Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,77 @@
+*.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
+granite-8b-code-base-4k-f16.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q2_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k.imatrix filter=lfs diff=lfs merge=lfs -text
+granite-8b-code-base-4k-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,381 @@
+---
+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 | Phase 2
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+model-index:
+- name: granite-8b-code-base-4k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+        type: mbpp
+        name: MBPP
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 42.2
+      veriefied: false      
+  - task:
+      type: text-generation
+    dataset:
+        type: evalplus/mbppplus
+        name: MBPP+
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 49.6
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack 
+        name: HumanEvalSynthesis(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 43.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 52.4
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 56.1
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 31.7
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 43.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name: HumanEvalSynthesis(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 32.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 23.5
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 32.3
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 25.0
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 23.2
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 28.0
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalExplain(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 19.5
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 22.6
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 35.4
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 38.4
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 37.2
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 28.7 
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack  
+        name:  HumanEvalFix(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 15.2
+      veriefied: false
+---
+
+# <span style="color: #7FFF7F;">granite-8b-code-base-4k 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 [`5dd942de`](https://github.com/ggerganov/llama.cpp/commit/5dd942de5922a22ec8446a4ad2203738dbcb9389).
+
+
+
+
+
+---
+
+## <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-8B-Code-Base-4K
+
+## Model Summary
+**Granite-8B-Code-Base-4K** is a decoder-only code model designed for code generative tasks (e.g., code generation, code explanation, code fixing, etc.). It is trained from scratch with a two-phase training strategy. In phase 1, our model is trained on 4 trillion tokens sourced from 116 programming languages, ensuring a comprehensive understanding of programming languages and syntax. In phase 2, our model is trained on 500 billion tokens with a carefully designed mixture of high-quality data from code and natural language domains to improve the models’ ability to reason and follow instructions.
+
+- **Developers:** IBM Research
+- **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)
+- **Paper:** [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://arxiv.org/abs/2405.04324)
+- **Release Date**: May 6th, 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 include 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 **8B 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-8B-Code-Base-4K** model.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # or "cpu"
+model_path = "ibm-granite/granite-8b-code-base-4k"
+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
+- **Data Collection and Filtering:** Pretraining code data is sourced from a combination of publicly available datasets (e.g., [GitHub Code Clean](https://huggingface.co/datasets/codeparrot/github-code-clean), [Starcoder data](https://huggingface.co/datasets/bigcode/starcoderdata)), and additional public code repositories and issues from GitHub. We filter raw data to retain a list of 116 programming languages. After language filtering, we also filter out low-quality code. 
+- **Exact and Fuzzy Deduplication:** We adopt an aggressive deduplication strategy that includes both exact and fuzzy deduplication to remove documents having (near) identical code content.
+- **HAP, PII, Malware Filtering:** We apply a HAP content filter that reduces models' likelihood of generating hateful, abusive, or profane language. We also make sure to redact Personally Identifiable Information (PII) by replacing PII content (e.g., names, email addresses, keys, passwords) with corresponding tokens (e.g., ⟨NAME⟩, ⟨EMAIL⟩, ⟨KEY⟩, ⟨PASSWORD⟩). Moreover, we scan all datasets using [ClamAV](https://www.clamav.net/) to identify and remove instances of malware in the source code.
+- **Natural Language Datasets:** In addition to collecting code data for model training, we curate several publicly available high-quality natural language datasets to improve models' proficiency in language understanding and mathematical reasoning. Unlike the code data, we do not deduplicate these datasets.
+
+## 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-8B-Code-Base-4K** 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-8B-Code-Base-4K** 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! 😊

granite-8b-code-base-4k-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e08601802120ff216166fa10f84bafaa4f0d41da16bf4610c54376ef928dd0
+size 16115269824

granite-8b-code-base-4k-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29aba62ab113e7212b4db369395bcfd944afd88c35cc9d7e47fed3759408ef11
+size 11443863744

granite-8b-code-base-4k-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b93524a6f63462e5de144210bc2255913cf01648a4277435887f8719346861
+size 11443863744

