This model was quantized by SanctumAI. To leave feedback, join our community in Discord.
Granite 3B Code Instruct GGUF
Model creator: ibm-granite
Original model: granite-3b-code-instruct
Model Summary:
Granite-3B-Code-Instruct is a 3B parameter model fine tuned from Granite-3B-Code-Base 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
- Paper: Granite Code Models: A Family of Open Foundation Models for Code Intelligence
- Release Date: May 6th, 2024
- License: Apache 2.0.
Prompt Template:
If you're using Sanctum app, simply use IBM Granite Code
model preset.
Prompt template:
System:
{system_prompt}
Question:
{prompt}
Answer:
Hardware Requirements Estimate
Name | Quant method | Size | Memory (RAM, vRAM) required (for full context of 32k tokens) |
---|---|---|---|
granite-3b-code-instruct.Q2_K.gguf | Q2_K | 1.34 GB | 4.68 GB |
granite-3b-code-instruct.Q3_K_S.gguf | Q3_K_S | 1.55 GB | ? |
granite-3b-code-instruct.Q3_K_M.gguf | Q3_K_M | 1.73 GB | ? |
granite-3b-code-instruct.Q3_K_L.gguf | Q3_K_L | 1.88 GB | ? |
granite-3b-code-instruct.Q4_0.gguf | Q4_0 | 2.00 GB | ? |
granite-3b-code-instruct.Q4_K_S.gguf | Q4_K_S | 2.01 GB | ? |
granite-3b-code-instruct.Q4_K_M.gguf | Q4_K_M | 2.13 GB | ? |
granite-3b-code-instruct.Q4_K.gguf | Q4_K | 2.13 GB | ? |
granite-3b-code-instruct.Q4_1.gguf | Q4_1 | 2.21 GB | ? |
granite-3b-code-instruct.Q5_0.gguf | Q5_0 | 2.42 GB | ? |
granite-3b-code-instruct.Q5_K_S.gguf | Q5_K_S | 2.42 GB | ? |
granite-3b-code-instruct.Q5_K_M.gguf | Q5_K_M | 2.49 GB | ? |
granite-3b-code-instruct.Q5_K.gguf | Q5_K | 2.49 GB | ? |
granite-3b-code-instruct.Q5_1.gguf | Q5_1 | 2.63 GB | ? |
granite-3b-code-instruct.Q6_K.gguf | Q6_K | 2.86 GB | ? |
granite-3b-code-instruct.Q8_0.gguf | Q8_0 | 3.71 GB | ? |
granite-3b-code-instruct.f16.gguf | f16 | 6.97 GB | 4.68 GB |
Disclaimer
Sanctum is not the creator, originator, or owner of any Model featured in the Models section of the Sanctum application. Each Model is created and provided by third parties. Sanctum does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Model listed there. You understand that supported Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Model is the sole responsibility of the person or entity who originated such Model. Sanctum may not monitor or control the Models supported and cannot, and does not, take responsibility for any such Model. Sanctum disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Models. Sanctum further disclaims any warranty that the Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Models, your downloading of any Model, or use of any other Model provided by or through Sanctum.
- Downloads last month
- 13,332
Model tree for SanctumAI/granite-3b-code-instruct-GGUF
Base model
ibm-granite/granite-3b-code-base-2kDatasets used to train SanctumAI/granite-3b-code-instruct-GGUF
Evaluation results
- pass@1 on HumanEvalSynthesis(Python)self-reported51.200
- pass@1 on HumanEvalSynthesis(JavaScript)self-reported43.900
- pass@1 on HumanEvalSynthesis(Java)self-reported41.500
- pass@1 on HumanEvalSynthesis(Go)self-reported31.700
- pass@1 on HumanEvalSynthesis(C++)self-reported40.200
- pass@1 on HumanEvalSynthesis(Rust)self-reported29.300
- pass@1 on HumanEvalExplain(Python)self-reported39.600
- pass@1 on HumanEvalExplain(JavaScript)self-reported26.800
- pass@1 on HumanEvalExplain(Java)self-reported39.000
- pass@1 on HumanEvalExplain(Go)self-reported14.000