commit 864760c431a68277019ac678b41373fae3f9c61d Author: ModelHub XC Date: Tue Sep 22 10:42:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Mungert/granite-3b-code-instruct-128k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d0563e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,75 @@ +*.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-instruct-128k-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-bf16.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k.imatrix filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q5_1.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-3b-code-instruct-128k-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..2faed36 --- /dev/null +++ b/README.md @@ -0,0 +1,277 @@ +--- +pipeline_tag: text-generation +inference: false +license: apache-2.0 +datasets: + - bigcode/commitpackft + - TIGER-Lab/MathInstruct + - meta-math/MetaMathQA + - glaiveai/glaive-code-assistant-v3 + - glaive-function-calling-v2 + - bugdaryan/sql-create-context-instruction + - garage-bAInd/Open-Platypus + - nvidia/HelpSteer + - bigcode/self-oss-instruct-sc2-exec-filter-50k +metrics: +- code_eval +library_name: transformers +tags: +- code +- granite +model-index: +- name: granite-3b-code-instruct-128k + results: + - task: + type: text-generation + dataset: + type: bigcode/humanevalpack + name: HumanEvalSynthesis (Python) + metrics: + - name: pass@1 + type: pass@1 + value: 53.7 + verified: false + - task: + type: text-generation + dataset: + type: bigcode/humanevalpack + name: HumanEvalSynthesis (Average) + metrics: + - name: pass@1 + type: pass@1 + value: 41.4 + verified: false + - task: + type: text-generation + dataset: + type: bigcode/humanevalpack + name: HumanEvalExplain (Average) + metrics: + - name: pass@1 + type: pass@1 + value: 25.1 + verified: false + - task: + type: text-generation + dataset: + type: bigcode/humanevalpack + name: HumanEvalFix (Average) + metrics: + - name: pass@1 + type: pass@1 + value: 26.2 + 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: 48.0 + 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: 38.0 + 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: 39.0 + 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 +--- + +# granite-3b-code-instruct-128k GGUF Models + + +## Model Generation Details + +This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`0a5a3b5c`](https://github.com/ggerganov/llama.cpp/commit/0a5a3b5cdfd887cf0f8e09d9ff89dee130cfcdde). + + + + + +--- + +## Quantization Beyond the IMatrix + +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?** + + + + +--- + + + Click here to get info on choosing the right GGUF model format + + +--- + + + + + + + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png) + +# Granite-3B-Code-Instruct-128K + +## Model Summary +**Granite-3B-Code-Instruct-128K** is a 3B parameter long-context instruct model fine tuned from *Granite-3B-Code-Base-128K* on a combination of **permissively licensed** data used in training the original Granite code instruct models, in addition to synthetically generated code instruction datasets tailored for solving long context problems. By exposing the model to both short and long context data, we aim to enhance its long-context capability without sacrificing code generation performance at short input context. + +- **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 +The model is designed to respond to coding related instructions over long-conext input up to 128K length and can be used to build coding assistants. + + + +### Generation +This is a simple example of how to use **Granite-3B-Code-Instruct** model. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer +device = "cuda" # or "cpu" +model_path = "ibm-granite/granite-3b-code-instruct-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 +chat = [ + { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." }, +] +chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) +# tokenize the text +input_tokens = tokenizer(chat, 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, max_new_tokens=100) +# 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 +Granite Code Instruct models are trained on a mix of short and long context data as follows. +* Short-Context Instruction Data: [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft), [BigCode-SC2-Instruct](bigcode/self-oss-instruct-sc2-exec-filter-50k), [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA), [Glaive-Code-Assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3), [Glaive-Function-Calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2), [NL2SQL11](https://huggingface.co/datasets/bugdaryan/sql-create-context-instruction), [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer), [OpenPlatypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus) including a synthetically generated dataset for API calling and multi-turn code interactions with execution feedback. We also include a collection of hardcoded prompts to ensure our model generates correct outputs given inquiries about its name or developers. +* Long-Context Instruction Data: A synthetically-generated