Upload folder using huggingface_hub

README.md

@@ -176,13 +176,31 @@ extra_gated_fields:
 extra_gated_description: The information you provide will be collected, stored, processed
   and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
 extra_gated_button_content: Submit
+widget:
+- example_title: Winter holidays
+  messages:
+  - role: system
+    content: You are a helpful and honest assistant. Please, respond concisely and
+      truthfully.
+  - role: user
+    content: Can you recommend a good destination for Winter holidays?
+- example_title: Programming assistant
+  messages:
+  - role: system
+    content: You are a helpful and honest code and programming assistant. Please,
+      respond concisely and truthfully.
+  - role: user
+    content: Write a function that computes the nth fibonacci number.
+inference:
+  parameters:
+    max_new_tokens: 300
+    stop:
+    - <|end_of_text|>
+    - <|eot_id|>
 ---
 
 # mlx-community/Meta-Llama-3-70B-Instruct-4bit
-This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.9.0**.
-
-Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
-
+This model was converted to MLX format from [`meta-llama/Meta-Llama-3-70B-Instruct`]() using mlx-lm version **0.10.0**.
 Refer to the [original model card](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct) for more details on the model.
 ## Use with mlx
 

config.json

@@ -1,85 +1,31 @@
 {
-    "add_cross_attention": false,
     "architectures": [
         "LlamaForCausalLM"
     ],
     "attention_bias": false,
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 128000,
-    "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": 128001,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "silu",
     "hidden_size": 8192,
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 28672,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 8192,
-    "min_length": 0,
     "model_type": "llama",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 64,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 80,
     "num_key_value_heads": 8,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "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": 500000.0,
-    "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": "4.40.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
+    "transformers_version": "4.40.0.dev0",
     "use_cache": true,
     "vocab_size": 128256
 }

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db3fd6ec2266ed400f0a967358f72c2ce4b4df53513a4e0365f2210f1e92f4b
-size 5338514834
+oid sha256:fad2c312718cadd55d3fe50fd5ae44cce500f9b61513ba92b180fc46cc34e49e
+size 5272167770

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0be6811819d56923a5aede8271ba3838b5c51998cb523103934341f02c25ef9
-size 5294649665
+oid sha256:ffb4f11fa816e5532f014eac891d3ab6da9b0e9f58d951cc7cf3e10dcd9715cb
+size 5294649694

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e0d9e2217379bef4e1a890f8ccec67527854e0fb95e6b15ed62719e4e38441
-size 5294649735
+oid sha256:c60d9e5e491175430f7c8f526821afb5ccea4028cf541a945d5683e1333b0ab3
+size 5294649717

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13973f7214cead910f4d0a45928ac338fd7a5bbefb08b2c4aae3942cfc102c33
-size 5294649737
+oid sha256:cf71556de92e26d1299a55e0f07dd3103ea88e724b38cdd4e7c7240552215011
+size 5294649733

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e85e1c9358138723de2d13c4ff3166419c2337d43c5fffbc72580c83b2a2028a
-size 5294649745
+oid sha256:c5bb8c45b4242c3b0850b775188732cdb0c8ac4b4cd557edfac7041030c0529c
+size 5294649717

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96946683ba5d32e811b35a3c4373564ded1dbcc039f9f04b9615cdb98a93b6ef
-size 5294649715
+oid sha256:26397f69a4bd11ee5a94926b5700228b23563bb1aca1bfd51d84712341207174
+size 5294649733

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb5deace8a8b18ea5aecca75c1ce5b1e78e89e84db3f9e980c5bd1427d9a169
-size 5294649715
+oid sha256:32e20364eee71bde6fbfafe11b9fc65a5be8a8f6ddd1383b785114497f4a5fe8
+size 5294649739

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94722b9eaef1d6638523202d91c9614611d209257c33caa449647871aba886ff
-size 4092496847
+oid sha256:f163ab85b3a035cedd77d53960d1ed65442ca0b6e33462329e0883692c52a562
+size 2648501502

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|eot_id|>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -2348,6 +2348,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -2050,9 +2050,9 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|eot_id|>",
+  "eos_token": "<|end_of_text|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"