初始化项目，由ModelHub XC社区提供模型

Model: SupraLabs/supra-50m-instruct-gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,93 @@
+*.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-50M-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq1_m.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-f32.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-iq1_s.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq2_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-mxfp4_moe.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-q2_k.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q2_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+
+Supra-50M-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+Supra-50M-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,236 @@
+---
+license: apache-2.0
+datasets:
+- HuggingFaceFW/fineweb-edu
+- yahma/alpaca-cleaned
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- supra
+- chimera
+- 50m
+- llama
+- small
+- open
+- open-source
+- cpu
+- tiny
+- slm
+base_model:
+- SupraLabs/Supra-50M-Base
+new_version: SupraLabs/Supra-1.5-50M-Instruct-exp
+---
+
+# 🦅 Supra-50M Instruct-GGUF
+
+**Supra-50M Instruct** is a compact 50M-parameter chat/instruct causal language model built by SupraLabs, trained from scratch using a Llama-style architecture on 20 billion tokens of high-quality educational web text. Despite being significantly smaller than comparable open models, it achieves competitive or superior results on several key benchmarks. It's our first SupraLabs Scaling Up Plan model.
+
+---
+
+## 📚 Training Data
+
+For the SFT (supervised finetuning) we used the full Alpaca-Cleaned dataset for 4 epochs. See the full SFT-code in sft.py
+
+---
+
+## Benchmarks
+
+
+| Task | Metric | Value |
+| :--- | :--- | :---: |
+| arc_easy | acc,none | 0.4659 |
+| arc_easy | acc_stderr,none | 0.0102 |
+| arc_easy | acc_norm,none | 0.4423 |
+| arc_easy | acc_norm_stderr,none | 0.0102 |
+| arc_challenge | acc,none | 0.2287 |
+| arc_challenge | acc_stderr,none | 0.0123 |
+| arc_challenge | acc_norm,none | 0.2756 |
+| arc_challenge | acc_norm_stderr,none | 0.0131 |
+| hellaswag | acc,none | 0.2794 |
+| hellaswag | acc_stderr,none | 0.0045 |
+| hellaswag | acc_norm,none | 0.2922 |
+| hellaswag | acc_norm_stderr,none | 0.0045 |
+| winogrande | acc,none | 0.5154 |
+| winogrande | acc_stderr,none | 0.0140 |
+| piqa | acc,none | 0.5558 |
+| piqa | acc_stderr,none | 0.0114 |
+| piqa | acc_norm,none | 0.5952 |
+| piqa | acc_norm_stderr,none | 0.0115 |
+| openbookqa | acc,none | 0.1580 |
+| openbookqa | acc_stderr,none | 0.0163 |
+| openbookqa | acc_norm,none | 0.2860 |
+| openbookqa | acc_norm_stderr,none | 0.0202 |
+| boolq | acc,none | 0.4205 |
+| boolq | acc_stderr,none | 0.0086 |
+
+
+---
+
+## ⚙️ Pretraining details
+For more details, the full code, configs and weights, please refer to [https://huggingface.co/SupraLabs/Supra-50M-Base](https://huggingface.co/SupraLabs/Supra-50M-Base)
+
+---
+
+## 🚀 Inference
+
+```python
+import os
+import warnings
+import time
+
+os.environ["TF_CPP_MIN_LOG_LEVEL"] = "3"
+os.environ["CUDA_VISIBLE_DEVICES"] = "0"
+warnings.filterwarnings("ignore", category=UserWarning, module="transformers")
+
+import torch
+from transformers import pipeline, AutoTokenizer, logging
+
+logging.set_verbosity_error()
+
+# ── Global variables ──────────────────────────────────────────────────────────
+
+end = time.time()
+start = time.time()
+tokens = []
+
+
+# ── Config ────────────────────────────────────────────────────────────────────
+
+MODEL_ID = "SupraLabs/Supra-50M-Instruct"  
+MAX_NEW_TOKENS = 512
+
+# ── Load pipeline directly from HF ────────────────────────────────────────────
+
+print(f"[*] Loading SFT model and tokenizer from HF Hub ({MODEL_ID})...")
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, clean_up_tokenization_spaces=False)
+
+pipe = pipeline(
+    "text-generation",
+    model=MODEL_ID,
+    tokenizer=tokenizer,
+    device_map="auto",
