add awq model

README.md

@@ -1,13 +1,69 @@
 ---
+library_name: transformers
+tags:
+- 4-bit
+- AWQ
+- text-generation
+- autotrain_compatible
+- endpoints_compatible
+pipeline_tag: text-generation
 inference: false
+quantized_by: Suparious
 ---
 # macadeliccc/gemma-orchid-7b-dpo AWQ
 
-** PROCESSING .... ETA 30mins **
-
 - Model creator: [macadeliccc](https://huggingface.co/macadeliccc)
 - Original model: [gemma-orchid-7b-dpo](https://huggingface.co/macadeliccc/gemma-orchid-7b-dpo)
 
+
+
+## How to use
+
+### Install the necessary packages
+
+```bash
+pip install --upgrade autoawq autoawq-kernels
+```
+
+### Example Python code
+
+```python
+from awq import AutoAWQForCausalLM
+from transformers import AutoTokenizer, TextStreamer
+
+model_path = "solidrust/gemma-orchid-7b-dpo-AWQ"
+system_message = "You are gemma-orchid-7b-dpo, incarnated as a powerful AI. You were created by macadeliccc."
+
+# Load model
+model = AutoAWQForCausalLM.from_quantized(model_path,
+                                          fuse_layers=True)
+tokenizer = AutoTokenizer.from_pretrained(model_path,
+                                          trust_remote_code=True)
+streamer = TextStreamer(tokenizer,
+                        skip_prompt=True,
+                        skip_special_tokens=True)
+
+# Convert prompt to tokens
+prompt_template = """\
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant"""
+
+prompt = "You're standing on the surface of the Earth. "\
+        "You walk one mile south, one mile west and one mile north. "\
+        "You end up exactly where you started. Where are you?"
+
+tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
+                  return_tensors='pt').input_ids.cuda()
+
+# Generate output
+generation_output = model.generate(tokens,
+                                  streamer=streamer,
+                                  max_new_tokens=512)
+```
+
 ### About AWQ
 
 AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--macadeliccc--gemma-orchid-7b-dpo/snapshots/765c358363079f45db287e5597c80236e02e0758",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 256000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529110cc977d6d6dc840676b35e0c539614148c89ce16aaefb87629593834f37
+size 6558499704

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73cd0e14fa48982d809f4e9c2cb81b1de2186d8dee8a826aa2769984a590b993
+size 614576896

model.safetensors.index.json

@@ -0,0 +1,654 @@
+{
+    "metadata": {
+        "total_size": 5600139264
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "lm_head.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

quant_config.json

@@ -0,0 +1,6 @@
+{
+  "zero_point": true,
+  "q_group_size": 128,
+  "w_bit": 4,
+  "version": "GEMM"
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}