Upload folder using huggingface_hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- code
+license: llama2
+tags:
+- llama-2
+- mlx
+pipeline_tag: text-generation
+---
+
+# mlx-community/CodeLlama-70b-Python-hf-4bit-MLX
+This model was converted to MLX format from [`codellama/CodeLlama-70b-Python-hf`]().
+Refer to the [original model card](https://huggingface.co/codellama/CodeLlama-70b-Python-hf) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/CodeLlama-70b-Python-hf-4bit-MLX")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<step>": 32015
+}

config.json

@@ -0,0 +1,86 @@
+{
+    "vocab_size": 32016,
+    "max_position_embeddings": 4096,
+    "hidden_size": 8192,
+    "intermediate_size": 28672,
+    "num_hidden_layers": 80,
+    "num_attention_heads": 64,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "pretraining_tp": 1,
+    "use_cache": true,
+    "rope_theta": 10000,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "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,
+    "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": null,
+    "eos_token_id": 2,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/ifioravanti/.cache/huggingface/hub/models--codellama--CodeLlama-70b-Python-hf/snapshots/79467981bab591dd6860707ed517d1186fbcfc1e",
+    "transformers_version": "4.36.2",
+    "model_type": "llama",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f5ab70853e48493171625c01f44fdea47c121276efd597aae12c7de7dbf6d6
+size 5337867948

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74036d817f8dd6e4d5bce0b2e90c6172a97d28a899751d275e66a07622bf1641
+size 5341836690

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2896f77bfe81e26a30217d5c0f983ca9eaaf3feaa3fbed8d73682c00ce3347
+size 5332398774

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947f57b4e0a2e2a3d009b35ae901735b5a2d785d4370e16a70f6d7a3553995c7
+size 5294649693

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e175a205fb61d1e841527ca694fbaa377039d8f817a183f97f03fbb06a97bcae
+size 5294649675

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0427fdba5c5518cbfd3780ebe763288f26796fdf06cd4c4863b0c2a38e9675fb
+size 5294649647

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4af3411ec85927c98916980611909a0d377b34543f40a55136a8874e22e184
+size 5294649703

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7c42ca926677cdcd75e9af28d9529296e2cd77d1f479ecae6c3d65b321ee91
+size 1987937565

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "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 sha256:99049b351301fb75b3b0587a484b675cbfd51abe27d2b92eabd385e4c41f97e9
+size 500033

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}