SupraLabs/Supra-1.5-50M-instruct-exp-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: SupraLabs/Supra-1.5-50M-instruct-exp-gguf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 22:01:05 +08:00
commit 6bfd3b4908
27 changed files with 368 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

83
.gitattributes vendored Normal file
View File

@@ -0,0 +1,83 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.F16.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.BF16.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.F32.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q1_0.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
Supra-1.5-50M-Instruct-exp.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text

212
README.md Normal file
View File

@@ -0,0 +1,212 @@
---
license: apache-2.0
language:
- en
base_model: SupraLabs/Supra-1.5-50M-instruct-exp
pipeline_tag: text-generation
tags:
- supra
- chimera
- project-chimera
- gguf
- quantized
- instruct
- conversational
- QnA
- GPT
- CPU
- tiny
- SLM
- open
- open-source
- 50M
- llama
---
<h1 align="center">Supra-1.5 Instruct • Experimental Chat Tune — GGUF</h1>
![Supra-1.5 Instruct](https://cdn-uploads.huggingface.co/production/uploads/68a5d0966d33a07f8aad2e51/GUYqhtlWoCAUnRLR1zEOX.png)
GGUF quantizations of [SupraLabs/Supra-1.5-50M-instruct-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp), an experimental 50M-parameter instruction-tuned model by [SupraLabs](https://huggingface.co/SupraLabs), part of **Project Chimera**.
Run it entirely on CPU, low-VRAM GPUs, or embedded hardware. No cloud required.
> **Note:** This is an experimental model. Do not use in production.
---
## 📦 Available Quantizations
| Bits | Quantization | Size |
|:--|:--|:--|
| 1-bit | `Q1_0` | 19.6 MB |
| 1-bit | `TQ1_0` | 25.1 MB |
| 2-bit | `Q2_K` | 28.8 MB |
| 2-bit | `TQ2_0` | 26.4 MB |
| 3-bit | `IQ3_S` | 31 MB |
| 3-bit | `Q3_K_S` | 31 MB |
| 3-bit | `IQ3_M` | 31.7 MB |
| 3-bit | `Q3_K_M` | 32.7 MB |
| 3-bit | `Q3_K_L` | 33.8 MB |
| 4-bit | `IQ4_XS` | 33.8 MB |
| 4-bit | `Q4_K_S` | 35.7 MB |
| 4-bit | `IQ4_NL` | 34.7 MB |
| 4-bit | `Q4_0` | 34.5 MB |
| 4-bit | `Q4_1` | 36.8 MB |
| 4-bit | `Q4_K_M` | 37.4 MB |
| 5-bit | `Q5_K_S` | 39.5 MB |
| 5-bit | `Q5_0` | 39 MB |
| 5-bit | `Q5_1` | 41.2 MB |
| 5-bit | `Q5_K_M` | 41 MB |
| 6-bit | `Q6_K` | 45.8 MB |
| 8-bit | `Q8_0` | 56.2 MB |
| 16-bit | `BF16` | 105 MB |
| 16-bit | `F16` | 105 MB |
| 32-bit | `F32` | 208 MB |
> **`Q4_K_M`** — Usable, not recommended unless device is compute-constrained.
> **`Q8_0`** — Perfect size/performance!.
> **`Q2_K`** — ultra-constrained devices (not reccomended!).
---
## 🚀 Quick Start
### llama.cpp
```bash
# Download
huggingface-cli download SupraLabs/Supra-1.5-50M-instruct-exp-gguf \
--include "*.Q4_K_M.gguf" \
--local-dir ./
# Run
./llama-cli \
-m supra-1.5-50m-instruct-exp-Q4_K_M.gguf \
-p "### Instruction:\nWhat is machine learning?\n\n### Response:\n" \
-n 256 \
--temp 0.7 \
--repeat-penalty 1.15
```
### Ollama
```bash
ollama run hf.co/SupraLabs/Supra-1.5-50M-instruct-exp-gguf:Q4_K_M
```
### Python (llama-cpp-python)
```python
from llama_cpp import Llama
llm = Llama.from_pretrained(
repo_id="SupraLabs/Supra-1.5-50M-instruct-exp-gguf",
filename="*Q4_K_M.gguf",
n_ctx=1024,
verbose=False,
)
def chat(instruction: str, input_text: str = "") -> str:
if input_text.strip():
prompt = (
"Below is an instruction that describes a task, paired with an input "
"that provides further context. Write a response that appropriately "
"completes the request.\n\n"
f"### Instruction:\n{instruction}\n\n"
f"### Input:\n{input_text}\n\n"
"### Response:\n"
)
else:
prompt = (
"Below is an instruction that describes a task. Write a response that "
"appropriately completes the request.\n\n"
f"### Instruction:\n{instruction}\n\n"
"### Response:\n"
)
output = llm(prompt, max_tokens=256, temperature=0.7, top_k=50, top_p=0.9, repeat_penalty=1.15)
return output["choices"][0]["text"].strip()
print(chat("Explain what artificial intelligence is."))
```
---
## 💬 Prompt Format
This model uses the **Alpaca Chat Format**:
```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response:
```
With optional input:
```
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Input:
{input}
### Response:
```
---
## 🏆 Benchmarks
Supra-1.5-50M-instruct-exp achieves superior performance within the 50M-parameter class, with a consistent **BLiMP score of 67.4**.
Key findings from evaluation:
- **Scientific/factual tasks** perform best under raw inference (no normalization)
- **Math and logical reasoning** benefit from normalized inference
- **Top syntactic categories**: structural dependency tracking, complex clausal configurations, and subtle syntactic error detection — performing at near-flawless precision
- **Hardest categories**: advanced binding phenomena and morphological agreement edge cases, reflecting known limits of 50M-class architectures
> For full benchmark charts and BLiMP probe analysis, see the [base model card](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp).
---
## 🧠 Model Architecture
| Property | Value |
|:--|:--|
| Architecture | Llama (decoder-only) |
| Parameters | ~50M |
| Vocabulary | 32,000 (custom BPE) |
| Context length | 5,120 tokens |
| Hidden size | 512 |
| Layers | 12 |
| Attention heads | 8 (GQA: 4 KV heads) |
| Base model | SupraLabs/Supra-1.5-50M-Base-exp |
| License | Apache 2.0 |
---
## 🔗 Related Models
| Model | Description |
|:--|:--|
| [Supra-1.5-50M-Base-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-Base-exp) | Pretrained base (v1.5) |
| [Supra-1.5-50M-instruct-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp) | fp weights |
| [Supra-50M-Base](https://huggingface.co/SupraLabs/Supra-50M-Base) | v1.0 pretrained base |
| [Supra-50M-Instruct](https://huggingface.co/SupraLabs/Supra-50M-Instruct) | v1.0 instruct model |
| [Supra-50M-Reasoning](https://huggingface.co/SupraLabs/Supra-50M-Reasoning) | Chain-of-thought reasoning variant |
---
## 📄 License
Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
---
*© SupraLabs 2026 — Project Chimera*

