Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+license: other
+tags:
+- mlx
+base_model: 01-ai/yi-34b-200k
+datasets:
+- ai2_arc
+- allenai/ultrafeedback_binarized_cleaned
+- argilla/distilabel-intel-orca-dpo-pairs
+- jondurbin/airoboros-3.2
+- codeparrot/apps
+- facebook/belebele
+- bluemoon-fandom-1-1-rp-cleaned
+- boolq
+- camel-ai/biology
+- camel-ai/chemistry
+- camel-ai/math
+- camel-ai/physics
+- jondurbin/contextual-dpo-v0.1
+- jondurbin/gutenberg-dpo-v0.1
+- jondurbin/py-dpo-v0.1
+- jondurbin/truthy-dpo-v0.1
+- LDJnr/Capybara
+- jondurbin/cinematika-v0.1
+- WizardLM/WizardLM_evol_instruct_70k
+- glaiveai/glaive-function-calling-v2
+- jondurbin/gutenberg-dpo-v0.1
+- grimulkan/LimaRP-augmented
+- lmsys/lmsys-chat-1m
+- ParisNeo/lollms_aware_dataset
+- TIGER-Lab/MathInstruct
+- Muennighoff/natural-instructions
+- openbookqa
+- kingbri/PIPPA-shareGPT
+- piqa
+- Vezora/Tested-22k-Python-Alpaca
+- ropes
+- cakiki/rosetta-code
+- Open-Orca/SlimOrca
+- b-mc2/sql-create-context
+- squad_v2
+- mattpscott/airoboros-summarization
+- migtissera/Synthia-v1.3
+- unalignment/toxic-dpo-v0.2
+- WhiteRabbitNeo/WRN-Chapter-1
+- WhiteRabbitNeo/WRN-Chapter-2
+- winogrande
+license_name: yi-license
+license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
+---
+
+# mlx-community/bagel-dpo-34b-v0.5-4bit-mlx
+This model was converted to MLX format from [`jondurbin/bagel-dpo-34b-v0.5`]() using mlx-lm version **0.6.0**.
+Refer to the [original model card](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.5) 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/bagel-dpo-34b-v0.5-4bit-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,85 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 20480,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 200000,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 56,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "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,
+    "vocab_size": 64000
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148c154222250e82946c38c2f1725c445f7724cec94145676ce5f8a206816ea6
+size 5348111210

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44313cd56cf432cb07df1a4706451e3c67f101c3e2f7e6a3cd284f8fca00f7fa
+size 5363802145

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afca1ab17fa688dd20acf41d50dcf4c6513f8c5263bf2a8601b2e4f0a64056d
+size 5334900451

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd2dc20c2de9ef525f220c99a840bda0db9433f58bca0ee0a1e053e7ceecc3bb
+size 3957813074

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": "<unk>",
+    "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 sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
+size 1033105

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_bos_token": false,
+  "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": 200000,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}