+    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32
+)
+
+print(f"[+] Pipeline ready — Model loaded using {pipe.model.device}")
+
+# ── Prompt template (must match sft.py exactly) ───────────────────────────────
+
+def build_prompt(instruction: str, input_text: str = "") -> str:
+    if input_text.strip():
+        return (
+            "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"
+        )
+    return (
+        "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"
+    )
+
+# ── Generate ──────────────────────────────────────────────────────────────────
+
+def generate(instruction: str, input_text: str = "", max_new_tokens: int = MAX_NEW_TOKENS) -> str:
+    prompt = build_prompt(instruction, input_text)
+    start = time.time()
+    result = pipe(
+        prompt,
+        max_new_tokens=max_new_tokens,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.9,
+        repetition_penalty=1.15,
+        pad_token_id=pipe.tokenizer.pad_token_id,
+        eos_token_id=pipe.tokenizer.eos_token_id,
+        return_full_text=False,
+        generation_config=None
+    )
+    end = time.time()
+    
+    generated_text = result[0]["generated_text"]
+    tokens = pipe.tokenizer(generated_text)["input_ids"]
+    
+    return generated_text, tokens, end, start
+
+# ── Interactive loop ──────────────────────────────────────────────────────────
+
+if __name__ == "__main__":
+    print("\n[+] Ready. Type 'quit' to exit.\n")
+
+    while True:
+        instruction = input("Instruction: ").strip()
+        if instruction.lower() == "quit":
+            break
+
+        inp = input("Input (optional, Enter to skip): ").strip()
+
+        print("-" * 50)
+        text, tokens, end, start = generate(instruction, inp)
+        print(text)
+        print()
+        
+        print(f"Generated tokens: {len(tokens)}")
+        print(f"Time: {end - start:.2f}s")
+        print(f"Speed: {len(tokens) / (end - start):.2f} tokens/sec")
+```
+
+---
+
+## 💬 Sample Outputs
+
+**These outputs were generated with these samplings: `temperature=0.7, top_k=50, top_p=0.9, repetition_penalty=1.15`**
+
+(The model still hallucinates, but can respond a big quantity of questions correctly)
+
+
+**User:** What is AI?<br>
+**Supra-50M Instruct:**:<br>
+AI refers to the simulation of human intelligence and creativity in machines, which are designed to mimic or surpass human cognition and reasoning. It is the process by which AI systems can solve problems, make predictions, or automate processes that typically require human-level thinking and problem solving. AI technology has been rapidly growing and evolving over time, with many potential benefits for society as a whole. Some of these include:
+1. Improved Accuracy: AI algorithms have demonstrated great accuracy in predicting outcomes, making accurate predictions on new data sets, and even answering real-world questions. This improves our ability to learn from experience and adapt to changing situations.
+2. Personalization: AI is used to personalize user experiences, such as recommending products based on their previous interactions and preferences. This helps people to stay motivated and maintain high levels of satisfaction.
+3. Better Decision Making: AI enables systems to analyze large amounts of data quickly and accurately, allowing us to make informed decisions more easily and
+
+<br>
+
+**User:** What is the capital of Japan?<br>
+**Supra-50M Instruct:**:<br>
+The capital of Japan is Tokyo.
+
+<br>
+
+**User:** Hi!<br>
+**Supra-50M Instruct:**:<br>
+Hello! How can i help you today?
+
+<br>
+
+**User:** What is the capital of United States?<br>
+**Supra-50M Instruct:**:<br>
+The capital of United States is New York City.
+
+<br>
+
+**User:** What is the capital of Russia?<br>
+**Supra-50M Instruct:**:<br>
+The capital of Russia is Moscow.
+
+<br>
+
+---
+
+## 📄 License
+
+This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
+
+---
+
+*© SupraLabs 2026 — Project Chimera*

