Upload 4 files

README.md

@@ -1,3 +1,41 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+inference: false
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0  
+base_model_relation: quantized 
+tags:
+- green
+- llmware-chat
+- p1
+- gguf
+- emerald
+---
+
+# tiny-llama-chat-gguf
+
+**tiny-llama-chat-gguf** is an GGUF Q4_K_M int4 quantized version of TinyLlama-Chat, providing a very fast, very small inference implementation, optimized for AI PCs.    
+
+[**tiny-llama-chat**](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) is the official chat finetuned version of tiny-llama. 
+
+
+### Model Description
+
+- **Developed by:** TinyLlama
+- **Quantized by:** llmware  
+- **Model type:** llama
+- **Parameters:** 1.1 billion
+- **Model Parent:** TinyLlama-1.1B-Chat-v1.0  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** Chat and general purpose LLM
+- **RAG Benchmark Accuracy Score:** NA  
+- **Quantization:** int4  
+  
+
+## Model Card Contact
+
+[llmware on github](https://www.github.com/llmware-ai/llmware)  
+
+[llmware on hf](https://www.huggingface.co/llmware)  
+
+[llmware website](https://www.llmware.ai)

config.json

@@ -1,8 +1,10 @@
 {
+  "_name_or_path": "tiny-llama-chat-gguf",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -10,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 5632,
   "max_position_embeddings": 2048,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
@@ -19,8 +22,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 32000
 }

hash_record_sha256.json

@@ -0,0 +1,4 @@
+{
+ "tiny-llama-chat.gguf": "1f7b92940e5711806cf4ea62a4ae588261ffb29f05e77f6dec282ac1ac41fdca",
+ "time_stamp": "2025-02-08_151503"
+}