Update models

.gitattributes

@@ -33,3 +33,16 @@ 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
+SmolVLM2-500M-Video-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-500M-Video-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

SmolVLM2-500M-Video-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ed1769ab3e4eccb17b0eacd9e2a7d2107406ba897be04413eb0c0daed9304a
+size 245423104

SmolVLM2-500M-Video-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd648b774b0d371741206637a8803ae05ff98e6ebdbbac2f6d53469fa79b19bc
+size 273071104

SmolVLM2-500M-Video-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5b0f544e445b8a841c50951f77c7a1e50f0afad5f8ab63faa8e18d9c30b5da
+size 261435904

SmolVLM2-500M-Video-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936639a718d1fe15068dc30efa47694e83feb99e8dae3bcaa3c91dec2af9607a
+size 245423104

SmolVLM2-500M-Video-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2741b3cad3cb4f72b240a74f63678e7af0091339d4e1a53473adc57d6fb2be57
+size 255867904

SmolVLM2-500M-Video-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d87ab0a92ba139cfdc0e79c40c20a93fa228d90643acf34c95367c446d3b02b
+size 303253504

SmolVLM2-500M-Video-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce7d595fd645d1ddc35a92560dadfb58f84dbfed723f3a0e38ceab40e70110f
+size 292578304

SmolVLM2-500M-Video-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a940d430d1dd95d123f8ce62a69b1d7a03b5de7b57cd2e41dcb190436ad190
+size 301103104

SmolVLM2-500M-Video-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341db7271cbb4d7fc823cfe42e42e0632ecf347191c51fafffe0d327d72771d8
+size 325563904

SmolVLM2-500M-Video-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bef5844796d3589a2b293015762beb099aa228c288c1204da1f0d06bc75e8e
+size 318805504

SmolVLM2-500M-Video-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4fda3bd0a18c4c7f0cf8576f25563ce7a9d28efed22783367bf56ba7a31934
+size 417762304

SmolVLM2-500M-Video-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f67b8036b2469fcd71728702720c6b51aebd759b78137a8120733b4d66438bc
+size 436808704

SmolVLM2-500M-Video-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f7e3f04bc2d3324ac1a9f52f5776fe13a69912adf74f8e7edacf773d140d77
+size 820424704

config.json

@@ -0,0 +1,141 @@
+{
+  "architectures": [
+    "SmolVLMForConditionalGeneration"
+  ],
+  "image_token_id": 49190,
+  "model_type": "smolvlm",
+  "pad_token_id": 128002,
+  "scale_factor": 4,
+  "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "head_dim": 64,
+    "hidden_size": 960,
+    "intermediate_size": 2560,
+    "is_llama_config": true,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_attention_heads": 15,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 5,
+    "pad_token_id": 2,
+    "perceiver_config": {
+      "_attn_implementation_autoset": false,
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "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": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "vllama3",
+      "no_repeat_ngram_size": 0,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_key_value_heads": 1,
+      "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": {},
+      "qk_layer_norms_perceiver": false,
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "resampler_depth": 6,
+      "resampler_head_dim": 96,
+      "resampler_n_heads": 16,
+      "resampler_n_latents": 64,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "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": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.46.0",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "pixel_shuffle_factor": 4,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_interleaved": false,
+    "rope_theta": 100000,
+    "torch_dtype": "bfloat16",
+    "transformers.js_config": {
+      "kv_cache_dtype": {
+        "fp16": "float16",
+        "q4f16": "float16"
+      }
+    },
+    "use_resampler": false,
+    "vocab_size": 49280
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_reentrant_checkpointing": false,
+  "vision_config": {
+    "hidden_size": 768,
+    "image_size": 512,
+    "max_image_size": {
+      "longest_edge": 512
+    },
+    "model_type": "smolvlm_vision",
+    "num_attention_heads": 12,
+    "patch_size": 16,
+    "size": {
+      "longest_edge": 2048
+    },
+    "tie_word_embeddings": false,
+    "use_base_siglip": false
+  },
+  "vocab_size": 49280
+}