初始化项目，由ModelHub XC社区提供模型
Model: DuoNeural/OLMo-2-7B-Instruct-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
46
.gitattributes
vendored
Normal file
46
.gitattributes
vendored
Normal file
@@ -0,0 +1,46 @@
|
|||||||
|
*.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
|
||||||
|
OLMo-2-7B-Instruct-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
OLMo-2-7B-Instruct-fp16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||||
|
imatrix.dat filter=lfs diff=lfs merge=lfs -text
|
||||||
3
OLMo-2-7B-Instruct-IQ1_S.gguf
Normal file
3
OLMo-2-7B-Instruct-IQ1_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e13ee4b1e6f6ee24e77578431178fab04eaefe25462adcbc1b7c73f1d53debab
|
||||||
|
size 1816796608
|
||||||
3
OLMo-2-7B-Instruct-IQ2_M.gguf
Normal file
3
OLMo-2-7B-Instruct-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:009e1917d0852aafce1fa125a2db49b98de117740f01d907f5852008505a75c2
|
||||||
|
size 2676399552
|
||||||
3
OLMo-2-7B-Instruct-IQ3_XXS.gguf
Normal file
3
OLMo-2-7B-Instruct-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b7269a1cec43a49b06261f4ee591e059c30e51bba2416840d40bd946955998ef
|
||||||
|
size 2902040000
|
||||||
3
OLMo-2-7B-Instruct-IQ4_XS.gguf
Normal file
3
OLMo-2-7B-Instruct-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a654a0a18aec2c8b434f95bdce6a3470f7fdb228af681483429bd9d857c55d12
|
||||||
|
size 4001603008
|
||||||
3
OLMo-2-7B-Instruct-Q3_K_M.gguf
Normal file
3
OLMo-2-7B-Instruct-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:c3110825e6f7f1f12ae6d2b24487a3e638c1ac8f2ae5fe73873ba0b578ceaf2f
|
||||||
|
size 3651837120
|
||||||
3
OLMo-2-7B-Instruct-Q4_K_M.gguf
Normal file
3
OLMo-2-7B-Instruct-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:729a9e590c6d7d2cba0e1a39d8563c60d501ce22f10bc14e83cb4d1736a07f19
|
||||||
|
size 4472020160
|
||||||
3
OLMo-2-7B-Instruct-Q5_K_M.gguf
Normal file
3
OLMo-2-7B-Instruct-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:34f1293db00f44974b0ca971bfb4a53c99ac27b12c88198d7aebbcba9a743f9f
|
||||||
|
size 5209169088
|
||||||
3
OLMo-2-7B-Instruct-Q6_K.gguf
Normal file
3
OLMo-2-7B-Instruct-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:aaa061163db6a3716fd64b2c3d415ceb1b0b6ad0e3afbb703c491ff3f6b56243
|
||||||
|
size 5992389824
|
||||||
3
OLMo-2-7B-Instruct-Q8_0.gguf
Normal file
3
OLMo-2-7B-Instruct-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:16c79acfade32ab3d0a3f945ea257ca82af8d37278f9d53277c9fef299af388e
|
||||||
|
size 7759895744
|
||||||
3
OLMo-2-7B-Instruct-fp16.gguf
Normal file
3
OLMo-2-7B-Instruct-fp16.gguf
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e7120b3279c7f15157c2c7321980569782df562b757ff9ba06c9777a65a00892
|
||||||
|
size 14601854144
|
||||||
88
README.md
Normal file
88
README.md
Normal file
@@ -0,0 +1,88 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model: allenai/OLMo-2-1124-7B-Instruct
|
||||||
|
tags:
|
||||||
|
- gguf
|
||||||
|
- quantized
|
||||||
|
- olmo
|
||||||
|
- allenai
|
||||||
|
- text-generation
|
||||||
|
- fully-open
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
pipeline_tag: text-generation
|
||||||
|
---
|
||||||
|
|
||||||
|
# OLMo-2-7B-Instruct — GGUF Quants
|
||||||
|
|
||||||
|
Quantized GGUF versions of [allenai/OLMo-2-1124-7B-Instruct](https://huggingface.co/allenai/OLMo-2-1124-7B-Instruct) — the Allen Institute for AI's fully open 7B language model. OLMo-2 is released under Apache 2.0 with **full training data, code, intermediate checkpoints, and evaluation data** all publicly available — the most transparent large language model at this scale.
