Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,13 @@
 ---
-base_model: GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0
 license: apache-2.0
+base_model: GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0
 tags:
 - mlx
 ---
 
 # GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx
 
-This quantized low-bit model [GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx](https://huggingface.co/GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx) was converted to MLX format from [`GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0`](https://huggingface.co/GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0) using gbx-lm version **0.3.4**.
+This quantized low-bit model [GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx](https://huggingface.co/GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx) was converted to MLX format from [`GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0`](https://huggingface.co/GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0) using gbx-lm version **0.4.0**.
 Refer to the [original model card](https://huggingface.co/GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0) for more details on the model.
 
 ## Use with mlx
@@ -20,5 +20,14 @@ pip install gbx-lm
 from gbx_lm import load, generate
 
 model, tokenizer = load("GreenBitAI/Qwen-2.5-3B-Instruct-layer-mix-bpw-4.0-mlx")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
 ```

config.json

@@ -1,84 +1,30 @@
 {
-    "add_cross_attention": false,
     "architectures": [
         "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 151643,
-    "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": 151645,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "silu",
     "hidden_size": 2048,
-    "id2label": {
-        "0": "LABEL_0",
-        "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 11008,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-        "LABEL_0": 0,
-        "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 32768,
     "max_window_layers": 70,
-    "min_length": 0,
     "model_type": "qwen2",
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 36,
     "num_key_value_heads": 2,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
     "quantization": {
         "group_size": null,
         "bits": null
     },
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
     "rms_norm_eps": 1e-06,
     "rope_theta": 1000000.0,
-    "sep_token_id": null,
     "sliding_window": null,
-    "suppress_tokens": null,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "tf_legacy_loss": false,
-    "tie_encoder_decoder": false,
     "tie_word_embeddings": true,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
     "torch_dtype": "float16",
-    "torchscript": false,
-    "transformers_version": "4.44.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
+    "transformers_version": "4.43.4",
     "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcaabcc407811b1185348b4c491f3241ff5f46a217fa1e61e9565313a9bc7c5
-size 2099383813
+oid sha256:78ce0de008185d935a4a7191e3505a1389eaf5a730238a8dd5b812668400bc1e
+size 2099384433

tokenizer_config.json

@@ -199,6 +199,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,