Mungert/granite-8b-code-instruct-4k-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Mungert/granite-8b-code-instruct-4k-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-17 02:32:17 +08:00
commit 95a7f6e484
30 changed files with 529 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

77
.gitattributes vendored Normal file
View File

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

368
README.md Normal file
View File

@@ -0,0 +1,368 @@
---
pipeline_tag: text-generation
base_model: ibm-granite/granite-8b-code-base-4k
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
metrics:
- code_eval
library_name: transformers
tags:
- code
- granite
model-index:
- name: granite-8b-code-instruct-4k
results:
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalSynthesis(Python)
metrics:
- name: pass@1
type: pass@1
value: 57.9
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: 58.5
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalSynthesis(Go)
metrics:
- name: pass@1
type: pass@1
value: 43.3
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalSynthesis(C++)
metrics:
- name: pass@1
type: pass@1
value: 48.2
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalSynthesis(Rust)
metrics:
- name: pass@1
type: pass@1
value: 37.2
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(Python)
metrics:
- name: pass@1
type: pass@1
value: 53.0
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(JavaScript)
metrics:
- name: pass@1
type: pass@1
value: 42.7
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(Java)
metrics:
- name: pass@1
type: pass@1
value: 52.4
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(Go)
metrics:
- name: pass@1
type: pass@1
value: 36.6
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(C++)
metrics:
- name: pass@1
type: pass@1
value: 43.9
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalExplain(Rust)
metrics:
- name: pass@1
type: pass@1
value: 16.5
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(Python)
metrics:
- name: pass@1
type: pass@1
value: 39.6
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(JavaScript)
metrics:
- name: pass@1
type: pass@1
value: 40.9
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(Java)
metrics:
- name: pass@1
type: pass@1
value: 48.2
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(Go)
metrics:
- name: pass@1
type: pass@1
value: 41.5
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(C++)
metrics:
- name: pass@1
type: pass@1
value: 39.0
veriefied: false
- task:
type: text-generation
dataset:
type: bigcode/humanevalpack
name: HumanEvalFix(Rust)
metrics:
- name: pass@1
type: pass@1
value: 32.9
veriefied: false
---
# <span style="color: #7FFF7F;">granite-8b-code-instruct-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 [`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-8B-Code-Instruct-4K
## Model Summary
**Granite-8B-Code-Instruct-4K** is a 8B parameter model fine tuned from *Granite-8B-Code-Base-4K* on a combination of **permissively licensed** instruction data to enhance instruction following capabilities including logical reasoning and problem-solving skills.
- **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
The model is designed to respond to coding related instructions and can be used to build coding assistants.
<!-- TO DO: Check starcoder2 instruct code example that includes the template https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 -->
### Generation
This is a simple example of how to use **Granite-8B-Code-Instruct-4K** model.
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # or "cpu"
model_path = "ibm-granite/granite-8b-code-instruct-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
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)
```
<!-- TO DO: Check this part -->
## Training Data
Granite Code Instruct models are trained on the following types of data.
* Code Commits Datasets: we sourced code commits data from the [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) dataset, a filtered version of the full CommitPack dataset. From CommitPackFT dataset, we only consider data for 92 programming languages. Our inclusion criteria boils down to selecting programming languages common across CommitPackFT and the 116 languages that we considered to pretrain the code-base model (*Granite-8B-Code-Base*).
* Math Datasets: We consider two high-quality math datasets, [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct) and [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA). Due to license issues, we filtered out GSM8K-RFT and Camel-Math from MathInstruct dataset.
* Code Instruction Datasets: We use [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) and a small collection of synthetic API calling datasets.
* Language Instruction Datasets: We include high-quality datasets such as [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) and an open license-filtered version of [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). We also include a collection of hardcoded prompts to ensure our model generates correct outputs given inquiries about its name or developers.
