[WIP] Upload folder using huggingface_hub (multi-commit 1787213f8bb770ac693d3723954c3be65528ce8ba1f6ffdfa526fd8d9f22e9b9)

README.md

@@ -1,36 +0,0 @@
----
-library_name: transformers
-license: apache-2.0
-language:
-- en
-base_model: mlx-community/SmolLM2-1.7B-Instruct
-tags:
-- mlx
-- mlx
----
-
-# 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/SmolLM2-1.7B-Instruct](https://huggingface.co/mlx-community/SmolLM2-1.7B-Instruct) using mlx-lm version **0.19.1**.
-
-## Use with mlx
-
-```bash
-pip install mlx-lm
-```
-
-```python
-from mlx_lm import load, generate
-
-model, tokenizer = load("dattaraj/smol-lora-insurance-estimates")
-
-prompt="hello"
-
-if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
-    messages = [{"role": "user", "content": prompt}]
-    prompt = tokenizer.apply_chat_template(
-        messages, tokenize=False, add_generation_prompt=True
-    )
-
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```

config.json

@@ -1,35 +0,0 @@
-{
-    "architectures": [
-        "LlamaForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "bos_token_id": 1,
-    "eos_token_id": 2,
-    "hidden_act": "silu",
-    "hidden_size": 2048,
-    "initializer_range": 0.02,
-    "intermediate_size": 8192,
-    "max_position_embeddings": 8192,
-    "mlp_bias": false,
-    "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 24,
-    "num_key_value_heads": 32,
-    "pad_token_id": 2,
-    "pretraining_tp": 1,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "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

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed434ebda3c316df8449bbf0061a63c10518926e82cdf283cc5d83790ee1c6a7
-size 3422777902

model.safetensors.index.json

@@ -1,225 +0,0 @@
-{
-    "metadata": {
-        "total_size": 3422752768
-    },
-    "weight_map": {
-        "model.embed_tokens.weight": "model.safetensors",
-        "model.layers.0.input_layernorm.weight": "model.safetensors",
-        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
-        "model.layers.0.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.0.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.1.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.1.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.10.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.10.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.11.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.11.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.12.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.12.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.13.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.13.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.14.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.14.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.15.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.15.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.16.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.16.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.17.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.17.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.18.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.18.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.19.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.19.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.2.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.2.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.20.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.20.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.21.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.21.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.22.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.22.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.23.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.23.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.3.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.3.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.4.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.4.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.5.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.5.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.6.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.6.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.7.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.7.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.8.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.8.self_attn.q_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.9.mlp.gate_proj.weight": "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.weight": "model.safetensors",
-        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
-        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
-        "model.norm.weight": "model.safetensors"
-    }
-}

special_tokens_map.json

@@ -1,34 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": {
-    "content": "<|im_start|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer_config.json

@@ -1,154 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": "<repo_name>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": "<reponame>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "<file_sep>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "<filename>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": "<gh_stars>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": "<issue_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": "<issue_comment>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": "<issue_closed>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<jupyter_start>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "12": {
-      "content": "<jupyter_text>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "13": {
-      "content": "<jupyter_code>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "14": {
-      "content": "<jupyter_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "15": {
-      "content": "<jupyter_script>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "16": {
-      "content": "<empty_output>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": "<|im_start|>",
-  "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,
-  "pad_token": "<|im_end|>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
-  "vocab_size": 49152
-}