dataset by bootstrapping the repository-level file-packed documents through Granite-8b-Code-Instruct to improve long-context capability of the model. + +## 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 +Granite code instruct models are primarily finetuned using instruction-response pairs across a specific set of programming languages. Thus, their performance may be limited with out-of-domain programming languages. In this situation, it is beneficial providing few-shot examples to steer the model's output. Moreover, developers should perform safety testing and target-specific tuning before deploying these models on critical applications. The model also inherits ethical considerations and limitations from its base model. For more information, please refer to *[Granite-3B-Code-Base-128K](https://huggingface.co/ibm-granite/granite-3b-code-base-128k)* model card. + + + + +--- + +# 🚀 If you find these models useful + +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! 😊 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/granite-3b-code-instruct-128k-bf16.gguf b/granite-3b-code-instruct-128k-bf16.gguf new file mode 100644 index 0000000..2af8bf0 --- /dev/null +++ b/granite-3b-code-instruct-128k-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c38c68e69a2795cd9b225d8a3b62e95bf7a35ff7261a5aadc9818ddda63895 +size 6969221248 diff --git a/granite-3b-code-instruct-128k-bf16_q8_0.gguf b/granite-3b-code-instruct-128k-bf16_q8_0.gguf new file mode 100644 index 0000000..8b4288f --- /dev/null +++ b/granite-3b-code-instruct-128k-bf16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05ea7b97f7a8e4fa8ec66e1427b253405af22f5ef966da5d44fbd77aedf5aac +size 5003141248 diff --git a/granite-3b-code-instruct-128k-f16_q8_0.gguf b/granite-3b-code-instruct-128k-f16_q8_0.gguf new file mode 100644 index 0000000..f599277 --- /dev/null +++ b/granite-3b-code-instruct-128k-f16_q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8edbc6b66a703cb05b9a1b636e8d97d819897f763c52aaaeb1b3088d5d52cd3 +size 5003141248 diff --git a/granite-3b-code-instruct-128k-iq2_m.gguf b/granite-3b-code-instruct-128k-iq2_m.gguf new file mode 100644 index 0000000..c428d53 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq2_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd40f09cfba8dd06e0989ff7e0da3faad9530048baeb61a0683b1d38fc4aa6e3 +size 1273856448 diff --git a/granite-3b-code-instruct-128k-iq2_s.gguf b/granite-3b-code-instruct-128k-iq2_s.gguf new file mode 100644 index 0000000..2d1f544 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq2_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fc6b56099b5f1fafd5ab97fcb843245b8e79968c67b31eb503071566b783339 +size 1214054848 diff --git a/granite-3b-code-instruct-128k-iq2_xs.gguf b/granite-3b-code-instruct-128k-iq2_xs.gguf new file mode 100644 index 0000000..5dcc3b0 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq2_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7956220552236717e4ee77bf9824a7de87b9158df347f4912f010cc169fa0b7a +size 1173914048 diff --git a/granite-3b-code-instruct-128k-iq2_xxs.gguf b/granite-3b-code-instruct-128k-iq2_xxs.gguf new file mode 100644 index 0000000..9c764db --- /dev/null +++ b/granite-3b-code-instruct-128k-iq2_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad24ec5a3876dc88a9f08323bd76d669acf3207816ee4c4273c46876d059eebb +size 1077043648 diff --git a/granite-3b-code-instruct-128k-iq3_m.gguf b/granite-3b-code-instruct-128k-iq3_m.gguf new file mode 100644 index 0000000..10cb796 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq3_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3686943e3390555aaa0f941232b9d0f11503a48fbeb28c78170e41c2c9a23f82 +size 1654989248 diff --git a/granite-3b-code-instruct-128k-iq3_s.gguf b/granite-3b-code-instruct-128k-iq3_s.gguf new file mode 100644 index 0000000..5f3c711 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq3_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf4f72e4b37476b36334c60dbb8e001cc9a00022aaabed9a1f4f9e73900de6fb +size 1654989248 diff --git a/granite-3b-code-instruct-128k-iq3_xs.gguf b/granite-3b-code-instruct-128k-iq3_xs.gguf new file mode 100644 index 0000000..6f4ff3a --- /dev/null +++ b/granite-3b-code-instruct-128k-iq3_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac7a6289b60a1b5ba93c4fc2caf5c391870d3f8e1892ea192b0371d88de29572 +size 1482957248 diff --git a/granite-3b-code-instruct-128k-iq3_xxs.gguf b/granite-3b-code-instruct-128k-iq3_xxs.gguf new file mode 100644 index 0000000..e692545 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq3_xxs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1af0872c25754b1449c99a3715d65236dbcb98f2f0b00c6cdb74c62f77132bf +size 1437082048 diff --git a/granite-3b-code-instruct-128k-iq4_nl.gguf b/granite-3b-code-instruct-128k-iq4_nl.gguf new file mode 100644 index 0000000..21ef10f --- /dev/null +++ b/granite-3b-code-instruct-128k-iq4_nl.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f36c741ebb669cf3d61db0e880f3600d73ec1cf3cb05b5f338da7616c86ea57 +size 1997332928 diff --git a/granite-3b-code-instruct-128k-iq4_xs.gguf b/granite-3b-code-instruct-128k-iq4_xs.gguf new file mode 100644 index 0000000..4b422d6 --- /dev/null +++ b/granite-3b-code-instruct-128k-iq4_xs.