Upload LlamaForCausalLM

config.json

@@ -1,27 +1,41 @@
 {
-  "_name_or_path": "LucidBrains/Pixely1B-V0",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attn_pdrop": 0.0,
   "bos_token_id": 1,
+  "c_max_position_embeddings": 2048,
+  "embd_pdrop": 0.0,
   "eos_token_id": 2,
+  "fcm_max_ratio": 0.0,
+  "fcm_min_ratio": 0.0,
+  "flash_attn_key_chunk_size": 1024,
+  "flash_attn_query_chunk_size": 1024,
+  "freq_max_position_embeddings": 2048,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
   "intermediate_size": 5632,
+  "load_in_8bit": false,
   "max_position_embeddings": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
+  "number_rep_kv": 1,
   "pretraining_tp": 1,
+  "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 10000,
+  "scan_mlp_chunk_size": 1024,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.35.2",
   "use_cache": true,
+  "use_flash_attention": false,
+  "use_pjit_attention_force": false,
+  "use_sacn_mlp": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.35.0"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cf73dac472049a5905ab0f8b343e78f860d5e3b94684243cfee0e8fbea36063
+size 2200119664