Add GGUF quantized versions for Ollama/llama.cpp compatibility with API instructions

.gitattributes

@@ -34,3 +34,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gguf/qwen3-0.6b-tensorslayer-f16.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/qwen3-0.6b-tensorslayer-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/qwen3-0.6b-tensorslayer-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+gguf/qwen3-0.6b-tensorslayer-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

gguf/README.md

@@ -6,10 +6,10 @@ This folder contains GGUF (GPT-Generated Unified Format) versions of the Tensor-
 
 | File | Quantization | Size | Use Case |
 |------|-------------|------|----------|
-| `qwen3-0.6b-tensorslayer-f16.gguf` | FP16 | ~1.2GB | Maximum quality |
-| `qwen3-0.6b-tensorslayer-q8_0.gguf` | 8-bit | ~650MB | High quality, smaller |
-| `qwen3-0.6b-tensorslayer-q5_k_m.gguf` | 5-bit K-quant | ~450MB | Balanced quality/size |
-| `qwen3-0.6b-tensorslayer-q4_0.gguf` | 4-bit | ~350MB | Fastest inference |
+| `qwen3-0.6b-tensorslayer-f16.gguf` | FP16 | ~1.1GB | Maximum quality |
+| `qwen3-0.6b-tensorslayer-q8_0.gguf` | 8-bit | ~610MB | High quality, smaller |
+| `qwen3-0.6b-tensorslayer-q5_k_m.gguf` | 5-bit K-quant | ~424MB | Balanced quality/size |
+| `qwen3-0.6b-tensorslayer-q4_0.gguf` | 4-bit | ~364MB | Fastest inference |
 
 ## Usage with Ollama
 
@@ -48,7 +48,7 @@ ollama run qwen3-enhanced "What is the relationship between 'semantic meaning' a
 ```python
 import requests
 
-# Using Ollama API (replace with your endpoint)
+# Using Ollama API
 OLLAMA_API = "2612b573cd924d148095de291b70bd98.MDGkuS-nd3Ms0a3tBQdpkk-Z"
 response = requests.post(f"{OLLAMA_API}/api/generate", json={
     "model": "qwen3-enhanced",

gguf/qwen3-0.6b-tensorslayer-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b02802d2abc6b5aad457a4fc64da01341b97f4d569b60bec1273e062b07ad4
+size 1198182016

gguf/qwen3-0.6b-tensorslayer-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44746f83b453466e40c6899e1d4059751655c6dffc4d00ed9418e3cfef6bfc9c
+size 381565568

gguf/qwen3-0.6b-tensorslayer-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc83a79c321e0d26dec88e29860675b85b57025e3bccad02589f5bd625e1f88
+size 444414592

gguf/qwen3-0.6b-tensorslayer-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a512a8ec6c39a301fd239758a80a8a22c5888b4a0cde6bc21462755db1dc88d
+size 639446656