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17c110e96b483284712d59d9eea7b1a00b82a99d6df68ca504e1f445a7c39f55 +size 1892475328 diff --git a/granite-3b-code-instruct-128k-q2_k_m.gguf b/granite-3b-code-instruct-128k-q2_k_m.gguf new file mode 100644 index 0000000..8641a4a --- /dev/null +++ b/granite-3b-code-instruct-128k-q2_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb84588223c869a649d7fb9c33fb8bf28829039d404b342b4e44df555084c0d1 +size 1331323328 diff --git a/granite-3b-code-instruct-128k-q2_k_s.gguf b/granite-3b-code-instruct-128k-q2_k_s.gguf new file mode 100644 index 0000000..9906bb7 --- /dev/null +++ b/granite-3b-code-instruct-128k-q2_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdcb770b04a5fabd2dcacfcd4f1097b664ad9a93943bdcad7470c85b68470ae +size 1314611648 diff --git a/granite-3b-code-instruct-128k-q3_k_m.gguf b/granite-3b-code-instruct-128k-q3_k_m.gguf new file mode 100644 index 0000000..a06ac44 --- /dev/null +++ b/granite-3b-code-instruct-128k-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5090c5f2dbbf6783f2db71c31a93924c21daa66ac4c129af013f64535c1d9d18 +size 1713889728 diff --git a/granite-3b-code-instruct-128k-q3_k_s.gguf b/granite-3b-code-instruct-128k-q3_k_s.gguf new file mode 100644 index 0000000..a0eab4f --- /dev/null +++ b/granite-3b-code-instruct-128k-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71239c522c7a0c677221e116ec1a301c81e3adc96d29a70cbaad0593eaedeb87 +size 1697178048 diff --git a/granite-3b-code-instruct-128k-q4_0.gguf b/granite-3b-code-instruct-128k-q4_0.gguf new file mode 100644 index 0000000..e7d7eff --- /dev/null +++ b/granite-3b-code-instruct-128k-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2614d00bba3f039d29c2e9d0a41519bd74c3d06bd02a13e85ed2e6d0476fa40c +size 1964892608 diff --git a/granite-3b-code-instruct-128k-q4_1.gguf b/granite-3b-code-instruct-128k-q4_1.gguf new file mode 100644 index 0000000..e7dc098 --- /dev/null +++ b/granite-3b-code-instruct-128k-q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f789160601f4cb0407f9af36e5b50e9233cd4c389e26bb15adf2c54d4559eeb9 +size 2182472128 diff --git a/granite-3b-code-instruct-128k-q4_k_m.gguf b/granite-3b-code-instruct-128k-q4_k_m.gguf new file mode 100644 index 0000000..30989ae --- /dev/null +++ b/granite-3b-code-instruct-128k-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e36490d57e7788db1b7b38048af468fa334ffcff9cf8d5fb8a82f1861b3fe50 +size 2104238528 diff --git a/granite-3b-code-instruct-128k-q4_k_s.gguf b/granite-3b-code-instruct-128k-q4_k_s.gguf new file mode 100644 index 0000000..d18cb8f --- /dev/null +++ b/granite-3b-code-instruct-128k-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b794789a42c89049eb1a45b21e94b01586e68b6b145a06007a2656c134977f5 +size 2036654528 diff --git a/granite-3b-code-instruct-128k-q5_0.gguf b/granite-3b-code-instruct-128k-q5_0.gguf new file mode 100644 index 0000000..29dab35 --- /dev/null +++ b/granite-3b-code-instruct-128k-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68473944ae0883d32314e9f832b3d20b997959a0064b8b4d02e2b2db82d6adec +size 2400051648 diff --git a/granite-3b-code-instruct-128k-q5_1.gguf b/granite-3b-code-instruct-128k-q5_1.gguf new file mode 100644 index 0000000..4bfd959 --- /dev/null +++ b/granite-3b-code-instruct-128k-q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89cf375ce3210e83bf90fb2b8ab3a53ab4dbc0534ddc36c6d905da04e9c52185 +size 2617631168 diff --git a/granite-3b-code-instruct-128k-q5_k_m.gguf b/granite-3b-code-instruct-128k-q5_k_m.gguf new file mode 100644 index 0000000..71cec60 --- /dev/null +++ b/granite-3b-code-instruct-128k-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1601d243fb9a6e0623aba298aafd8f4daff399c7ce136878108492dd0990478 +size 2493358528 diff --git a/granite-3b-code-instruct-128k-q5_k_s.gguf b/granite-3b-code-instruct-128k-q5_k_s.gguf new file mode 100644 index 0000000..f0e694a --- /dev/null +++ b/granite-3b-code-instruct-128k-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1af895c229e2e91f2fd038bde002504481f986d7b142bdb09aec984367c517a +size 2458542528 diff --git a/granite-3b-code-instruct-128k-q6_k_m.gguf b/granite-3b-code-instruct-128k-q6_k_m.gguf new file mode 100644 index 0000000..97ed7fe --- /dev/null +++ b/granite-3b-code-instruct-128k-q6_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f75c8f16ccf3f353c0adf52ab68a679a4ce9f8ebcf99e8882a4dfa1061f6ef4e +size 2862408128 diff --git a/granite-3b-code-instruct-128k-q8_0.gguf b/granite-3b-code-instruct-128k-q8_0.gguf new file mode 100644 index 0000000..9d047f6 --- /dev/null +++ b/granite-3b-code-instruct-128k-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35970f87ce9238477a4dabf978a545fa62437d0b16369dcf71a1b4f5dc4e513 +size 3705528448 diff --git a/granite-3b-code-instruct-128k.imatrix b/granite-3b-code-instruct-128k.imatrix new file mode 100644 index 0000000..742a118 --- /dev/null +++ b/granite-3b-code-instruct-128k.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ce77f5ceb934c00bf8f31ea01b2b88e1d60d640dffd1e303f67b49195a84ad7 +size 3284268