|
||||||
|
|
||||||
|
## Available Files
|
||||||
|
|
||||||
|
| File | Quant | Size | Use Case |
|
||||||
|
|------|-------|------|----------|
|
||||||
|
| `OLMo-2-7B-Instruct-Q8_0.gguf` | Q8_0 | ~7.4GB | Maximum quality |
|
||||||
|
| `OLMo-2-7B-Instruct-Q6_K.gguf` | Q6_K | ~5.7GB | Near-lossless |
|
||||||
|
| `OLMo-2-7B-Instruct-Q5_K_M.gguf` | Q5_K_M | ~5.0GB | High quality |
|
||||||
|
| `OLMo-2-7B-Instruct-Q4_K_M.gguf` | Q4_K_M | ~4.2GB | **Recommended default** |
|
||||||
|
| `OLMo-2-7B-Instruct-Q3_K_M.gguf` | Q3_K_M | ~3.5GB | Low VRAM |
|
||||||
|
| `OLMo-2-7B-Instruct-IQ4_XS.gguf` | IQ4_XS | ~3.8GB | Imatrix 4-bit |
|
||||||
|
| `OLMo-2-7B-Instruct-IQ3_XXS.gguf` | IQ3_XXS | ~2.7GB | Imatrix 3-bit |
|
||||||
|
| `OLMo-2-7B-Instruct-IQ2_M.gguf` | IQ2_M | ~2.4GB | Imatrix 2-bit |
|
||||||
|
| `OLMo-2-7B-Instruct-IQ1_S.gguf` | IQ1_S | ~1.6GB | Extreme compression |
|
||||||
|
| `OLMo-2-7B-Instruct-fp16.gguf` | FP16 | ~14.0GB | Full precision |
|
||||||
|
| `imatrix.dat` | — | — | Importance matrix |
|
||||||
|
|
||||||
|
## Usage
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# llama.cpp
|
||||||
|
./llama-cli -m OLMo-2-7B-Instruct-Q4_K_M.gguf \
|
||||||
|
--ctx-size 4096 -n 512 \
|
||||||
|
-p "<|endoftext|><|user|>\nHello!<|assistant|>\n"
|
||||||
|
|
||||||
|
# Ollama
|
||||||
|
ollama run hf.co/DuoNeural/OLMo-2-7B-Instruct-GGUF:Q4_K_M
|
||||||
|
```
|
||||||
|
|
||||||
|
## About OLMo-2-7B
|
||||||
|
|
||||||
|
- **Parameters**: 7B
|
||||||
|
- **Context**: 4096 tokens
|
||||||
|
- **Architecture**: Modified decoder-only transformer (RoPE, SwiGLU, QK-norm)
|
||||||
|
- **Training Data**: Dolmino Mix 1124 — fully open dataset
|
||||||
|
- **License**: Apache 2.0 (commercial use OK)
|
||||||
|
- **Unique value**: All artifacts open — weights, data, code, evals, checkpoints
|
||||||
|
|
||||||
|
OLMo-2 is the gold standard for research reproducibility in the 7B class. If you need a model where you can trace every decision back to first principles, this is it.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*Quantized by DuoNeural using llama.cpp on RTX 5090.*
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## DuoNeural
|
||||||
|
|
||||||
|
**DuoNeural** is an open AI research lab — human + AI in collaboration.
|
||||||
|
|
||||||
|
| Platform | Link |
|
||||||
|
|----------|------|
|
||||||
|
| HuggingFace | [huggingface.co/DuoNeural](https://huggingface.co/DuoNeural) |
|
||||||
|
| Website | [duoneural.com](https://duoneural.com) |
|
||||||
|
| GitHub | [github.com/DuoNeural](https://github.com/DuoNeural) |
|
||||||
|
| X / Twitter | [@DuoNeural](https://x.com/DuoNeural) |
|
||||||
|
| Email | duoneural@proton.me |
|
||||||
|
| Newsletter | [duoneural.beehiiv.com](https://duoneural.beehiiv.com) |
|
||||||
|
| Support | [buymeacoffee.com/duoneural](https://buymeacoffee.com/duoneural) |
|
||||||
|
|
||||||
|
### DuoNeural Research Publications
|
||||||
|
|
||||||
|
| Title | DOI |
|
||||||
|
|-------|-----|
|
||||||
|
| [Nano-CTM: Ternary Continuous Thought Machines with Thought-Space Self-Prediction for Efficient Iterative Reasoning](https://doi.org/10.5281/zenodo.19775622) | [10.5281/zenodo.19775622](https://doi.org/10.5281/zenodo.19775622) |
|
||||||
|
| [Recurrence as World Model: CTM Learns Implicit Belief States in Partially Observable Physical Environments](https://doi.org/10.5281/zenodo.19810620) | [10.5281/zenodo.19810620](https://doi.org/10.5281/zenodo.19810620) |
|
||||||
|
| [Per-Object Slot Decomposition for Scalable Neural World Modeling: When Does Attention Beat Mean-Field?](https://doi.org/10.5281/zenodo.19846804) | [10.5281/zenodo.19846804](https://doi.org/10.5281/zenodo.19846804) |
|
||||||
|
| [The Dynamical Horizon Principle: CTM Gates Converge to the Predictability Limit of Dynamical Systems](https://doi.org/10.5281/zenodo.19952612) | [10.5281/zenodo.19952612](https://doi.org/10.5281/zenodo.19952612) |
|
||||||
|
|
||||||
|
*Open access, CC BY 4.0. Authored by Archon, Jesse Caldwell, Aura — DuoNeural.*
|
||||||
3
imatrix.dat
Normal file
3
imatrix.dat
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:294792382dd9e0392ab9b69a4c8761ab3ed3d7c2fe4ebaa5296c4949c28e3302
|
||||||
|
size 4589216
|
||||||
Reference in New Issue
Block a user