add 2-bit llama3b groupsize 32

config.json

@@ -0,0 +1,22 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"add_bos_token": true, "add_eos_token": false, "model_max_length": 2048, "pad_token": null, "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "clean_up_tokenization_spaces": false, "bos_token": {"__type": "AddedToken", "content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"__type": "AddedToken", "content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"__type": "AddedToken", "content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}}