Supra-50M-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac343c5c47cd7bf76ea7d133681e516fa4d93292caddf5c6121424a159dd0a18
+size 104739616

Supra-50M-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a5840b3e66cd159eae57675dab4ec4e8eb074b823ee68c2f65eb58a655f6f7
+size 104739616

Supra-50M-f32.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064af637a96629396a393f0fa07127b2f7112cdff425a600931ded2c1dfd05f3
+size 208286496

Supra-50M-iq1_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f52bfb2c1ad2dea33a1cbb730cff20fb3b255604ed0f8af28b3cf9c2654b9f
+size 23467168

Supra-50M-iq1_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575316b9a41d007eceed7114665404150f88efd8567070a96bb1334bb4a631d2
+size 22951072

Supra-50M-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58df1dd345b7fe778d75e8be7f76351cf78bf5a983422d1aa4527db63d9a77a0
+size 26404000

Supra-50M-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8da099acf66c43a8c24c4fb00f2b0398bccf33cae3041f8bc9df2f444403b2
+size 25715872

Supra-50M-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff6987747c0d92712c1fd05bf6f248e063e68809a5efa6233de1200fd7351efb
+size 25113760

Supra-50M-iq2_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a74deedf08f0bf77a560f602b748bf75cc183a75b8d8de29b00f3dbc630890
+size 24327328

Supra-50M-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18595237f929bd50dbc0d87baa319493cc6d71092694e3e0b0632d3f43825ece
+size 31704864

Supra-50M-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8619fe9959a730d8fa4d5c380c2652e4961074e74fd6e9eecd5adfb585455c1
+size 30988064

Supra-50M-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d5ffcd666c96c924f8f47a59c46b7e47bb16ac88daacc44564c0968736c8ab
+size 30159008

Supra-50M-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37504aff08245a321da540c5ac2a3d7b1fefc82926601dc94a1bd33042c9378
+size 27411616

Supra-50M-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1721fc1b644a08e723983aaf4ec22521fee015bae289f0241a2e79e72162cc2d
+size 34674464

Supra-50M-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8dabde0cc8eb4f8282c3760bcae72864c450361f87d9750cc3bab9cb2906f04
+size 33838880

Supra-50M-mxfp4_moe.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:475e95297cbfbd1ba402caef6b90d2a4ac58fb74403a18d92ceb318c054a1c2c
+size 56202016

Supra-50M-q1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30b4f062c747b21385ec62a629a64d6cd3f8dd565ed8b67737d47bb478019861
+size 19609376

Supra-50M-q2_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be159b8b588bbfab01acb9c7e7029e3cc5e47bb73e86b18d879d4c9614d241b
+size 28751648

Supra-50M-q2_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd2729f2686bf950415db4e9bd6c753b9aa5a1f5376700894eb99ceceb4299a
+size 28362912

Supra-50M-q3_k_l.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ad032471804e03439a40bb5a590dedfb10f638af3bcc7a034795a1331e4c4fd
+size 33826592

Supra-50M-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c32fb72ea9d0919fa882e7d722cd34c476c09a4a4d667cb242dcc95c214ef92a
+size 32728864

Supra-50M-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0123be26348080d3cf85947329b867b797b4bcce00ad101423f8dd048f0935a
+size 30988064

Supra-50M-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d08824c77aaff2edad58baa8201ea4780c904815e985271bd5d7e3a57e66859
+size 34539296

Supra-50M-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16a1a42313278294bf8c8e1354f189e9d13dc7f70bc03639573b419b72cfb19
+size 36751136

Supra-50M-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ceed3cfe8251c68552d92679bac3e7bd81bcf0b730a67d5c034d5206ed47909
+size 37445408

Supra-50M-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c981691b2111d5b745fa41f843b9668a694f71056d93f12c20039efe0d68ed
+size 35731232

Supra-50M-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a42073a9e95aa300eb324208eca3cdf56ef1f1f44eeb72cdd05c7bbfa1dfb8
+size 38962976

Supra-50M-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8f620cdcc2f05499e25651c1b8e3055f14402bfe67d0cb026d468b2f88ca06
+size 41174816

Supra-50M-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17fe75f627004dc57405a41e56d03b0d446e4594af5ce82dc0b89bd40ed0c19
+size 40959776

Supra-50M-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb594101c4a206680087bf3d460dc0e0d13faa0b90f7b9103720290874ac161
+size 39503648

Supra-50M-q6_k.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb812b8d657c12e4108ede360a4446a434c2f6e15195667a7a8f8431d99e6ed
+size 45758240

Supra-50M-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8223f3cc3be7e3d2a98ccf72a6408c9affebe95a68704363f979eea961620e6
+size 56202016

Supra-50M-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be346076332845bac748171e785cee49e09392746a7600aa18469c6d92a7ae3
+size 25138976

Supra-50M-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366f471bd8b0fbcf6bdc53a820214be62db71ff69aef1697d005727d4bfbba10
+size 26392352

configuration.json

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