Upload folder using huggingface_hub

README.md

@@ -11,7 +11,7 @@ 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`]().
+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.
 ## Use with mlx
 

config.json

@@ -1,86 +1,81 @@
 {
-    "vocab_size": 151936,
-    "max_position_embeddings": 32768,
-    "hidden_size": 1024,
-    "intermediate_size": 2816,
-    "num_hidden_layers": 24,
-    "num_attention_heads": 16,
-    "use_sliding_window": false,
-    "sliding_window": 32768,
-    "max_window_layers": 21,
-    "num_key_value_heads": 16,
-    "hidden_act": "silu",
-    "initializer_range": 0.02,
-    "rms_norm_eps": 1e-06,
-    "use_cache": true,
-    "rope_theta": 1000000.0,
+    "add_cross_attention": false,
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
     "attention_dropout": 0.0,
-    "return_dict": true,
-    "output_hidden_states": false,
-    "output_attentions": false,
-    "torchscript": false,
-    "torch_dtype": "bfloat16",
-    "use_bfloat16": false,
-    "tf_legacy_loss": false,
-    "pruned_heads": {},
-    "tie_word_embeddings": false,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
     "chunk_size_feed_forward": 0,
-    "is_encoder_decoder": false,
-    "is_decoder": false,
     "cross_attention_hidden_size": null,
-    "add_cross_attention": false,
-    "tie_encoder_decoder": false,
-    "max_length": 20,
-    "min_length": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
     "do_sample": false,
     "early_stopping": false,
-    "num_beams": 1,
-    "num_beam_groups": 1,
-    "diversity_penalty": 0.0,
-    "temperature": 1.0,
-    "top_k": 50,
-    "top_p": 1.0,
-    "typical_p": 1.0,
-    "repetition_penalty": 1.0,
-    "length_penalty": 1.0,
-    "no_repeat_ngram_size": 0,
     "encoder_no_repeat_ngram_size": 0,
-    "bad_words_ids": null,
-    "num_return_sequences": 1,
-    "output_scores": false,
-    "return_dict_in_generate": false,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "remove_invalid_values": false,
+    "eos_token_id": 151645,
     "exponential_decay_length_penalty": null,
-    "suppress_tokens": null,
-    "begin_suppress_tokens": null,
-    "architectures": [
-        "Qwen2ForCausalLM"
-    ],
     "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
     },
-    "tokenizer_class": null,
-    "prefix": null,
-    "bos_token_id": 151643,
+    "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,
-    "eos_token_id": 151645,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
     "sep_token_id": null,
-    "decoder_start_token_id": null,
+    "sliding_window": 32768,
+    "suppress_tokens": null,
     "task_specific_params": null,
-    "problem_type": null,
-    "_name_or_path": "/Users/madroid/.cache/huggingface/hub/models--Qwen--Qwen1.5-0.5B-Chat/snapshots/6c705984bb8b5591dd4e1a9e66e1a127965fd08d",
-    "transformers_version": "4.38.1",
-    "model_type": "qwen2",
-    "quantization": {
-        "group_size": 64,
-        "bits": 4
-    }
+    "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,
+    "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 sha256:4385eea06aa05ad0b7c6210b8464ddbfd1450bf8b502fcda0f49fbf4836f5d89
-size 572405815
+oid sha256:c2d101b67a41cdc6bb2241ef790029e6028f2552b74b3419e72dc507ecdafbe3
+size 1239172751

model.safetensors.index.json

@@ -1,635 +1,297 @@
 {
     "metadata": {
-        "total_size": 572336128
+        "total_size": 1239140352
     },
     "weight_map": {
-        "lm_head.biases": "model.safetensors",
-        "lm_head.scales": "model.safetensors",
         "lm_head.weight": "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"
     }

tokenizer_config.json

@@ -31,7 +31,7 @@
     "<|im_end|>"
   ],
   "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",