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
+SmolVLM2-2.2B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+SmolVLM2-2.2B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text

SmolVLM2-2.2B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a37e1e1e3e828c064a9b98c4d2e4b90ecef15d1df2985ac49610b6be2d76937
+size 707921984

SmolVLM2-2.2B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1738177f6191c353c5c9078d7ed1305dd0bae7d9d668eef676c1a4cc17157512
+size 976121920

SmolVLM2-2.2B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b230be04ffd5b39ef6cc58a56e3d7eccf5b7e6d05c40d649d857eb5c3e71ef
+size 903770176

SmolVLM2-2.2B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525bd03a4614cbd092f8506a02b22fb45434544f2b19e58d541f16984189b12a
+size 820408384

SmolVLM2-2.2B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5085401c3b4794134b459dd774c937f972586d9652c9e3aad32e084a8b6ccf74
+size 1047722048

SmolVLM2-2.2B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc2437c20ba68ea8f744229d2eeb8ddfe61a40cd9bb05488a5330908c1ae779
+size 1112602688

SmolVLM2-2.2B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1ecc65287b0e885cf9cc3e8c908faa42dc8fda572601472e26b93c7d20c88c
+size 1056110656

SmolVLM2-2.2B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8103fc4075ba1a7a62b2b4adfd556254d7d6fbb4a379dbb929ce94c5df504e41
+size 1261664320

SmolVLM2-2.2B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093de66fb7554d4224456969dc5e101bea83701d5f0d2e8109bd065bb8c073c3
+size 1295087680

SmolVLM2-2.2B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c42afa0ed54b2073f1ab4f769d7ac53c67aff8f2bcc40b2a3373b2acf49518
+size 1261664320

SmolVLM2-2.2B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043eaae371c5fe5ca32c695148f8db781bb14a1f4027d078164b32ff2ab4649c
+size 1488977984

SmolVLM2-2.2B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45dfed3500c79c68aaf504cf4aabe4af6b2dd7067515ce8f5ab35b074a43cc2
+size 1927934016

SmolVLM2-2.2B-Instruct-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28e45e05ff20bcfb70d6a8c3f539fd1bb532ce18329502946a452b718a502a09
+size 3627118656

config.json

@@ -0,0 +1,132 @@
+{
+  "_name_or_path": "/fsx/miquel/smolvlmvideo/checkpoints/final-visionUnfrozen-balanced/checkpoint-6550",
+  "architectures": [
+    "SmolVLMForConditionalGeneration"
+  ],
+  "image_token_id": 49190,
+  "model_type": "smolvlm",
+  "pad_token_id": 128002,
+  "scale_factor": 3,
+  "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "VLlama3ForCausalLM"
+    ],
+    "head_dim": 64,
+    "hidden_size": 2048,
+    "intermediate_size": 8192,
+    "max_position_embeddings": 8192,
+    "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
+    "num_hidden_layers": 24,
+    "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": 3,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 130000,
+    "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_version": "4.47.1",
+  "use_cache": false,
+  "use_reentrant_checkpointing": false,
+  "vision_config": {
+    "image_size": 384,
+    "intermediate_size": 4304,
+    "max_image_size": {
+      "longest_edge": 384
+    },
+    "model_type": "smolvlm_vision",
+    "num_hidden_layers": 27,
+    "patch_size": 14,
+    "size": {
+      "longest_edge": 1920
+    },
+    "tie_word_embeddings": false,
+    "use_base_siglip": false
+  },
+  "vocab_size": 49280
+}