Upload folder using huggingface_hub

README.md

@@ -0,0 +1,129 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-generation
+- mlx
+datasets:
+- ehartford/wizard_vicuna_70k_unfiltered
+- totally-not-an-llm/EverythingLM-data-V3
+- Open-Orca/SlimOrca-Dedup
+- databricks/databricks-dolly-15k
+- THUDM/webglm-qa
+base_model: JackFram/llama-160m
+widget:
+- text: '<|im_start|>system
+
+    You are a helpful assistant, who answers with empathy.<|im_end|>
+
+    <|im_start|>user
+
+    Got a question for you!<|im_end|>
+
+    <|im_start|>assistant
+
+    Sure! What''s it?<|im_end|>
+
+    <|im_start|>user
+
+    Why do you love cats so much!? 🐈<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with empathy.<|im_end|>
+
+    <|im_start|>user
+
+    Who is Mona Lisa?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who provides concise responses.<|im_end|>
+
+    <|im_start|>user
+
+    Heya!<|im_end|>
+
+    <|im_start|>assistant
+
+    Hi! How may I help you today?<|im_end|>
+
+    <|im_start|>user
+
+    I need to build a simple website. Where should I start learning about web development?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>user
+
+    Invited some friends to come home today. Give me some ideas for games to play
+    with them!<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with details and curiosity.<|im_end|>
+
+    <|im_start|>user
+
+    What are some potential applications for quantum computing?<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who gives creative responses.<|im_end|>
+
+    <|im_start|>user
+
+    Write the specs of a game about mages in a fantasy world.<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with details.<|im_end|>
+
+    <|im_start|>user
+
+    Tell me about the pros and cons of social media.<|im_end|>
+
+    <|im_start|>assistant'
+- text: '<|im_start|>system
+
+    You are a helpful assistant who answers user''s questions with confidence.<|im_end|>
+
+    <|im_start|>user
+
+    What is a dog?<|im_end|>
+
+    <|im_start|>assistant
+
+    A dog is a four-legged, domesticated animal that is a member of the class Mammalia,
+    which includes all mammals. Dogs are known for their loyalty, playfulness, and
+    ability to be trained for various tasks. They are also used for hunting, herding,
+    and as service animals.<|im_end|>
+
+    <|im_start|>user
+
+    What is the color of an apple?<|im_end|>
+
+    <|im_start|>assistant'
+inference:
+  parameters:
+    max_new_tokens: 250
+    penalty_alpha: 0.5
+    top_k: 4
+    repetition_penalty: 1.01
+---
+
+# Llama-160M-Chat-v1-4bit-mlx
+This model was converted to MLX format from [`Felladrin/Llama-160M-Chat-v1`]().
+Refer to the [original model card](https://huggingface.co/Felladrin/Llama-160M-Chat-v1) for more details on the model.
+## Use with mlx
+```bash
+pip install mlx
+git clone https://github.com/ml-explore/mlx-examples.git
+cd mlx-examples/llms/hf_llm
+python generate.py --model mlx-community/Llama-160M-Chat-v1-4bit-mlx --prompt "My name is"
+```

config.json

@@ -0,0 +1,85 @@
+{
+    "vocab_size": 32000,
+    "max_position_embeddings": 2048,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "num_hidden_layers": 12,
+    "num_attention_heads": 12,
+    "num_key_value_heads": 12,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "float32",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "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,
+    "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,
+    "chunk_size_feed_forward": 0,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": 0,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "Felladrin/Llama-160M-Chat-v1",
+    "transformers_version": "4.35.2",
+    "model_type": "llama",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

weights.00.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a0a8dd2483a1e6b13cdaf6aaf7d0cb52556f461132a6d35a0c8425a293c199
+size 126745598