Upload 2 files

README.md

@@ -1,3 +1,41 @@
----
-license: gemma
----
+---
+license: gemma
+inference: false
+base_model: google/gemma-2-9b-it
+base_model_relation: quantized 
+tags:
+- green
+- p9
+- llmware-chat
+- gguf
+- emerald
+---
+
+# gemma-2-9b-gguf
+
+**gemma-2-9b-gguf** is a GGUF Q4_K_M int4 quantized version of Google's Gemma-2-9B with Instruct Training (IT), providing a very fast, very small inference implementation, optimized for AI PCs.    
+
+[**gemma-2-9b-gguf**](https://huggingface.co/google/gemma-2-9b-it) is a leading open source foundation model from Google.  
+
+
+### Model Description
+
+- **Developed by:** Google
+- **Quantized by:** llmware
+- **Model type:** gemma-2-9b  
+- **Parameters:** 9 billion
+- **Model Parent:** google/gemma-2-9b-it  
+- **Language(s) (NLP):** English  
+- **License:** Apache 2.0  
+- **Uses:** General purpose chat 
+- **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 +1,33 @@
+{
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 42,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "sliding_window_size": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.0.dev0",
+  "use_cache": true,
+  "vocab_size": 256000
+}