granite-8b-code-base-4k-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c466b6b6be11ff25efb701e2afa9a4cbbea06f392fccc08d8d5f1134c5bb66a5
+size 2904261120

granite-8b-code-base-4k-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b15c1e9d33d3fcd02a16d6fd2a2fa5e2187866746ac0c746ff7839e4d521057d
+size 2759033344

granite-8b-code-base-4k-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91a4bf3a579650cee8e5ca2be83a0da5be9735cd40b70cdbe16ecd6ad04d2e2
+size 2669249024

granite-8b-code-base-4k-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26dbca5c2c1c31ba903841dea495b139e828707c41c74124204eebc59dc6808e
+size 2441314816

granite-8b-code-base-4k-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2afc86978738f210514b7e4af09cf0cfbf26df662048bf1c1bdbbc3295a1ca
+size 3780739584

granite-8b-code-base-4k-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b56de90e28cc47786668862127c40021e4616d9031e5d265ef8806c66f2ab103
+size 3780739584

granite-8b-code-base-4k-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9465ecd4544b3b33627cf3214ed154ff19952d90f59f3028d1ba4fc5d7efa47d
+size 3388441088

granite-8b-code-base-4k-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b97c1b9972094f03f92e9f64f50da8f44025628f323bcd543b78ce10ae50a5
+size 3291709952

granite-8b-code-base-4k-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c5a2ebf67968466b660a3eda71eb63735c1c5d6e7a2496c29f9fccc1770d803
+size 4609769984

granite-8b-code-base-4k-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64a41dfeb8a39b80aa02499138466c49c88cbea4519c236cda70e0eb987e73d
+size 4369121792

granite-8b-code-base-4k-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a03f128bdd8fa611429de4ad04f63aa0ef1ac57a2f6a99e3aa49e8fc0841434
+size 3019997696

granite-8b-code-base-4k-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66163b20a13c8ef14d23bafc9388a855af1f94d87da1ba617aa93bcde57e9e98
+size 2993259008

granite-8b-code-base-4k-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179ff99ea30413c4507dbb180111e48674d39241ec6bab4ab9ef94e169cb51fd
+size 3914433024

granite-8b-code-base-4k-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a109e75603d09ab79fa6733891e6c6d555132aa71cb97baa2df90e5d42430e
+size 3887694336

granite-8b-code-base-4k-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f3e745b8c0611e4e6c82ff0c92c4298a52d4445c87a22ea839227c9cb8a060
+size 4538991104

granite-8b-code-base-4k-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77b973397d56a9e8553fa74a2b687b3bff40b5d5b4ae579bccd7d56c38ab42a9
+size 5042307584

granite-8b-code-base-4k-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b20670b190ccec88c7f6022f4bace8b878c81a6241f9e8b71182d8b09b8aa5
+size 4832788992

granite-8b-code-base-4k-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d251a8a9c6888b6f0bc4e04608321c04b7722007af256f4b18681bdb56cb13e
+size 4670587392

granite-8b-code-base-4k-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26626d7ffd844096b27ad6ce2c4c445af60049d616103f279fffaac3a9d59129
+size 5545624064

granite-8b-code-base-4k-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e80d519de0598e20fe10c3ac3059668868a15ce97cf6d41f62e420b9ce2342f
+size 6048940544

granite-8b-code-base-4k-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5d39c799aa86fac78090bcf90f286487e3fe6a4a98adb2d882a2f5a3c30fea9
+size 5740593664

granite-8b-code-base-4k-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa2d706a832788710ff35a1928f101a93b7cd5e9f48024820e5a5d4778b26b0c
+size 5657035264

granite-8b-code-base-4k-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46a7a42fc8c2cac2b56fbd85c9ef730bf98a4a54a92db1da0ee3ee1ebe3d54f5
+size 6615171584

granite-8b-code-base-4k-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fff85c6f239e0c1d24e0689ae043543a9f7c923bb4bb491cf51eee3e845264
+size 8565522624

granite-8b-code-base-4k.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc047d4968b63a0fd1fa4d79b79d173bfabc06b98ecc8c4ced9b8f993c9cbd4b
+size 5611728