pipeline_tag, base_model, inference, license, datasets, metrics, library_name, tags, model-index

pipeline_tag	base_model	inference	license	datasets	metrics	library_name	tags	model-index
text-generation	ibm-granite/granite-8b-code-base	false	apache-2.0	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	code_eval	transformers	code granite	name results granite-8b-code-instruct task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(Python) name type value veriefied pass@1 pass@1 57.9 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(JavaScript) name type value veriefied pass@1 pass@1 52.4 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(Java) name type value veriefied pass@1 pass@1 58.5 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(Go) name type value veriefied pass@1 pass@1 43.3 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(C++) name type value veriefied pass@1 pass@1 48.2 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalSynthesis(Rust) name type value veriefied pass@1 pass@1 37.2 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(Python) name type value veriefied pass@1 pass@1 53.0 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(JavaScript) name type value veriefied pass@1 pass@1 42.7 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(Java) name type value veriefied pass@1 pass@1 52.4 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(Go) name type value veriefied pass@1 pass@1 36.6 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(C++) name type value veriefied pass@1 pass@1 43.9 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalExplain(Rust) name type value veriefied pass@1 pass@1 16.5 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(Python) name type value veriefied pass@1 pass@1 39.6 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(JavaScript) name type value veriefied pass@1 pass@1 40.9 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(Java) name type value veriefied pass@1 pass@1 48.2 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(Go) name type value veriefied pass@1 pass@1 41.5 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(C++) name type value veriefied pass@1 pass@1 39.0 false task dataset metrics type text-generation type name bigcode/humanevalpack HumanEvalFix(Rust) name type value veriefied pass@1 pass@1 32.9 false

This model was quantized by SanctumAI. To leave feedback, join our community in Discord.

Granite 8B Code Instruct GGUF

Model creator: ibm-granite
Original model: granite-8b-code-instruct

Model Summary:

Granite-8B-Code-Instruct is a 8B parameter model fine tuned from Granite-8B-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
granite-8b-code-instruct.Q2_K.gguf	Q2_K	3.06 GB	7.47 GB
granite-8b-code-instruct.Q3_K_S.gguf	Q3_K_S	3.55 GB	?
granite-8b-code-instruct.Q3_K_M.gguf	Q3_K_M	3.94 GB	?
granite-8b-code-instruct.Q3_K_L.gguf	Q3_K_L	4.29 GB	?
granite-8b-code-instruct.Q4_0.gguf	Q4_0	4.59 GB	?
granite-8b-code-instruct.Q4_K_S.gguf	Q4_K_S	4.62 GB	?
granite-8b-code-instruct.Q4_K_M.gguf	Q4_K_M	4.88 GB	?
granite-8b-code-instruct.Q4_K.gguf	Q4_K	4.88 GB	?
granite-8b-code-instruct.Q4_1.gguf	Q4_1	5.08 GB	?
granite-8b-code-instruct.Q5_0.gguf	Q5_0	5.57 GB	?
granite-8b-code-instruct.Q5_K_S.gguf	Q5_K_S	5.57 GB	?
granite-8b-code-instruct.Q5_K_M.gguf	Q5_K_M	5.72 GB	?
granite-8b-code-instruct.Q5_K.gguf	Q5_K	5.72 GB	?
granite-8b-code-instruct.Q5_1.gguf	Q5_1	6.06 GB	?
granite-8b-code-instruct.Q6_K.gguf	Q6_K	6.62 GB	?
granite-8b-code-instruct.Q8_0.gguf	Q8_0	8.57 GB	?
granite-8b-code-instruct.f16.gguf	f16	16.12 GB	19.62 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.