Upload folder using huggingface_hub

config.json

@@ -0,0 +1,52 @@
+{
+    "_name_or_path": "/workspace/process/llama-68m",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "bos_token_id": 0,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "max_position_embeddings": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 12,
+    "pad_token_id": 1,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 4,
+        "block_name_to_quantize": "model.layers",
+        "cache_block_outputs": true,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "exllama_config": {
+            "version": 1
+        },
+        "group_size": 128,
+        "max_input_length": null,
+        "model_seqlen": 4096,
+        "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,
+        "use_exllama": false
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.35.0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603971352a2aed704e6ece67d273a8731500209f4edd7601645028d66431c1fd
+size 49152136

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460e1e9fd8efae4d546ea490292a8260d1e465568336aabb8bdc3f9fce902ba7
+size 9922680

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:480a097c63ac151fabbeaa0a2970c2ac012e1d4afb723a9356c56ddb93a163e8
+size 49152128

model.safetensors.index.json

@@ -0,0 +1,84 @@
+{
+  "metadata": {
+    "total_size": 108218880
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.g_idx": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00002-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00002-of-00003.safetensors"
+  }
+}

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": true
+}