Update tiny models for FalconH1ForCausalLM

chat_template.jinja

@@ -0,0 +1,17 @@
+{{bos_token}}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "You are a function calling AI model. You are provided with function signature within <tools> </tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions.\n<tools>\n" }}
+    {%- for tool in tools %}[{{- tool | tojson }}]{%- endfor %}
+    {{- "\n</tools>\nFor each function call, return a json object with function name and arguments within <tool_call> </tool_call> tags with the following schema:\n<tool_call>\n{'arguments': <args-dict>, 'name': <function-name>}\n</tool_call>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}{% for message in messages %}{%- if message.role != 'system' %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{%- endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,74 @@
+{
+  "architectures": [
+    "FalconH1ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_in_multiplier": 1.0,
+  "attention_out_multiplier": 1.0,
+  "attn_layer_indices": [
+    1,
+    3
+  ],
+  "attn_rotary_emb": 8,
+  "bos_token_id": 17,
+  "dtype": "float32",
+  "embedding_multiplier": 1.0,
+  "eos_token_id": 11,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "is_decoder": true,
+  "key_multiplier": 1.0,
+  "lm_head_multiplier": 1.0,
+  "mamba_chunk_size": 16,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_head": 64,
+  "mamba_d_ssm": 1024,
+  "mamba_d_state": 16,
+  "mamba_expand": 2,
+  "mamba_n_groups": 1,
+  "mamba_n_heads": 16,
+  "mamba_norm_before_gate": true,
+  "mamba_proj_bias": false,
+  "mamba_rms_norm": false,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_multipliers": [
+    1.0,
+    1.0
+  ],
+  "model_type": "falcon_h1",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 2,
+  "num_logits_to_keep": 1,
+  "pad_token_id": 65536,
+  "projectors_bias": false,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "ssm_in_multiplier": 1.0,
+  "ssm_multipliers": [
+    1.0,
+    1.0,
+    1.0,
+    1.0,
+    1.0
+  ],
+  "ssm_out_multiplier": 1.0,
+  "tie_word_embeddings": false,
+  "time_step_limit": [
+    0.0,
+    {
+      "__float__": "Infinity"
+    }
+  ],
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65537
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 17,
+  "eos_token_id": 11,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 65536,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c9c2146f50b2fc3441ff139a04c057bbddeeadd747a416b059a0a198bb4c23
+size 18615808

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend"
+}