Upload 2 files

README.md

@@ -1,3 +1,39 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+inference: false
+tags:
+- green
+- llmware-chat
+- p1
+- ov
+- emerald
+---
+
+# tiny-llama-chat-ov
+
+**tiny-llama-chat-ov** is an OpenVino int4 quantized version of TinyLlama-Chat, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    
+
+[**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

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "tiny-llama-chat-ov",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "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,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}