Upload 9 files

README.md

@@ -1,3 +1,36 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+inference: false 
+---
+
+# bling-tiny-llama-ov
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+**bling-tiny-llama-ov** is an OpenVino int4 quantized version of BLING Tiny-Llama 1B, providing a very fast, very small inference implementation, optimized for AI PCs using Intel GPU, CPU and NPU.    
+
+[**bling-tiny-llama**](https://huggingface.co/llmware/bling-tiny-llama-v0) is a fact-based question-answering model, optimized for complex business documents.  
+
+Get started right away with [OpenVino](https://github.com/openvinotoolkit/openvino) 
+
+Looking for AI PC solutions and demos, contact us at [llmware](https://www.llmware.ai)    
+
+
+### Model Description
+
+- **Developed by:** llmware  
+- **Model type:** tinyllama  
+- **Parameters:** 1.1 billion
+- **Model Parent:** llmware/bling-tiny-llama-v0  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** Fact-based question-answering  
+- **RAG Benchmark Accuracy Score:** 86.5  
+- **Quantization:** int4  
+  
+
+## Model Card Contact
+
+[llmware on hf](https://www.huggingface.co/llmware)  
+
+[llmware website](https://www.llmware.ai)  

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32768,
+  "<|im_start|>": 32769
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "cognitivecomputations/dolphin-2.9.3-mistral-7B-32k",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32768,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "vocab_size": 32770
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.43.4"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404