Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -9,6 +9,7 @@ tags:
 - unsloth
 - mistral
 - trl
+- sft
 ---
 
 # Uploaded  model

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "LeroyDyer/_Spydaz_Web_AI_MistralStar",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "LeroyDyer/_Spydaz_Web_AI_MistralStar--_SpydazWebAI_Mistral_Transformer_.MistralConfig",
+    "AutoModel": "LeroyDyer/_Spydaz_Web_AI_MistralStar--_SpydazWebAI_Mistral_Transformer_.MistralModel",
+    "AutoModelForCausalLM": "LeroyDyer/_Spydaz_Web_AI_MistralStar--_SpydazWebAI_Mistral_Transformer_.MistralStarForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "max_thoughts": 13,
+  "merged_lm_and_talk_heads": false,
+  "merged_lm_and_think_heads": true,
+  "merged_talk_heads": true,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "thought_length": 10,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.0.dev0",
+  "unsloth_version": "2024.7",
+  "use_cache": true,
+  "use_complex_talk_head": true,
+  "use_complex_think_head": false,
+  "use_concat_talk_head": true,
+  "use_shallow_talk": false,
+  "use_shallow_think": true,
+  "use_weighted_talk_head": true,
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "num_beams": 4,
+  "num_return_sequences": 2,
+  "temperature": 0.7,
+  "top_k": 100,
+  "top_p": 0.68,
+  "transformers_version": "4.43.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69208e317aa4c795ef5841c83d214f9bbdcfdb025ace4a3382cd66a5ca409095
+size 4413906182