a8b7eda132fbab4b8955ac6dfe1658edf27a4038deb0a4b55aceecd13e79cf93

README.md

@@ -1,21 +1,17 @@
 ---
-language:
-- en
 library_name: transformers
 license: apache-2.0
+language:
+- en
+base_model: mlx-community/SmolLM2-1.7B-Instruct
 tags:
 - mlx
 - mlx
-base_model: mlx-community/SmolLM-1.7B-Instruct-8bit
-datasets:
-- dattaraj/pc-insurance-cost-estimator
 ---
 
 # dattaraj/smol-lora-insurance-estimates
 
-The Model [dattaraj/smol-lora-insurance-estimates](https://huggingface.co/dattaraj/smol-lora-insurance-estimates) was converted to MLX format from [mlx-community/SmolLM-1.7B-Instruct-8bit](https://huggingface.co/mlx-community/SmolLM-1.7B-Instruct-8bit) using mlx-lm version **0.19.1**.
-This is a test to demonstrate the power of small langauge models. We take a SmoLM 1.7B model and fine-tune it on insurance estimation dataset available at: https://huggingface.co/datasets/dattaraj/pc-insurance-cost-estimator
-The fine-tuned language model is now expert at taking text description of damage and generating cost estimation.
+The Model [dattaraj/smol-lora-insurance-estimates](https://huggingface.co/dattaraj/smol-lora-insurance-estimates) was converted to MLX format from [mlx-community/SmolLM2-1.7B-Instruct](https://huggingface.co/mlx-community/SmolLM2-1.7B-Instruct) using mlx-lm version **0.19.1**.
 
 ## Use with mlx
 
@@ -37,4 +33,4 @@ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not
     )
 
 response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```
+```

config.json

@@ -10,7 +10,7 @@
     "hidden_size": 2048,
     "initializer_range": 0.02,
     "intermediate_size": 8192,
-    "max_position_embeddings": 2048,
+    "max_position_embeddings": 8192,
     "mlp_bias": false,
     "model_type": "llama",
     "num_attention_heads": 32,
@@ -18,15 +18,17 @@
     "num_key_value_heads": 32,
     "pad_token_id": 2,
     "pretraining_tp": 1,
-    "quantization": {
-        "group_size": 64,
-        "bits": 8
-    },
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
-    "rope_theta": 10000.0,
+    "rope_theta": 130000,
     "tie_word_embeddings": true,
     "torch_dtype": "bfloat16",
+    "transformers.js_config": {
+        "kv_cache_dtype": {
+            "q4f16": "float16",
+            "fp16": "float16"
+        }
+    },
     "transformers_version": "4.42.3",
     "use_cache": true,
     "vocab_size": 49152

model.safetensors.index.json

@@ -1,562 +1,224 @@
 {
     "metadata": {
-        "total_size": 1818431488
+        "total_size": 3422752768
     },
     "weight_map": {
-        "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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

@@ -143,7 +143,7 @@
     "<|im_end|>"
   ],
   "bos_token": "<|im_start|>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|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 AI assistant named SmolLM, trained by Hugging Face<|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|>",
   "model_max_length": 2048,