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
+openhermes-2.5-mistral-7b.Q4_K_M.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: teknium/OpenHermes-2.5-Mistral-7B
+base_model_relation: quantized 
+tags: [green, p7, llmware-chat, gguf]
+---
+
+# teknium-open-hermes-2.5-mistral-gguf
+
+**teknium-open-hermes-2.5-mistral-gguf** is a GGUF Q4_K_M int4 quantized version of teknium's popular open hermes finetune of mistral, providing a very fast, very small inference implementation.    
+
+[**teknium-open-hermes-2.5-mistral**](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) is a leading chat finetuned version of mistral 7b.  
+
+
+### Model Description
+
+- **Developed by:** teknium
+- **Quantized by:** llmware   
+- **Model type:** mistral-7b  
+- **Parameters:** 7 billion
+- **Model Parent:** teknium/OpenHermes-2.5-Mistral-7B
+- **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 +1,25 @@
+{
+  "_name_or_path": "teknium/OpenHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "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": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

hash_record_sha256.json

@@ -0,0 +1,4 @@
+{
+ "openhermes-2.5-mistral-7b.Q4_K_M.gguf": "cd58120326971c71c0590f6b7084a0744e287ce9c67275d8b4bf34a5947d950b",
+ "time_stamp": "2025-02-11_002209"
+}

openhermes-2.5-mistral-7b.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd58120326971c71c0590f6b7084a0744e287ce9c67275d8b4bf34a5947d950b
+size 4368450304