Upload folder using huggingface_hub

README.md

@@ -11,8 +11,8 @@ pipeline_tag: text-generation
 ---
 
 # mlx-community/Qwen1.5-0.5B-Chat-4bit
-This model was converted to MLX format from [`Qwen/Qwen1.5-0.5B-Chat`]() using mlx-lm version **0.6.0**.
-Refer to the [original model card](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) for more details on the model.
+This model was converted to MLX format from [`qwen/Qwen1.5-0.5B-Chat`]() using mlx-lm version **0.10.0**.
+Refer to the [original model card](https://huggingface.co/qwen/Qwen1.5-0.5B-Chat) for more details on the model.
 ## Use with mlx
 
 ```bash

config.json

@@ -1,80 +1,30 @@
 {
-    "add_cross_attention": false,
     "architectures": [
         "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 151643,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 151645,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "silu",
     "hidden_size": 1024,
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 2816,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 32768,
     "max_window_layers": 21,
-    "min_length": 0,
     "model_type": "qwen2",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 24,
     "num_key_value_heads": 16,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
-    "sep_token_id": null,
     "sliding_window": 32768,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "transformers_version": "4.39.3",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
+    "transformers_version": "4.37.0",
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d101b67a41cdc6bb2241ef790029e6028f2552b74b3419e72dc507ecdafbe3
-size 1239172751
+oid sha256:a264bf9589d80795e1202f3eb83c4f40d116dbef317ef620de78bd79ce4a4495
+size 261240111

model.safetensors.index.json

@@ -1,297 +1,634 @@
 {
     "metadata": {
-        "total_size": 1239140352
+        "total_size": 261171200
     },
     "weight_map": {
-        "lm_head.weight": "model.safetensors",
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
         "model.embed_tokens.weight": "model.safetensors",
         "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
         "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
         "model.layers.0.mlp.up_proj.weight": "model.safetensors",
         "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
         "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
         "model.layers.1.mlp.up_proj.weight": "model.safetensors",
         "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
         "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
         "model.layers.10.mlp.up_proj.weight": "model.safetensors",
         "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
         "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
         "model.layers.11.mlp.up_proj.weight": "model.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
         "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
         "model.layers.12.mlp.up_proj.weight": "model.safetensors",
         "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
         "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
         "model.layers.13.mlp.up_proj.weight": "model.safetensors",
         "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
         "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
         "model.layers.14.mlp.up_proj.weight": "model.safetensors",
         "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
         "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
         "model.layers.15.mlp.up_proj.weight": "model.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
         "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
         "model.layers.16.mlp.up_proj.weight": "model.safetensors",
         "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
         "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
         "model.layers.17.mlp.up_proj.weight": "model.safetensors",
         "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.18.input_layernorm.weight": "model.safetensors",
+        "model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model.safetensors",
         "model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model.safetensors",
         "model.layers.18.mlp.up_proj.weight": "model.safetensors",
         "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.19.input_layernorm.weight": "model.safetensors",
+        "model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model.safetensors",
         "model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model.safetensors",
         "model.layers.19.mlp.up_proj.weight": "model.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
         "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
         "model.layers.2.mlp.up_proj.weight": "model.safetensors",
         "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.20.input_layernorm.weight": "model.safetensors",
+        "model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model.safetensors",
         "model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model.safetensors",
         "model.layers.20.mlp.up_proj.weight": "model.safetensors",
         "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.21.input_layernorm.weight": "model.safetensors",
+        "model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model.safetensors",
         "model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model.safetensors",
         "model.layers.21.mlp.up_proj.weight": "model.safetensors",
         "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.22.input_layernorm.weight": "model.safetensors",
+        "model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model.safetensors",
         "model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model.safetensors",
         "model.layers.22.mlp.up_proj.weight": "model.safetensors",
         "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.23.input_layernorm.weight": "model.safetensors",
+        "model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model.safetensors",
         "model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model.safetensors",
         "model.layers.23.mlp.up_proj.weight": "model.safetensors",
         "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
         "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
         "model.layers.3.mlp.up_proj.weight": "model.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
         "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
         "model.layers.4.mlp.up_proj.weight": "model.safetensors",
         "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
         "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
         "model.layers.5.mlp.up_proj.weight": "model.safetensors",
         "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
         "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
         "model.layers.6.mlp.up_proj.weight": "model.safetensors",
         "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
         "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
         "model.layers.7.mlp.up_proj.weight": "model.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
         "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
         "model.layers.8.mlp.up_proj.weight": "model.safetensors",
         "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
         "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
         "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
         "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
         "model.layers.9.mlp.up_proj.weight": "model.safetensors",
         "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
         "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
         "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
         "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
         "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
         "model.norm.weight": "model.safetensors"
     }