Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+sage-gpt-neo-1.3B.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,28 @@
----
-license: mit
----
+# SAGE (Q8_0)
+
+Sage - GPT-Neo 1.3B fine-tuned on educational data
+
+- **Base Model**: EleutherAI/gpt-neo-1.3B
+- **Quantization**: Q8_0
+- **Format**: GGUF (llama.cpp / LM Studio compatible)
+- **Architecture**: GPT-NeoX
+
+## Quick Start
+
+### llama.cpp
+```bash
+./main -m sage-q8_0.gguf -p "Your prompt here"
+```
+
+### LM Studio
+1. Download `sage-q8_0.gguf`
+2. Open LM Studio
+3. Load model and start chatting
+
+### Python
+```python
+from llama_cpp import Llama
+llm = Llama(model_path="sage-q8_0.gguf")
+output = llm("Hello", max_tokens=128)
+print(output['choices'][0]['text'])
+```

sage-gpt-neo-1.3B.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2dbf14b9121340af6b169afc3bfbdb98363ea25c0fb904482ad3dda19e37d58
+size 4527693823

tokenizer.json

@@ -0,0 +1,11 @@
+{
+  "model": {
+    "type": "BPE",
+    "prefix": ""
+  },
+  "vocab": {},
+  "merges": [],
+  "special_tokens": {
+    "<|endoftext|>": 50256
+  }
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "gpt2"}