70 lines
2.0 KiB
Markdown
70 lines
2.0 KiB
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
base_model:
|
||
|
|
- artificialguybr/LLAMA-3.2-1B-OpenHermes2.5
|
||
|
|
- dphn/Dolphin3.0-Llama3.2-1B
|
||
|
|
- meta-llama/Llama-3.2-1B-Instruct
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- llama
|
||
|
|
- mergekit
|
||
|
|
- merge
|
||
|
|
- slerp
|
||
|
|
- text-generation
|
||
|
|
- code
|
||
|
|
- instruct
|
||
|
|
datasets:
|
||
|
|
- OpenCoder-LLM/opc-sft-stage1
|
||
|
|
- OpenCoder-LLM/opc-sft-stage2
|
||
|
|
- microsoft/orca-agentinstruct-1M-v1
|
||
|
|
- microsoft/orca-math-word-problems-200k
|
||
|
|
- NousResearch/hermes-function-calling-v1
|
||
|
|
- AI-MO/NuminaMath-CoT
|
||
|
|
- AI-MO/NuminaMath-TIR
|
||
|
|
- allenai/tulu-3-sft-mixture
|
||
|
|
- HuggingFaceTB/smoltalk
|
||
|
|
- m-a-p/CodeFeedback-Filtered-Instruction
|
||
|
|
- m-a-p/Code-Feedback
|
||
|
|
- teknium/OpenHermes-2.5
|
||
|
|
---
|
||
|
|
|
||
|
|
# Llama-3.2-HermesDolphin-Coder-1B
|
||
|
|
|
||
|
|
Llama-3.2-HermesDolphin-Coder-1B is a compact merged language model designed for general instruction following, coding assistance, and lightweight conversational use. It combines Hermes-style instruction tuning and Dolphin-style helpfulness into a small Llama 3.2 class model intended for experimentation, local workflows, and developer-oriented prompting.
|
||
|
|
|
||
|
|
This repository appears to be a **merge model** created with **mergekit** using the **SLERP** merge method.
|
||
|
|
|
||
|
|
## Model Summary
|
||
|
|
|
||
|
|
- **Model type:** Causal language model
|
||
|
|
- **Architecture:** LlamaForCausalLM
|
||
|
|
- **Primary use:** Text generation, instruction following, code-oriented prompting
|
||
|
|
- **Library:** Transformers
|
||
|
|
- **Merge method:** SLERP
|
||
|
|
- **Format:** Safetensors
|
||
|
|
|
||
|
|
## Base Models
|
||
|
|
|
||
|
|
This merged model is based on:
|
||
|
|
|
||
|
|
- `artificialguybr/LLAMA-3.2-1B-OpenHermes2.5`
|
||
|
|
- `dphn/Dolphin3.0-Llama3.2-1B`
|
||
|
|
- `meta-llama/Llama-3.2-1B-Instruct`
|
||
|
|
|
||
|
|
## Merge Details
|
||
|
|
|
||
|
|
According to the repository metadata/configuration, the merge was produced with `mergekit` using a SLERP setup with a midpoint interpolation parameter.
|
||
|
|
|
||
|
|
### Merge configuration
|
||
|
|
|
||
|
|
```yaml
|
||
|
|
merge_method: slerp
|
||
|
|
base_model: artificialguybr/LLAMA-3.2-1B-OpenHermes2.5
|
||
|
|
models:
|
||
|
|
- model: dphn/Dolphin3.0-Llama3.2-1B
|
||
|
|
parameters:
|
||
|
|
weight: 1.0
|
||
|
|
dtype: float32
|
||
|
|
parameters:
|
||
|
|
t: 0.5
|