Upload accepted Forge-1-Base checkpoint

README.md

@@ -0,0 +1,7 @@
+# Forge-1-Base
+
+Forge-1-Base is the published Forge-1V / Willow-family checkpoint selected from the rescue run.
+
+Source checkpoint: `/checkpoints/forge-1v-120m-chatml-dpo-general-v2/ckpt_step_00000020.pt`.
+
+This checkpoint preserved the accepted ChatML behavior, identity, basic science, simple arithmetic, and refusal behavior better than the later code-repair experiments. Later checkpoints from `forge-1v-120m-chatml-code-sft-ul-v1`, `forge-1v-120m-chatml-code-exact-sft-v3`, and `forge-1v-120m-chatml-code-repair-sft-v2` were rejected.

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "use_cache": true,
+  "vocab_size": 16386
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:461206ef048e84ee28acdb40886e4a0eed56408cc5b88fd922cad86e2db84bb8
+size 453108576

model.safetensors.index.json

@@ -0,0 +1,153 @@
+{
+  "metadata": {
+    "total_size": 453092352
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.0.input_layernorm.weight": "model.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.1.input_layernorm.weight": "model.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.2.input_layernorm.weight": "model.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.3.input_layernorm.weight": "model.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.4.input_layernorm.weight": "model.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.5.input_layernorm.weight": "model.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.6.input_layernorm.weight": "model.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.7.input_layernorm.weight": "model.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.8.input_layernorm.weight": "model.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.9.input_layernorm.weight": "model.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.10.input_layernorm.weight": "model.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.11.input_layernorm.weight": "model.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.12.input_layernorm.weight": "model.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.13.input_layernorm.weight": "model.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.14.input_layernorm.weight": "model.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+    "model.layers.15.input_layernorm.weight": "model.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+    "model.norm.weight": "model.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>",
+    "<|end|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ]
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "model_max_length": 2048,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>",
+  "pad_token": "<pad>",
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>",
+    "<|end|>",
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|im_start|>system\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'user' %}<|im_start|>user\n{{ message['content'] }}<|im_end|>\n{% elif message['role'] == 'assistant' %}<|im_start|>assistant\n{{ message['content'] }}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}