Upload 4 files

.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
+qwen-instruct-1-5b.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,36 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+inference: false 
+base_model: Qwen/Qwen2-1.5B-Instruct
+base_model_relation: quantized 
+tags: [green, p1, llmware-chat, gguf,emerald]
+---
+
+# qwen-2-1.5b-instruct-gguf
+
+**qwen-2-1.5b-instruct-gguf** is Q4_K_M (int 4) quantized version of Qwen2 1.5b Instruct, providing a very fast, very small inference implementation, optimized for AI PCs.    
+
+[**qwen-2-1.5b-instruct-gguf**](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) is a leading chat model known for its high accuracy and strong math and logical capabilities.  
+
+
+### Model Description
+
+- **Developed by:** Qwen
+- **Quantized by:** llmware
+- **Model type:** qwen2-1.5b-instruct  
+- **Parameters:** 1.5 billion
+- **Model Parent:** Qwen/Qwen2 1.5B-Instruct  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** General purpose chat
+- **RAG Benchmark Accuracy Score:** NA  
+- **Quantization:** Q4_K_M  
+  
+
+## Model Card Contact
+
+[llmware on github](https://www.huggingface.co/llmware)  
+
+[llmware on hf](https://www.huggingface.co/llmware)  
+
+[llmware website](https://www.llmware.ai)  

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

hash_record_sha256.json

@@ -0,0 +1,4 @@
+{
+ "qwen-instruct-1-5b.gguf": "df9ddd27ecd956dc20fd43c6c583821947dc3ef3c6ffaa3ff25e5cc951a3130c",
+ "time_stamp": "2025-01-13_031122"
+}

qwen-instruct-1-5b.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9ddd27ecd956dc20fd43c6c583821947dc3ef3c6ffaa3ff25e5cc951a3130c
+size 986045504