3
Supra-1.5-50M-Instruct-exp.BF16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8bb981ec71b8c356d9f2388380501218388124d6558aa3869549c6593768fdb8
size 104740320

3
Supra-1.5-50M-Instruct-exp.F16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c676d3e4591bf08dcfc5876daee87488808e6b6339d5e74a495b6a5eac75dd7f
size 104740320

3
Supra-1.5-50M-Instruct-exp.F32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c2031d239bc018115e365ce92b9d8546ce946cc6e8b11bf1433954f4566877a
size 208287200

3
Supra-1.5-50M-Instruct-exp.IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7244eaa3889a51c7ec51ca793bb7e36b24a64cc5da674ea99d7235c056845ae
size 31705568

3
Supra-1.5-50M-Instruct-exp.IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e19d1da3464c5f7cd01b57ddcfb41946dc45f268c02cda8fbe919918438eecb5
size 30988768

3
Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:02f3b5d6f423b1e7e8891ec3bf6288d74d31c587cb0dc979ddf4d9a6d0e35bf7
size 34675168

3
Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee350e7fa1949be217d5fffc7aa3cb148079f97d01263a40acfbd0ca0fb17335
size 33839584

3
Supra-1.5-50M-Instruct-exp.Q1_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad63e1d1404b8ce85c443cb0935ae55ac46902a21e610bcdcca946a5f769f63c
size 19610080

3
Supra-1.5-50M-Instruct-exp.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25670601e6c28ee307448e6de1cfb3bda7e9760bb21df8a4aca395ad023a08d7
size 28752352

3
Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a43ba5ea76cb8b82ddff15de419a8c744572b43322dc3ea4c7305332e16d32ef
size 33827296

3
Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:eed188d2bacb45ec44f3cc5365d83b522ed234786b8f2584c2e54f02104222d2
size 32729568

3
Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ca4b7ddb4fc943d321bb5f3bff439b97c21ea14344d4ae736d2300d0077afd3
size 30988768

3
Supra-1.5-50M-Instruct-exp.Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d81dc1cd6f6f3f1680451d055f9fd758b18da922b69d6111205e43a23ceb0729
size 34540000

3
Supra-1.5-50M-Instruct-exp.Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be920d0b74686aa16ee6bef8982afa68b9f4168d60ccca585244864e924a098b
size 36751840

3
Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e839cb0e618a52acd5d3adec95f4a6de893b3ab00893826f55cf54c6bd6250f5
size 37446112

3
Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d581095acdaf14168dde1d4bb9308d239389343f06d8aa095cdf1381a27c6724
size 35731936

3
Supra-1.5-50M-Instruct-exp.Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8cecd81b1dd43b991bbf1c71881c85aed1dc6faa25423e94cf06fbc9266bfd5b
size 38963680

3
Supra-1.5-50M-Instruct-exp.Q5_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61a79ca5932a7e7a0dea279d4f4ecd5a2ef77b05c5158c3a4398e468888381f6
size 41175520

3
Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05c51010bc5f0955c7c9a9206684e563be1b9ceab3b282ed9698fd85f77a6c23
size 40960480

3
Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:987d8ef97eba532624324d34aca8d9849b3c6bf758ed8eeee3f529f408d62a81
size 39504352

3
Supra-1.5-50M-Instruct-exp.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:897306f0539dd5a0aea53682a92280c47a5ac155a3cae3c5014b25eef7bad082
size 45758944

3
Supra-1.5-50M-Instruct-exp.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6c943cd868d4ae3e44731ca03661f381816a2f9d39586b73ab21a2d1f2f61b96
size 56202720

3
Supra-1.5-50M-Instruct-exp.TQ1_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:50035f3178ec36efdf21a1b8e72857f07ef7dc7d30d4f78e2f5196b9dd0e412d
size 25139680

3
Supra-1.5-50M-Instruct-exp.TQ2_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5ad0eb6108e21a7507be7921c12d68afac0cdbc0008eb08570b77e76d68a84f3
size 26393056

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}