Upload LlamaForCausalLM

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "PY007/TinyLlama-1.1B-Chat-v0.3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "disable_exllama": false,
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": 2048,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": false,
+  "vocab_size": 32003
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_new_tokens": 32,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4c62f59e25a664332371901b86ad817c33c46590a0037c732d3b1e55d37341
+size 768345169