## 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-8B-Code-Base-4K](https://huggingface.co/ibm-granite/granite-8b-code-base-4k)* model card.
<!--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! 😊

3
granite-8b-code-instruct-4k-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0f91f3aef42f19ee082ae34b27b78c4529be256632347de5725f6ebf955650c
size 16115271232

3
granite-8b-code-instruct-4k-bf16_q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aea6448faaff0ebe2f022b688cd8fe3dbd53d7abe262c263c7b31c5cfb468ca6
size 11443865152

3
granite-8b-code-instruct-4k-f16_q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6e9429897d7783daa427ed9b9b5aa61db14015db6341560af3367b474df534c
size 11443865152

3
granite-8b-code-instruct-4k-iq2_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1b4c89c90e3de2fd39b6eb19261ff3f16b86f6251bba3bdf5c5298fb9f8f3866
size 2904262560

3
granite-8b-code-instruct-4k-iq2_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85cf6584714a8fc1ef3dda0e168434905168ac3ec7e8352a323cc6dd8b2606cb
size 2759034784

3
granite-8b-code-instruct-4k-iq2_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:598606b346a7736a67aefc05cc09e0801d7510c79e23d8721b98486cd336317c
size 2669250464

3
granite-8b-code-instruct-4k-iq2_xxs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4bdb53accd9b4d01c43d2c1e4ebc342731e320a27e535d76397d7c2563826cd9
size 2441316256

3
granite-8b-code-instruct-4k-iq3_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f2f2eff4898216a7681c3afe968b70e4c1127d0b95ab5a91ec53bdc2c40c56c4
size 3780741024

3
granite-8b-code-instruct-4k-iq3_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcc29ed16a5b89353a2c4ee8ae797d4c263ac8126387da692dcfc0f947a21d16
size 3780741024

3
granite-8b-code-instruct-4k-iq3_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:393eb980e49f6864159b1fdccb3cbba99a27a06dfd1e7cdbfd4329b88006bdad
size 3388442528

3
granite-8b-code-instruct-4k-iq3_xxs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1eabc1c33d4ea3098101a308d7393456f5578223da8060a47c822734d0aee343
size 3291711392

3
granite-8b-code-instruct-4k-iq4_nl.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c31316d4b033d4990c90c85fcf320faa2ee1362ab4204411e6c6823b71101994
size 4609771424

3
granite-8b-code-instruct-4k-iq4_xs.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bdc232748dc1f152e06876965fb1f2a89c84f2bc3202d26bfc27658d3eaee0dc
size 4369123232

3
granite-8b-code-instruct-4k-q2_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75d8bea79e99902465803a29365c1a702d87fafc9786a1da3091b6b22095a052
size 3019999136

3
granite-8b-code-instruct-4k-q2_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b97d5c1aa587ad82b9f4c48abe15baf45c93e713af144dc0d4c8e4445706d2cb
size 2993260448

3
granite-8b-code-instruct-4k-q3_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf7f69fa511dedda19e47161d0619b9f942791e13d974d0031efbb9f491158bf
size 3914434464

3
granite-8b-code-instruct-4k-q3_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6b2c6e7109aaf613a568ddefc627cfaee4dc7a4416eba175955e81fdf20ffd4
size 3887695776

3
granite-8b-code-instruct-4k-q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1abf73a89b0c3d2c0d97d68a2b3273e2cd8d9a9d50640140339110c71a2ee2c1
size 4538992544

3
granite-8b-code-instruct-4k-q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:70d1da2505f52e2cbcc067306325f3e9b44808e73c3d7b64226de7b4c8214356
size 5042309024

3
granite-8b-code-instruct-4k-q4_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:945e09c7372f667dd782bd71ecd4cebb7649ffdb325c46dcec2ac002caa5ab65
size 4832790432

3
granite-8b-code-instruct-4k-q4_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:411b8d8a8446f9d3c7c0d16798fa30cc350cc048d53485cc5b783c55c00e7aae
size 4670588832

3
granite-8b-code-instruct-4k-q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0f9432c6727f39c59cd4eb96148018bbdd8b5db75b22e4847dd045ab2399cc3
size 5545625504

3
granite-8b-code-instruct-4k-q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a9e548226aad5926024641210241f4abe75f4e0a990ea66ec0777eb6fba1030
size 6048941984

3
granite-8b-code-instruct-4k-q5_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d78204c87424b30b37593ae6bf3d031420a535422413faacfe5d707da3cf4e60
size 5740595104

3
granite-8b-code-instruct-4k-q5_k_s.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e84991e51471d1b6022eb44dfd9962cddde1a0751676ad8a7744125be80ce6b
size 5657036704

3
granite-8b-code-instruct-4k-q6_k_m.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d6318d6b66eadbbd2442ce7ca41fd2e48e3b095aa52164b5eb9960795733d7b
size 6615173024

3
granite-8b-code-instruct-4k-q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:927c2ceced7cf0b227f4f8c8feab2da039d96cb63533ad8cc76d42e9bc2c7871
size 8565524032

3
granite-8b-code-instruct-4k.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:db16e1675f5c2d36640c3408c655277a15b66a6c2f684d87b9a2d54252fed09a
size 5611728