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
+starling-lm-7b-alpha.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: berkeley-nest/Starling-LM-7B-alpha
+base_model_relation: quantized 
+tags: [green, p7, llmware-chat, gguf]
+---
+
+# starling-lm-7b-alpha-gguf
+
+**starling-lm-7b-alpha-gguf** is a GGUF Q4_K_M int4 quantized version of Berkeley Nest's popular finetune of mistral, providing a very fast, very small inference implementation.    
+
+[**starling-lm-7b-alpha-gguf**](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) is a leading chat finetuned version of mistral 7b.  
+
+
+### Model Description
+
+- **Developed by:** berkeley-nest
+- **Quantized by:** llmware   
+- **Model type:** mistral-7b  
+- **Parameters:** 7 billion
+- **Model Parent:** berkeley-nest/Starling-LM-7B-alpha
+- **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": "openchat/openchat_3.5",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "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,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32002
+}

hash_record_sha256.json

@@ -0,0 +1,4 @@
+{
+ "starling-lm-7b-alpha.Q4_K_M.gguf": "0951cbc1a6c3ed8d081db59366ccccf09ed52a4cfd5191812665b911fe6c669a",
+ "time_stamp": "2025-02-11_003708"
+}

starling-lm-7b-alpha.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0951cbc1a6c3ed8d081db59366ccccf09ed52a4cfd5191812665b911fe6c669a
+size 4368450368