1bb2fb14cb61b5cafecdd32f35344ffa641da4ba519
+size 2493356992

granite-3b-code-base-128k-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cc82279dfe415af6ed92ed89fe03cfbf859da13bad333a439879e59e3ecd26d
+size 2458540992

granite-3b-code-base-128k-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e537e968a1adc79d5102531bafcccc95c5f8488d7b04e93904ab0ebedc164537
+size 2862406592

granite-3b-code-base-128k-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a6340fb3c0a5a0c34480f04758f61f5966a3a621d2ffbb3dde13f6e918af5f
+size 3705526880

granite-3b-code-base-128k.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428cdf271eae8b1f7f72fb6e7d2e716f9dcc46da8822b72e696b1949d4c75791
+size 3284268